Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists
Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic err...
Saved in:
| Published in | PLoS medicine Vol. 15; no. 11; p. e1002686 |
|---|---|
| Main Authors | , , , , , , , , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Public Library of Science
20.11.2018
Public Library of Science (PLoS) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1549-1676 1549-1277 1549-1676 |
| DOI | 10.1371/journal.pmed.1002686 |
Cover
| Abstract | Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists.
We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution.
In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. |
|---|---|
| AbstractList | Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists. We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution. In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. Background Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists. Methods and findings We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt’s discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4–28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863–0.910), 0.911 (95% CI 0.866–0.947), and 0.985 (95% CI 0.974–0.991), respectively, whereas CheXNeXt’s AUCs were 0.831 (95% CI 0.790–0.870), 0.704 (95% CI 0.567–0.833), and 0.851 (95% CI 0.785–0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825–0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777–0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution. Conclusions In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. In their study, Pranav Rajpurkar and colleagues test a deep learning algorithm that classifies clinically important abnormalities in chest radiographs. Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists. We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution. In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists.BACKGROUNDChest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists.We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution.METHODS AND FINDINGSWe developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution.In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics.CONCLUSIONSIn this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. BackgroundChest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists.Methods and findingsWe developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution.ConclusionsIn this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. Background Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists. Methods and findings We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt’s discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4–28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863–0.910), 0.911 (95% CI 0.866–0.947), and 0.985 (95% CI 0.974–0.991), respectively, whereas CheXNeXt’s AUCs were 0.831 (95% CI 0.790–0.870), 0.704 (95% CI 0.567–0.833), and 0.851 (95% CI 0.785–0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825–0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777–0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution. Conclusions In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics. |
| Audience | Academic |
| Author | Bagul, Aarti Mong, David A. Ball, Robyn L. Langlotz, Curtis P. Mehta, Hershel Rajpurkar, Pranav Zhu, Kaylie Lungren, Matthew P. Seekins, Jayne Patel, Bhavik N. Blankenberg, Francis G. Amrhein, Timothy J. Irvin, Jeremy Duan, Tony Yang, Brandon Zucker, Evan J. Shpanskaya, Katie Ding, Daisy Halabi, Safwan S. Yeom, Kristen W. Ng, Andrew Y. |
| AuthorAffiliation | Edinburgh University, UNITED KINGDOM 2 Department of Medicine, Quantitative Sciences Unit, Stanford University, Stanford, California, United States of America 4 Department of Radiology, Duke University, Durham, North Carolina, United States of America 5 Department of Radiology, University of Colorado, Denver, Colorado, United States of America 3 Department of Radiology, Stanford University, Stanford, California, United States of America 1 Department of Computer Science, Stanford University, Stanford, California, United States of America |
| AuthorAffiliation_xml | – name: 1 Department of Computer Science, Stanford University, Stanford, California, United States of America – name: 5 Department of Radiology, University of Colorado, Denver, Colorado, United States of America – name: 3 Department of Radiology, Stanford University, Stanford, California, United States of America – name: 2 Department of Medicine, Quantitative Sciences Unit, Stanford University, Stanford, California, United States of America – name: 4 Department of Radiology, Duke University, Durham, North Carolina, United States of America – name: Edinburgh University, UNITED KINGDOM |
| Author_xml | – sequence: 1 givenname: Pranav orcidid: 0000-0002-8030-3727 surname: Rajpurkar fullname: Rajpurkar, Pranav – sequence: 2 givenname: Jeremy orcidid: 0000-0002-0395-4403 surname: Irvin fullname: Irvin, Jeremy – sequence: 3 givenname: Robyn L. surname: Ball fullname: Ball, Robyn L. – sequence: 4 givenname: Kaylie surname: Zhu fullname: Zhu, Kaylie – sequence: 5 givenname: Brandon surname: Yang fullname: Yang, Brandon – sequence: 6 givenname: Hershel surname: Mehta fullname: Mehta, Hershel – sequence: 7 givenname: Tony surname: Duan fullname: Duan, Tony – sequence: 8 givenname: Daisy surname: Ding fullname: Ding, Daisy – sequence: 9 givenname: Aarti surname: Bagul fullname: Bagul, Aarti – sequence: 10 givenname: Curtis P. orcidid: 0000-0002-8972-8051 surname: Langlotz fullname: Langlotz, Curtis P. – sequence: 11 givenname: Bhavik N. surname: Patel fullname: Patel, Bhavik N. – sequence: 12 givenname: Kristen W. orcidid: 0000-0001-9860-3368 surname: Yeom fullname: Yeom, Kristen W. – sequence: 13 givenname: Katie orcidid: 0000-0003-2741-4046 surname: Shpanskaya fullname: Shpanskaya, Katie – sequence: 14 givenname: Francis G. surname: Blankenberg fullname: Blankenberg, Francis G. – sequence: 15 givenname: Jayne surname: Seekins fullname: Seekins, Jayne – sequence: 16 givenname: Timothy J. orcidid: 0000-0002-9354-9486 surname: Amrhein fullname: Amrhein, Timothy J. – sequence: 17 givenname: David A. surname: Mong fullname: Mong, David A. – sequence: 18 givenname: Safwan S. orcidid: 0000-0003-1317-984X surname: Halabi fullname: Halabi, Safwan S. – sequence: 19 givenname: Evan J. surname: Zucker fullname: Zucker, Evan J. – sequence: 20 givenname: Andrew Y. surname: Ng fullname: Ng, Andrew Y. – sequence: 21 givenname: Matthew P. surname: Lungren fullname: Lungren, Matthew P. |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30457988$$D View this record in MEDLINE/PubMed |
| BookMark | eNqVk21rFDEQxxep2Af9BqIBQfTFncluNrvXF0KpT4ViQYv0XchlJ7spuWRNckVf-N2da6_SK4cou7DL7G_-M5P_zn6x44OHonjK6JRVDXtzGZbRKzcdF9BNGaWlaMWDYo_VfDZhohE7d953i_2ULpGZ0Rl9VOxWlNfNrG33il_vAEbiQEVvfU9MiEQPkDKJqrOhj2ocSGdV70Oy6ZAckQg5hjSCzvYKiA6LUUWbgifBkDwAOR7g4jNcZKJcH6LNw4LkQMaoMEGvSlwLu9DblNPj4qFRLsGT9fOgOP_w_vz40-T07OPJ8dHpRLcVzRPRdC2IjvNmRucUe4e64Vp3rNOmpU3XGFo2LStZ3bKuQsTQGTOgRVkxNm-qg-L5jezoQpLrg0uyLGu8RcUoEic3RBfUpRyjXaj4UwZl5XUgxF6qiAM4kHPGmFBGgOGGN0y1TUVZVWJorvjcdKj1dl1tOUdvNPgcldsQ3fzi7SD7cCVFyWs0CwVerQVi-L5EM-TCJg3OKQ9hiX2zStQ15RVH9MU9dPt0a6pXOID1JmBdvRKVR7XgtKVt3SI12UL14AGbxH_PWAxv8NMtPF4dLKzemvB6IwGZDD9yr5YpyZOvX_6D_fzv7Nm3TfblHXYA5fKQgltmG3zaBJ_ddfGPfberg8DhDaBxH1IEI7XNaqWDx2CdZFSu9vTWELnaU7neU0zm95Jv9f-a9hsGtUDu |
| CitedBy_id | crossref_primary_10_1002_jmrs_385 crossref_primary_10_1038_s42256_019_0126_0 crossref_primary_10_1038_s41591_024_02850_w crossref_primary_10_1016_j_crad_2019_08_005 crossref_primary_10_2196_10010 crossref_primary_10_1038_s43856_021_00043_x crossref_primary_10_1109_JBHI_2020_2974425 crossref_primary_10_1016_j_msksp_2024_103152 crossref_primary_10_1038_s41598_022_24721_5 crossref_primary_10_1109_TIP_2021_3052711 crossref_primary_10_1097_PRA_0000000000000713 crossref_primary_10_1364_BOE_447392 crossref_primary_10_1001_jamanetworkopen_2022_53820 crossref_primary_10_1109_ACCESS_2020_3010800 crossref_primary_10_1016_j_sasc_2023_200068 crossref_primary_10_1007_s00464_021_08331_2 crossref_primary_10_1007_s00330_020_07044_9 crossref_primary_10_1038_s41591_020_1037_7 crossref_primary_10_1109_TMI_2021_3054817 crossref_primary_10_1371_journal_pmed_1003381 crossref_primary_10_1016_j_jns_2022_120454 crossref_primary_10_3389_fdgth_2022_890759 crossref_primary_10_1038_s41598_019_50137_9 crossref_primary_10_1016_j_bone_2020_115561 crossref_primary_10_1024_1661_8157_a003597 crossref_primary_10_1002_jbio_202300486 crossref_primary_10_1155_2020_8876798 crossref_primary_10_1109_JBHI_2022_3162748 crossref_primary_10_3390_jimaging11030090 crossref_primary_10_7759_cureus_72173 crossref_primary_10_1016_S2589_7500_20_30218_1 crossref_primary_10_1038_s41467_021_24464_3 crossref_primary_10_53685_jshmdc_v5i1_227 crossref_primary_10_3390_biomedicines10030551 crossref_primary_10_32604_cmes_2022_022322 crossref_primary_10_1038_s42256_021_00399_8 crossref_primary_10_1016_j_patrec_2020_12_010 crossref_primary_10_1007_s00330_022_08538_4 crossref_primary_10_1148_radiol_2020192224 crossref_primary_10_1186_s12909_021_02870_x crossref_primary_10_2196_15963 crossref_primary_10_1109_ACCESS_2022_3175311 crossref_primary_10_1148_ryai_230240 crossref_primary_10_1007_s00292_020_00827_3 crossref_primary_10_1016_j_acra_2021_09_013 crossref_primary_10_1148_ryai_2021200267 crossref_primary_10_1007_s10278_024_00990_6 crossref_primary_10_1136_bmjopen_2021_053024 crossref_primary_10_7717_peerj_cs_495 crossref_primary_10_37990_medr_1567242 crossref_primary_10_2214_AJR_22_27487 crossref_primary_10_1038_s42256_022_00536_x crossref_primary_10_1177_0706743721998044 crossref_primary_10_1007_s12194_024_00871_1 crossref_primary_10_1109_JBHI_2022_3220813 crossref_primary_10_1007_s00330_019_06628_4 crossref_primary_10_1016_S2589_7500_20_30219_3 crossref_primary_10_1109_JPROC_2019_2943836 crossref_primary_10_51537_chaos_1326790 crossref_primary_10_1016_j_pacs_2020_100203 crossref_primary_10_1148_radiol_2021202818 crossref_primary_10_1097_ICU_0000000000001111 crossref_primary_10_1186_s12893_024_02646_2 crossref_primary_10_1038_s41598_021_89848_3 crossref_primary_10_1007_s10278_024_01136_4 crossref_primary_10_1167_jov_24_4_6 crossref_primary_10_35713_aic_v5_i2_97317 crossref_primary_10_1016_j_neucom_2021_04_044 crossref_primary_10_1007_s10278_024_01247_y crossref_primary_10_58742_bmj_v2i4_140 crossref_primary_10_3389_fnume_2022_1083245 crossref_primary_10_3390_diagnostics11101868 crossref_primary_10_1016_j_media_2021_102125 crossref_primary_10_1038_s41598_022_25062_z crossref_primary_10_1117_1_JMI_10_4_044504 crossref_primary_10_1117_1_JMI_10_4_044503 crossref_primary_10_1126_sciadv_abb7973 crossref_primary_10_3390_app10093233 crossref_primary_10_1016_j_ibmed_2020_100013 crossref_primary_10_1148_radiol_2019182627 crossref_primary_10_1016_j_health_2023_100206 crossref_primary_10_2174_1875036202114010093 crossref_primary_10_1021_acssensors_4c00636 crossref_primary_10_3389_fonc_2024_1424546 crossref_primary_10_1016_j_ejrad_2020_109188 crossref_primary_10_1053_j_ro_2023_02_001 crossref_primary_10_1016_j_jhazmat_2024_136003 crossref_primary_10_3390_app10186264 crossref_primary_10_1038_s41746_021_00438_z crossref_primary_10_1016_j_compgeo_2023_105452 crossref_primary_10_1007_s42979_021_00881_5 crossref_primary_10_1038_s41598_022_16514_7 crossref_primary_10_1007_s11654_021_00298_9 crossref_primary_10_1038_s41598_025_90607_x crossref_primary_10_3390_diagnostics10060417 crossref_primary_10_1038_s41551_024_01257_9 crossref_primary_10_1136_medhum_2021_012318 crossref_primary_10_11648_j_ijdsa_20241001_12 crossref_primary_10_31436_iiumej_v22i2_1752 crossref_primary_10_1007_s00138_020_01101_5 crossref_primary_10_1016_j_media_2022_102721 crossref_primary_10_2329_perio_63_119 crossref_primary_10_2214_AJR_21_26796 crossref_primary_10_1001_jamanetworkopen_2021_41096 crossref_primary_10_55525_tjst_1222836 crossref_primary_10_35401_2541_9897_2023_26_2_21_27 crossref_primary_10_1007_s41030_020_00110_z crossref_primary_10_3389_fonc_2022_960178 crossref_primary_10_1016_j_bspc_2022_104488 crossref_primary_10_1007_s11042_023_16983_6 crossref_primary_10_1016_j_bspc_2022_104126 crossref_primary_10_1088_1361_6560_ac9510 crossref_primary_10_1016_j_patcog_2020_107613 crossref_primary_10_1038_s41598_022_15341_0 crossref_primary_10_1007_s10278_023_00868_z crossref_primary_10_3348_kjr_2019_0821 crossref_primary_10_3390_sym14051003 crossref_primary_10_1016_j_annemergmed_2024_01_031 crossref_primary_10_1371_journal_pone_0279349 crossref_primary_10_1016_j_acra_2022_04_022 crossref_primary_10_1259_bjro_20190020 crossref_primary_10_3390_s21237966 crossref_primary_10_1117_1_JMI_11_6_064003 crossref_primary_10_1016_j_jvir_2019_05_026 crossref_primary_10_1016_j_ibmed_2020_100014 crossref_primary_10_1155_2021_5592472 crossref_primary_10_1136_bmj_m3164 crossref_primary_10_1007_s00521_023_09207_3 crossref_primary_10_1016_j_jacr_2024_02_034 crossref_primary_10_1371_journal_pone_0281690 crossref_primary_10_1155_2022_6872045 crossref_primary_10_1007_s40846_023_00828_6 crossref_primary_10_1111_exsy_13750 crossref_primary_10_1002_ima_22715 crossref_primary_10_1007_s11042_023_17215_7 crossref_primary_10_1038_s41598_024_53311_w crossref_primary_10_1016_j_ebiom_2020_103106 crossref_primary_10_1038_s41598_024_65703_z crossref_primary_10_1038_s41467_021_22328_4 crossref_primary_10_1038_s41598_020_61055_6 crossref_primary_10_3389_fmed_2023_1280462 crossref_primary_10_1016_j_asoc_2023_110817 crossref_primary_10_1200_EDBK_238891 crossref_primary_10_1038_s41598_022_05572_6 crossref_primary_10_1073_pnas_2001227117 crossref_primary_10_1080_1206212X_2021_1983289 crossref_primary_10_1148_radiol_232746 crossref_primary_10_3348_jksr_2020_0150 crossref_primary_10_1371_journal_pone_0246472 crossref_primary_10_1007_s10462_023_10457_9 crossref_primary_10_1257_jel_20241351 crossref_primary_10_3390_bioengineering11060626 crossref_primary_10_1371_journal_pone_0250952 crossref_primary_10_1016_j_wneu_2023_09_012 crossref_primary_10_1007_s00761_019_00679_4 crossref_primary_10_1148_radiol_2020200165 crossref_primary_10_3389_fradi_2021_713681 crossref_primary_10_1056_NEJMms1904869 crossref_primary_10_1038_s41746_019_0189_7 crossref_primary_10_26633_RPSP_2024_12 crossref_primary_10_26633_RPSP_2024_13 crossref_primary_10_1016_j_cbpa_2021_04_001 crossref_primary_10_1148_ryai_220187 crossref_primary_10_1111_jcpe_13689 crossref_primary_10_1002_mp_16790 crossref_primary_10_1148_ryai_220062 crossref_primary_10_1097_XCS_0000000000000190 crossref_primary_10_1038_s41746_020_0232_8 crossref_primary_10_1038_s41746_022_00698_3 crossref_primary_10_1097_TA_0000000000002320 crossref_primary_10_32604_cmc_2021_014134 crossref_primary_10_1007_s13721_023_00435_0 crossref_primary_10_1016_j_eswa_2020_114054 crossref_primary_10_1016_j_cmpb_2022_107024 crossref_primary_10_1088_1755_1315_794_1_012109 crossref_primary_10_1109_ACCESS_2022_3210468 crossref_primary_10_3390_encyclopedia1010021 crossref_primary_10_2147_CMAR_S279990 crossref_primary_10_1038_s41698_024_00649_z crossref_primary_10_1371_journal_pone_0257884 crossref_primary_10_7759_cureus_41840 crossref_primary_10_1016_j_media_2024_103107 crossref_primary_10_1148_radiol_212482 crossref_primary_10_1038_s41551_023_01049_7 crossref_primary_10_1038_s41598_021_89194_4 crossref_primary_10_1148_ryai_220056 crossref_primary_10_1371_journal_pone_0242013 crossref_primary_10_1038_s41591_020_1034_x crossref_primary_10_1038_s41598_024_60429_4 crossref_primary_10_1007_s00521_023_08606_w crossref_primary_10_1002_ird3_113 crossref_primary_10_3390_diagnostics12071706 crossref_primary_10_1001_jamanetworkopen_2020_17135 crossref_primary_10_48175_IJETIR_1202 crossref_primary_10_1007_s42600_024_00392_1 crossref_primary_10_1186_s13244_019_0738_2 crossref_primary_10_1097_01_CDR_0000804996_57509_75 crossref_primary_10_1148_ryai_220170 crossref_primary_10_1136_bmjopen_2020_044461 crossref_primary_10_3390_app122211750 crossref_primary_10_7759_cureus_50316 crossref_primary_10_1148_ryai_230094 crossref_primary_10_1007_s11042_021_10707_4 crossref_primary_10_1016_j_asoc_2021_108094 crossref_primary_10_1109_ACCESS_2020_2995567 crossref_primary_10_1038_s41598_023_28633_w crossref_primary_10_1016_j_jbi_2020_103528 crossref_primary_10_1016_j_cjca_2024_07_027 crossref_primary_10_1109_TMI_2024_3382042 crossref_primary_10_1093_pcmedi_pbaa028 crossref_primary_10_32604_csse_2022_021438 crossref_primary_10_3892_br_2019_1199 crossref_primary_10_1038_s41598_023_27397_7 crossref_primary_10_1007_s00330_020_07062_7 crossref_primary_10_1007_s00117_022_01097_1 crossref_primary_10_1016_j_patter_2020_100019 crossref_primary_10_1007_s10278_019_00180_9 crossref_primary_10_1016_j_dajour_2024_100460 crossref_primary_10_1109_RBME_2021_3131358 crossref_primary_10_3390_diagnostics14111081 crossref_primary_10_3138_utlj_2023_0002 crossref_primary_10_1111_vru_12901 crossref_primary_10_1136_bjo_2022_322183 crossref_primary_10_1183_16000617_0259_2022 crossref_primary_10_7717_peerj_8693 crossref_primary_10_3390_diagnostics13030574 crossref_primary_10_1038_s41598_022_27211_w crossref_primary_10_1136_bmj_2023_076703 crossref_primary_10_1007_s43681_020_00002_7 crossref_primary_10_1111_jep_13510 crossref_primary_10_1038_s41551_022_00898_y crossref_primary_10_1142_S2196888822500348 crossref_primary_10_1016_j_radi_2022_01_001 crossref_primary_10_1088_1361_6560_ac944d crossref_primary_10_3348_kjr_2022_0588 crossref_primary_10_1109_ACCESS_2023_3249759 crossref_primary_10_1093_jamia_ocaa164 crossref_primary_10_1007_s10140_022_02019_3 crossref_primary_10_1016_j_acra_2020_01_012 crossref_primary_10_1016_j_bspc_2024_107018 crossref_primary_10_1177_20552076221143903 crossref_primary_10_1371_journal_pone_0293967 crossref_primary_10_56977_jicce_2024_22_2_165 crossref_primary_10_1167_tvst_9_2_7 crossref_primary_10_2478_amset_2022_0018 crossref_primary_10_1038_s41598_021_87762_2 crossref_primary_10_1155_2021_5556635 crossref_primary_10_1088_1742_6596_1951_1_012064 crossref_primary_10_1109_ACCESS_2025_3529206 crossref_primary_10_1007_s10462_024_11033_5 crossref_primary_10_3390_sym13081344 crossref_primary_10_1038_s41598_021_93202_y crossref_primary_10_1097_SLA_0000000000004229 crossref_primary_10_1080_17476348_2020_1697853 crossref_primary_10_3390_diagnostics11112114 crossref_primary_10_1038_s41598_024_76608_2 crossref_primary_10_2319_031022_210_1 crossref_primary_10_1089_sur_2021_007 crossref_primary_10_1155_2022_7474304 crossref_primary_10_1016_j_tranon_2024_101894 crossref_primary_10_12688_wellcomeopenres_17164_2 crossref_primary_10_3390_diagnostics14121269 crossref_primary_10_1038_s41467_021_22018_1 crossref_primary_10_1186_s12880_022_00847_w crossref_primary_10_1371_journal_pone_0253239 crossref_primary_10_1007_s00266_021_02698_2 crossref_primary_10_2139_ssrn_3861229 crossref_primary_10_1016_S1470_2045_19_30149_4 crossref_primary_10_3390_diagnostics13203195 crossref_primary_10_1016_j_compbiomed_2022_105466 crossref_primary_10_1038_s41746_023_00811_0 crossref_primary_10_3389_fphy_2024_1445204 crossref_primary_10_1007_s11548_021_02480_4 crossref_primary_10_3389_fbioe_2023_1268543 crossref_primary_10_1145_3625287 crossref_primary_10_1155_2022_7733583 crossref_primary_10_1148_ryai_220012 crossref_primary_10_1148_radiol_2019191293 crossref_primary_10_1371_journal_pone_0264140 crossref_primary_10_1002_cnm_3303 crossref_primary_10_1371_journal_pone_0264383 crossref_primary_10_4236_jcc_2024_126012 crossref_primary_10_1016_j_cmpb_2023_107359 crossref_primary_10_3390_reports2040026 crossref_primary_10_1002_mp_15655 crossref_primary_10_1542_hpeds_2022_007066 crossref_primary_10_7326_M23_1898 crossref_primary_10_1111_ijn_12725 crossref_primary_10_7759_cureus_72646 crossref_primary_10_1371_journal_pone_0232376 crossref_primary_10_1016_j_mcpdig_2024_07_005 crossref_primary_10_1109_ACCESS_2022_3182498 crossref_primary_10_1038_s41568_020_00327_9 crossref_primary_10_21015_vtcs_v10i2_1271 crossref_primary_10_1097_MD_0000000000023568 crossref_primary_10_12688_wellcomeopenres_17164_1 crossref_primary_10_3390_app12073247 crossref_primary_10_1007_s00256_021_03880_y crossref_primary_10_1007_s10278_021_00543_1 crossref_primary_10_1088_1742_6596_2335_1_012023 crossref_primary_10_1007_s00330_020_07544_8 crossref_primary_10_1016_j_isci_2024_110511 crossref_primary_10_18231_j_jchm_2024_022 crossref_primary_10_1038_s41591_021_01614_0 crossref_primary_10_1253_circj_CJ_21_0265 crossref_primary_10_1016_j_ajpath_2021_05_005 crossref_primary_10_3390_diagnostics13020216 crossref_primary_10_1186_s42836_022_00145_4 crossref_primary_10_1016_j_compag_2025_110104 crossref_primary_10_1016_j_cmpb_2019_06_023 crossref_primary_10_1155_2022_9580991 crossref_primary_10_1016_j_chest_2024_01_039 crossref_primary_10_1055_a_2234_8268 crossref_primary_10_1302_0301_620X_101B12_BJJ_2019_0850_R1 crossref_primary_10_1038_s41598_024_66530_y crossref_primary_10_1177_0846537120941671 crossref_primary_10_1016_j_rmr_2023_12_001 crossref_primary_10_48175_IJARSCT_22061 crossref_primary_10_1007_s00595_022_02601_9 crossref_primary_10_3390_geriatrics10020049 crossref_primary_10_3390_diagnostics14242865 crossref_primary_10_1016_j_diii_2022_11_007 crossref_primary_10_1117_1_JMI_10_6_064504 crossref_primary_10_1016_j_jpeds_2023_01_010 crossref_primary_10_1177_10935266211059809 crossref_primary_10_3389_fpubh_2021_640598 crossref_primary_10_1001_jamanetworkopen_2019_7416 crossref_primary_10_1007_s10278_024_01005_0 crossref_primary_10_1016_j_cjca_2021_02_016 crossref_primary_10_1016_j_procs_2020_12_015 crossref_primary_10_1016_j_radi_2022_09_011 crossref_primary_10_1109_JBHI_2020_3023476 crossref_primary_10_1016_j_patcog_2021_107856 crossref_primary_10_1371_journal_pmed_1002707 crossref_primary_10_1186_s12859_020_3503_0 crossref_primary_10_1038_s41598_021_90411_3 crossref_primary_10_3390_app12073341 crossref_primary_10_3934_mbe_2022322 crossref_primary_10_1093_labmed_lmaa023 crossref_primary_10_1148_ryai_230397 crossref_primary_10_32628_CSEIT2410116 crossref_primary_10_1109_ACCESS_2024_3400007 crossref_primary_10_1007_s10639_022_11086_5 crossref_primary_10_56977_jicce_2022_20_3_219 crossref_primary_10_1001_jamanetworkopen_2021_17391 crossref_primary_10_1007_s10554_024_03177_w crossref_primary_10_17946_JRST_2020_43_3_195 crossref_primary_10_1016_j_artmed_2025_103089 crossref_primary_10_1038_s41598_020_74626_4 crossref_primary_10_3390_children11101232 crossref_primary_10_48175_IJARSCT_9564 crossref_primary_10_1002_aic_16260 crossref_primary_10_1007_s11277_024_11587_1 crossref_primary_10_1186_s12890_022_02068_x crossref_primary_10_1148_ryai_2019190177 crossref_primary_10_1007_s00521_023_09147_y crossref_primary_10_1186_s40537_024_01018_0 crossref_primary_10_1007_s42979_021_00720_7 crossref_primary_10_1148_ryai_2019190058 crossref_primary_10_3389_fmed_2023_1329087 crossref_primary_10_4081_jphr_2021_1985 crossref_primary_10_2214_AJR_23_29530 crossref_primary_10_1136_jnis_2023_021022 crossref_primary_10_7759_cureus_49723 crossref_primary_10_1227_ons_0000000000000774 crossref_primary_10_1177_20552076241300229 crossref_primary_10_1155_2022_1306664 crossref_primary_10_3389_fmed_2022_830515 crossref_primary_10_3390_cancers13092162 crossref_primary_10_3934_mbe_2022017 crossref_primary_10_48175_IJARSCT_9697 crossref_primary_10_1109_ACCESS_2022_3172706 crossref_primary_10_1136_bmjopen_2022_061519 crossref_primary_10_1111_resp_13676 crossref_primary_10_2214_AJR_22_28802 crossref_primary_10_3389_fmicb_2020_616971 crossref_primary_10_1055_s_0041_1735470 crossref_primary_10_1097_RLI_0000000000000771 crossref_primary_10_1371_journal_pone_0276545 crossref_primary_10_1016_j_jcrc_2024_154794 crossref_primary_10_1259_bjr_20210688 crossref_primary_10_1007_s11547_024_01770_6 crossref_primary_10_1038_s41746_022_00658_x crossref_primary_10_1016_j_compbiomed_2023_106646 crossref_primary_10_1051_itmconf_20257002022 crossref_primary_10_1016_j_crad_2021_03_021 crossref_primary_10_1071_AH21034 crossref_primary_10_1007_s00330_019_06205_9 crossref_primary_10_1016_j_crad_2020_08_027 crossref_primary_10_1007_s10916_022_01870_8 crossref_primary_10_1016_S2589_7500_19_30123_2 crossref_primary_10_1371_journal_pmed_1002721 crossref_primary_10_1038_s41598_024_76450_6 crossref_primary_10_1080_0886022X_2024_2402075 crossref_primary_10_1016_j_ibmed_2021_100039 crossref_primary_10_3390_diagnostics14131439 crossref_primary_10_1186_s12894_021_00874_9 crossref_primary_10_3390_app10020559 crossref_primary_10_1007_s11042_023_14940_x crossref_primary_10_11622_smedj_2021054 crossref_primary_10_1259_bjr_20210435 crossref_primary_10_1097_MD_0000000000026270 crossref_primary_10_3390_info15040189 crossref_primary_10_1148_ryai_2019180031 crossref_primary_10_2196_28114 crossref_primary_10_1007_s10916_022_01806_2 crossref_primary_10_3390_biomedinformatics4010044 crossref_primary_10_1016_j_media_2020_101773 crossref_primary_10_3171_2019_6_SPINE19463 crossref_primary_10_1016_j_ajoms_2022_02_004 crossref_primary_10_1109_ACCESS_2025_3525806 crossref_primary_10_3390_jpm13091338 crossref_primary_10_1177_0284185120973630 crossref_primary_10_1016_j_patol_2024_04_003 crossref_primary_10_3390_biomedicines11030760 crossref_primary_10_1148_radiol_2019190613 crossref_primary_10_3390_diagnostics14131456 crossref_primary_10_1148_ryai_2019180041 crossref_primary_10_1117_1_JMI_11_6_064503 crossref_primary_10_2139_ssrn_5044890 crossref_primary_10_1007_s00108_023_01604_z crossref_primary_10_3390_e24101434 crossref_primary_10_1016_S2589_7500_19_30124_4 crossref_primary_10_1007_s00330_021_08162_8 crossref_primary_10_1016_j_surg_2020_04_049 crossref_primary_10_1038_s41581_022_00562_3 crossref_primary_10_1007_s12530_023_09565_2 crossref_primary_10_1038_s41598_025_93471_x crossref_primary_10_1001_jamanetworkopen_2019_5600 crossref_primary_10_1097_RTI_0000000000000505 crossref_primary_10_1016_j_vaccine_2024_126370 crossref_primary_10_1007_s10489_020_01900_3 crossref_primary_10_7759_cureus_77391 crossref_primary_10_1097_RTI_0000000000000622 crossref_primary_10_1017_S1047951121004212 crossref_primary_10_1038_s41746_022_00648_z crossref_primary_10_1186_s12880_022_00827_0 crossref_primary_10_3390_life15030498 crossref_primary_10_35940_ijrte_C7897_0912323 crossref_primary_10_1016_j_bspc_2024_107103 crossref_primary_10_1038_s41467_024_51136_9 crossref_primary_10_1055_s_0040_1701985 crossref_primary_10_1148_ryai_210299 crossref_primary_10_26442_20751753_2021_8_201148 crossref_primary_10_2139_ssrn_4073610 crossref_primary_10_32604_cmes_2023_030806 crossref_primary_10_3390_biology11040490 crossref_primary_10_1007_s42979_024_03131_6 crossref_primary_10_38124_ijisrt_IJISRT24JUL1334 crossref_primary_10_1038_s41598_024_68866_x crossref_primary_10_2196_43415 crossref_primary_10_1111_coin_12526 crossref_primary_10_1007_s00330_022_08752_0 crossref_primary_10_1038_s41598_023_37270_2 crossref_primary_10_35712_aig_v2_i2_10 crossref_primary_10_1016_j_ejrad_2022_110447 crossref_primary_10_1001_jamanetworkopen_2022_55113 crossref_primary_10_1038_s41746_020_0266_y crossref_primary_10_1067_j_cpradiol_2022_11_004 crossref_primary_10_1016_j_acra_2021_12_032 crossref_primary_10_1016_S2589_7500_20_30200_4 crossref_primary_10_1148_ryai_210064 crossref_primary_10_1371_journal_pone_0249399 crossref_primary_10_1038_s41597_022_01498_w crossref_primary_10_1097_MOO_0000000000000697 crossref_primary_10_1097_RTI_0000000000000618 crossref_primary_10_1038_s41598_022_22506_4 crossref_primary_10_3390_diagnostics13010131 crossref_primary_10_1016_j_radi_2023_10_014 crossref_primary_10_1155_2020_9258649 crossref_primary_10_1016_j_neunet_2023_02_020 crossref_primary_10_1016_j_yebeh_2021_108047 crossref_primary_10_1016_j_compbiomed_2024_108922 crossref_primary_10_1109_TMI_2024_3419134 crossref_primary_10_1007_s00521_024_10527_1 crossref_primary_10_1038_s41598_021_93967_2 crossref_primary_10_1177_11779322211037770 crossref_primary_10_1016_j_jidi_2020_12_001 crossref_primary_10_1016_j_rcl_2021_07_006 crossref_primary_10_1097_RLI_0000000000000813 crossref_primary_10_1007_s00408_023_00655_1 crossref_primary_10_1038_s41598_021_00018_x crossref_primary_10_3390_app10082908 crossref_primary_10_7759_cureus_11137 crossref_primary_10_1021_acs_iecr_2c01982 crossref_primary_10_3389_fgene_2023_1004481 crossref_primary_10_3348_jksr_2019_80_2_176 crossref_primary_10_3390_app11062751 crossref_primary_10_1016_j_media_2020_101855 crossref_primary_10_1063_5_0040315 crossref_primary_10_1109_TMI_2020_2974159 crossref_primary_10_3389_fnagi_2020_603790 crossref_primary_10_1002_inpr_522 crossref_primary_10_1186_s12880_021_00625_0 crossref_primary_10_1109_TNNLS_2021_3105384 crossref_primary_10_1007_s00259_019_04374_9 crossref_primary_10_25259_IJDVL_518_19 crossref_primary_10_3390_s22083049 crossref_primary_10_1097_RLI_0000000000000707 crossref_primary_10_17816_socm106054 crossref_primary_10_1007_s11042_023_16555_8 crossref_primary_10_1038_s41746_022_00709_3 crossref_primary_10_1016_j_molmed_2024_11_009 crossref_primary_10_1016_j_crbiot_2023_100164 crossref_primary_10_1007_s10140_020_01767_4 crossref_primary_10_3390_electronics9010190 crossref_primary_10_3390_math10193646 crossref_primary_10_1016_j_nec_2022_02_012 crossref_primary_10_1016_j_jcf_2019_04_016 crossref_primary_10_1016_j_patrec_2019_11_013 crossref_primary_10_1183_13993003_00625_2021 crossref_primary_10_3390_diagnostics13010076 crossref_primary_10_1148_ryai_2021210136 crossref_primary_10_1371_journal_pone_0273445 crossref_primary_10_1177_0271678X211029178 crossref_primary_10_1016_j_jid_2020_01_019 crossref_primary_10_1148_ryai_2021210014 crossref_primary_10_1007_s10278_024_01309_1 crossref_primary_10_1007_s42058_021_00078_y crossref_primary_10_1016_j_bspc_2020_102365 crossref_primary_10_1007_s12539_023_00562_2 crossref_primary_10_1016_j_compbiomed_2023_107569 crossref_primary_10_3390_diagnostics12092084 crossref_primary_10_1007_s42979_024_02751_2 crossref_primary_10_3389_fmed_2022_945698 crossref_primary_10_1109_ACCESS_2024_3454537 crossref_primary_10_3390_jcm13144042 crossref_primary_10_4028_www_scientific_net_JBBBE_45_57 crossref_primary_10_1111_2041_210X_14001 crossref_primary_10_1186_s13244_020_00955_7 crossref_primary_10_1007_s10462_024_10714_5 crossref_primary_10_1016_j_cjca_2021_09_028 crossref_primary_10_7717_peerj_12598 crossref_primary_10_36740_EmeMS202402109 crossref_primary_10_3390_jcm13144180 crossref_primary_10_1111_1754_9485_13105 crossref_primary_10_1063_5_0188187 crossref_primary_10_3390_computers13120343 crossref_primary_10_1016_j_media_2020_101839 crossref_primary_10_1016_j_sciaf_2023_e01989 crossref_primary_10_3390_tomography9020052 crossref_primary_10_1002_widm_1510 crossref_primary_10_1371_journal_pone_0236378 crossref_primary_10_1016_j_ecoleng_2020_105816 crossref_primary_10_1109_ACCESS_2023_3283216 crossref_primary_10_1016_j_phrs_2023_106706 crossref_primary_10_1016_j_jacr_2019_05_048 crossref_primary_10_1007_s00259_021_05270_x crossref_primary_10_2339_politeknik_1395811 crossref_primary_10_1007_s00247_021_05146_0 crossref_primary_10_1371_journal_pone_0229963 crossref_primary_10_1183_13993003_03061_2020 crossref_primary_10_1007_s10278_023_00882_1 crossref_primary_10_1007_s13755_020_00116_6 crossref_primary_10_1016_j_jet_2025_105970 crossref_primary_10_1016_j_arbres_2020_10_008 crossref_primary_10_1016_j_neucom_2020_03_127 crossref_primary_10_1016_j_compeleceng_2022_108325 crossref_primary_10_1007_s00120_020_01272_z crossref_primary_10_1109_ACCESS_2021_3133338 crossref_primary_10_1109_TMI_2020_2992546 crossref_primary_10_1038_s41746_021_00393_9 crossref_primary_10_1016_j_scib_2023_03_031 crossref_primary_10_1038_s41598_024_58220_6 crossref_primary_10_7759_cureus_58607 crossref_primary_10_1007_s00204_021_03188_9 crossref_primary_10_1016_j_oor_2024_100365 crossref_primary_10_61969_jai_1469589 crossref_primary_10_1167_tvst_9_2_64 crossref_primary_10_1021_acs_iecr_1c04669 crossref_primary_10_1080_0142159X_2019_1679361 crossref_primary_10_1177_2058460119830222 crossref_primary_10_1016_j_neucom_2021_08_157 crossref_primary_10_1016_j_ejrad_2020_108925 crossref_primary_10_1007_s00330_023_10124_1 crossref_primary_10_1155_2020_8828855 crossref_primary_10_3389_fmed_2024_1445069 crossref_primary_10_1148_radiol_221894 crossref_primary_10_37699_2308_7005_4_2024_21 crossref_primary_10_1038_s41598_020_77924_z crossref_primary_10_1007_s00330_020_06771_3 crossref_primary_10_1007_s00223_022_01035_2 crossref_primary_10_3390_ai6020037 crossref_primary_10_1007_s00264_024_06369_0 crossref_primary_10_3390_ai6020038 crossref_primary_10_1097_CCM_0000000000004397 crossref_primary_10_30897_ijegeo_710913 crossref_primary_10_1016_j_media_2021_102087 crossref_primary_10_1038_s41598_023_41463_0 crossref_primary_10_3389_fonc_2022_938413 crossref_primary_10_3389_fpsyg_2021_710982 crossref_primary_10_1111_1754_9485_13274 crossref_primary_10_2196_59045 crossref_primary_10_1109_ACCESS_2020_3010287 crossref_primary_10_1038_s41597_023_02102_5 crossref_primary_10_3390_forecast6020022 crossref_primary_10_1001_jamadermatol_2019_3807 crossref_primary_10_1016_j_jacr_2019_05_010 crossref_primary_10_1016_j_rcl_2021_11_011 crossref_primary_10_1016_j_cjca_2021_12_019 crossref_primary_10_1055_s_0040_1718584 crossref_primary_10_1016_j_eswa_2025_126806 crossref_primary_10_1038_s41746_020_0273_z crossref_primary_10_3390_jimaging9070128 crossref_primary_10_1007_s11548_022_02607_1 crossref_primary_10_1111_1754_9485_13393 crossref_primary_10_1111_1754_9485_13273 crossref_primary_10_1177_02841851231202323 crossref_primary_10_1016_j_cmpb_2022_106651 crossref_primary_10_1109_ACCESS_2021_3095312 crossref_primary_10_1007_s13755_021_00169_1 crossref_primary_10_3390_jcm9123860 crossref_primary_10_3389_fmed_2021_706794 crossref_primary_10_1259_bjr_20200975 crossref_primary_10_1186_s13244_019_0830_7 crossref_primary_10_14316_pmp_2019_30_2_39 crossref_primary_10_4103_jdmimsu_jdmimsu_303_20 crossref_primary_10_1051_shsconf_202213903008 crossref_primary_10_1136_bmjinnov_2020_000593 crossref_primary_10_1016_j_semcancer_2020_12_005 crossref_primary_10_1038_s41467_021_25503_9 crossref_primary_10_1016_j_media_2020_101911 crossref_primary_10_2196_39565 crossref_primary_10_1002_mp_16188 crossref_primary_10_1002_psp4_12418 crossref_primary_10_1016_j_ejrad_2019_108774 crossref_primary_10_1177_0846537120971745 crossref_primary_10_1097_TA_0000000000004030 crossref_primary_10_1016_j_jacr_2019_05_007 crossref_primary_10_1371_journal_pone_0261307 crossref_primary_10_1002_jmri_27266 crossref_primary_10_48084_etasr_3503 crossref_primary_10_1097_OGX_0000000000000902 crossref_primary_10_1016_j_patrec_2019_11_040 crossref_primary_10_2147_IDR_S404786 crossref_primary_10_2196_39536 crossref_primary_10_2196_38325 crossref_primary_10_2147_IJGM_S325609 crossref_primary_10_32604_cmc_2024_051420 crossref_primary_10_1148_ryai_2021200190 crossref_primary_10_1097_RTI_0000000000000485 crossref_primary_10_1016_j_jacr_2023_02_031 crossref_primary_10_1016_j_jacr_2021_08_018 crossref_primary_10_3390_cancers15225389 crossref_primary_10_1007_s11042_024_18975_6 crossref_primary_10_3390_jcm10020254 crossref_primary_10_1007_s00330_019_06214_8 crossref_primary_10_1016_j_media_2022_102470 crossref_primary_10_1038_s41551_022_00936_9 crossref_primary_10_1016_j_jacr_2019_05_036 crossref_primary_10_1080_08164622_2021_2022961 crossref_primary_10_5664_jcsm_8388 crossref_primary_10_1097_RLI_0000000000000775 crossref_primary_10_1109_JBHI_2024_3362243 crossref_primary_10_1016_j_athoracsur_2019_09_042 crossref_primary_10_3390_electronics12173551 crossref_primary_10_1136_bmj_m3210 crossref_primary_10_1007_s00330_019_06589_8 crossref_primary_10_1038_s41746_020_00341_z crossref_primary_10_1038_s41467_024_45599_z crossref_primary_10_3389_fnins_2022_889808 crossref_primary_10_1080_15265161_2022_2040647 crossref_primary_10_1007_s11042_022_13486_8 crossref_primary_10_1016_j_engappai_2024_108516 crossref_primary_10_3390_jcm13020344 crossref_primary_10_1111_1754_9485_13282 crossref_primary_10_1016_j_jneumeth_2021_109098 crossref_primary_10_1115_1_4062808 crossref_primary_10_1259_bjr_20210979 crossref_primary_10_1109_JIOT_2021_3126471 crossref_primary_10_1148_radiol_212631 crossref_primary_10_1148_radiol_2021210902 crossref_primary_10_3390_diagnostics14050500 crossref_primary_10_1016_j_healun_2021_02_016 crossref_primary_10_31083_j_rcm2312402 crossref_primary_10_1007_s10140_021_01954_x crossref_primary_10_1007_s13139_023_00821_6 crossref_primary_10_1148_ryai_2021200172 crossref_primary_10_1117_1_JMI_8_6_064501 |
| Cites_doi | 10.4187/respcare.01475 10.1109/CVPR.2017.243 10.1136/bmj.j4683 10.1001/jama.2016.17216 10.1177/001316446002000104 10.1371/journal.pmed.0030442 10.1109/TMI.2016.2536809 10.1259/bjr/28883951 10.1109/CVPR.2016.319 10.1097/00004424-198503000-00004 10.1109/ISBI.2015.7163871 10.1007/s10278-016-9937-2 10.1097/00004424-199008000-00004 10.1097/RLI.0000000000000341 10.1148/radiol.2017162326 10.1259/bjr.74.886.740949 10.1378/chest.10-1302 10.1214/aoms/1177706443 10.1002/acp.2869 10.1097/00004424-199009000-00006 10.1068/p090339 10.1016/j.amjmed.2006.10.025 10.1038/nature21056 10.1001/jama.2017.14585 10.1186/1471-2105-12-77 10.4103/jcis.JCIS_75_16 10.1109/CVPR.2017.369 10.5588/ijtld.13.0325 10.1016/j.jacr.2011.01.011 10.1109/CVPR.2009.5206848 10.1148/radiol.14131315 10.1097/RTI.0b013e3181f240bc 10.1007/s10278-012-9565-4 |
| ContentType | Journal Article |
| Copyright | COPYRIGHT 2018 Public Library of Science 2018 Rajpurkar et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2018 Rajpurkar et al 2018 Rajpurkar et al |
| Copyright_xml | – notice: COPYRIGHT 2018 Public Library of Science – notice: 2018 Rajpurkar et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2018 Rajpurkar et al 2018 Rajpurkar et al |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM IOV ISN ISR 3V. 7TK 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA CZK |
| DOI | 10.1371/journal.pmed.1002686 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Opposing Viewpoints in Context Gale In Context: Canada Gale In Context: Science ProQuest Central (Corporate) Neurosciences Abstracts ProQuest Central Health & Medical Collection (via ProQuest) ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) ProQuest Health & Medical Collection Proquest Medical Database ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals PLoS Medicine |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Neurosciences Abstracts ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | Publicly Available Content Database MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database – sequence: 4 dbid: BENPR name: ProQuest Central url: http://www.proquest.com/pqcentral?accountid=15518 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Computer Science |
| DocumentTitleAlternate | Deep learning for chest radiograph diagnosis |
| EISSN | 1549-1676 |
| ExternalDocumentID | 2252256310 oai_doaj_org_article_b1116af6ef4f471a87301326afba4bfd PMC6245676 A564080858 30457988 10_1371_journal_pmed_1002686 |
| Genre | Validation Study Comparative Study Research Support, Non-U.S. Gov't Journal Article |
| GeographicLocations | United States--US California |
| GeographicLocations_xml | – name: United States--US – name: California |
| GrantInformation_xml | – fundername: NIBIB NIH HHS grantid: R01 EB000898 |
| GroupedDBID | --- 123 29O 2WC 53G 5VS 7X7 88E 8FI 8FJ AAFWJ AAUCC AAWOE AAWTL AAYXX ABDBF ABUWG ACGFO ACIHN ACPRK ACUHS ADBBV ADRAZ AEAQA AENEX AFKRA AFPKN AFRAH AFXKF AHMBA AKRSQ ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS B0M BAWUL BCNDV BENPR BPHCQ BVXVI BWKFM CCPQU CITATION CS3 DIK DU5 E3Z EAP EAS EBD EBS EJD EMK EMOBN ESX F5P FPL FYUFA GROUPED_DOAJ GX1 HMCUK HYE IAO IHR IHW INH INR IOF IOV IPO ISN ISR ITC KQ8 M1P M48 MK0 O5R O5S OK1 OVT P2P PHGZM PHGZT PIMPY PQQKQ PROAC PSQYO PV9 RNS RPM RZL SV3 TR2 TUS UKHRP WOW XSB YZZ ~8M ADXHL CGR CUY CVF ECM EIF H13 IPNFZ NPM PJZUB PPXIY RIG WOQ PMFND 3V. 7TK 7XB 8FK AZQEC DWQXO K9. PKEHL PQEST PQUKI PRINS 7X8 PUEGO 5PM AAPBV ABPTK BCGST CZK ICW M~E |
| ID | FETCH-LOGICAL-c830t-67d8e6d44790b0045e574ccd1dcf807d7f0278121581d30b0f091fec62311b73 |
| IEDL.DBID | M48 |
| ISSN | 1549-1676 1549-1277 |
| IngestDate | Sun Jun 04 13:13:08 EDT 2023 Wed Aug 27 01:25:33 EDT 2025 Thu Aug 21 18:29:06 EDT 2025 Fri Sep 05 07:53:00 EDT 2025 Fri Jul 25 20:01:36 EDT 2025 Tue Jun 17 21:33:25 EDT 2025 Thu Jun 12 23:50:44 EDT 2025 Tue Jun 10 20:47:16 EDT 2025 Fri Jun 27 03:56:04 EDT 2025 Fri Jun 27 05:11:27 EDT 2025 Fri Jun 27 03:50:37 EDT 2025 Thu May 22 21:21:11 EDT 2025 Mon Jul 21 05:21:51 EDT 2025 Thu Apr 24 22:56:08 EDT 2025 Tue Jul 01 03:17:38 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 11 |
| Language | English |
| License | This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Creative Commons Attribution License |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c830t-67d8e6d44790b0045e574ccd1dcf807d7f0278121581d30b0f091fec62311b73 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23 ObjectType-Undefined-3 These authors share first authorship on, and contributed equally to, this work. I have read the journal's policy and the authors of this manuscript have the following competing interests: CPL holds shares in whiterabbit.ai and Nines.ai, is on the Advisory Board of Nuance Communications and on the Board of Directors for the Radiological Society of North America, and has other research support from Philips, GE Healthcare, and Philips Healthcare. MPL holds shares in and serves on the Advisory Board for Nines.ai. None of these organizations have a financial interest in the results of this study. |
| ORCID | 0000-0003-2741-4046 0000-0002-0395-4403 0000-0003-1317-984X 0000-0001-9860-3368 0000-0002-8972-8051 0000-0002-9354-9486 0000-0002-8030-3727 |
| OpenAccessLink | http://journals.scholarsportal.info/openUrl.xqy?doi=10.1371/journal.pmed.1002686 |
| PMID | 30457988 |
| PQID | 2252256310 |
| PQPubID | 1436338 |
| ParticipantIDs | plos_journals_2252256310 doaj_primary_oai_doaj_org_article_b1116af6ef4f471a87301326afba4bfd pubmedcentral_primary_oai_pubmedcentral_nih_gov_6245676 proquest_miscellaneous_2136550434 proquest_journals_2252256310 gale_infotracmisc_A564080858 gale_infotracgeneralonefile_A564080858 gale_infotracacademiconefile_A564080858 gale_incontextgauss_ISR_A564080858 gale_incontextgauss_ISN_A564080858 gale_incontextgauss_IOV_A564080858 gale_healthsolutions_A564080858 pubmed_primary_30457988 crossref_citationtrail_10_1371_journal_pmed_1002686 crossref_primary_10_1371_journal_pmed_1002686 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 20181120 |
| PublicationDateYYYYMMDD | 2018-11-20 |
| PublicationDate_xml | – month: 11 year: 2018 text: 20181120 day: 20 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: San Francisco – name: San Francisco, CA USA |
| PublicationTitle | PLoS medicine |
| PublicationTitleAlternate | PLoS Med |
| PublicationYear | 2018 |
| Publisher | Public Library of Science Public Library of Science (PLoS) |
| Publisher_xml | – name: Public Library of Science – name: Public Library of Science (PLoS) |
| References | S Bastawrous (ref32) 2017; 30 ref15 ref14 A Esteva (ref4) 2017; 542 T Donovan (ref34) 2013; 27 DP Carmody (ref37) 1980; 9 M Gamer (ref23) 2012 ref16 ref18 B Ehteshami Bejnordi (ref5) 2017; 318 V Gulshan (ref3) 2016; 316 OJ Dunn (ref21) 1958; 29 CD Mathers (ref2) 2006; 3 M Meziane (ref44) 2012; 27 P Goddard (ref33) 2001; 74 M Monney (ref42) 2005; 135 G Laifer (ref41) 2007; 120 Z Mor (ref39) 2015; 17 J Cohen (ref19) 1960; 20 ref7 S Raoof (ref1) 2012; 141 HL Kundel (ref38) 1990; 25 JC Bass (ref36) 1990; 25 (ref22) 2017 S Schalekamp (ref46) 2014; 272 N Dellios (ref47) 2017; 7 P Lakhani (ref9) 2017; 284 E Pesce (ref12) 2017 M Gopal (ref43) 2010; 5 X Robin (ref26) 2011; 12 CT Ekstrøm (ref27) 2018 Z Mor (ref40) 2012; 57 M Cicero (ref6) 2017; 52 RD Welling (ref30) 2011; 8 A Rimmer (ref31) 2017; 359 L Yao (ref11) 2017 R Tibshirani (ref20) 1994 A Canty (ref24) 2017 RD Novak (ref45) 2013; 26 DP Kingma (ref17) 2014 Q Guan (ref13) 2018 MC Meyer (ref25) 2017 E Potchen (ref50) 1979; 14 AAA Setio (ref10) 2016; 35 H Wickham (ref28) 2009 DJ Manning (ref35) 2004; 77 K Berbaum (ref49) 1985; 20 B Auguie (ref29) 2017 P Maduskar (ref8) 2013; 17 S Quadrelli (ref48) 2015 |
| References_xml | – volume: 57 start-page: 1137 issue: 7 year: 2012 ident: ref40 article-title: Chest radiography validity in screening pulmonary tuberculosis in immigrants from a high-burden country publication-title: Respir Care doi: 10.4187/respcare.01475 – ident: ref15 doi: 10.1109/CVPR.2017.243 – year: 2009 ident: ref28 – year: 2014 ident: ref17 article-title: Adam: A Method for Stochastic Optimization publication-title: Proc 3rd Int Conf Learn Represent ICLR – volume: 359 start-page: j4683 year: 2017 ident: ref31 article-title: Radiologist shortage leaves patient care at risk, warns royal college publication-title: BMJ doi: 10.1136/bmj.j4683 – volume: 316 year: 2016 ident: ref3 article-title: Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs publication-title: JAMA doi: 10.1001/jama.2016.17216 – year: 2017 ident: ref11 article-title: Learning to diagnose from scratch by exploiting dependencies among labels publication-title: ArXiv171010501 Cs – volume: 20 start-page: 37 issue: 1 year: 1960 ident: ref19 article-title: A Coefficient of Agreement for Nominal Scales publication-title: Educ Psychol Meas doi: 10.1177/001316446002000104 – volume: 17 start-page: 11 issue: 1 year: 2015 ident: ref39 article-title: The yield of tuberculosis screening of undocumented migrants from the Horn of Africa based on chest radiography publication-title: Isr Med Assoc J IMAJ – year: 2017 ident: ref29 article-title: gridExtra: Miscellaneous Functions for “Grid” Graphics – volume: 3 start-page: e442 issue: 11 year: 2006 ident: ref2 article-title: Projections of Global Mortality and Burden of Disease from 2002 to 2030 publication-title: PLOS Med doi: 10.1371/journal.pmed.0030442 – volume: 35 start-page: 1160 issue: 5 year: 2016 ident: ref10 article-title: Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2016.2536809 – year: 1994 ident: ref20 – volume: 77 start-page: 231 issue: 915 year: 2004 ident: ref35 article-title: Detection or decision errors? Missed lung cancer from the posteroanterior chest radiograph publication-title: Br J Radiol doi: 10.1259/bjr/28883951 – year: 2017 ident: ref12 article-title: Learning to detect chest radiographs containing lung nodules using visual attention networks publication-title: ArXiv171200996 Cs Stat – ident: ref18 doi: 10.1109/CVPR.2016.319 – volume: 20 start-page: 124 issue: 2 year: 1985 ident: ref49 article-title: The effect of comparison films upon resident interpretation of pediatric chest radiographs publication-title: Invest Radiol doi: 10.1097/00004424-198503000-00004 – volume: 14 start-page: 404 year: 1979 ident: ref50 article-title: Effect of clinical history data on chest film interpretation-direction or distraction publication-title: Invest Radiol – ident: ref7 doi: 10.1109/ISBI.2015.7163871 – volume: 30 start-page: 309 issue: 3 year: 2017 ident: ref32 article-title: Improving Patient Safety: Avoiding Unread Imaging Exams in the National VA Enterprise Electronic Health Record publication-title: J Digit Imaging doi: 10.1007/s10278-016-9937-2 – volume: 25 start-page: 890 issue: 8 year: 1990 ident: ref38 article-title: Computer-displayed eye position as a visual aid to pulmonary nodule interpretation publication-title: Invest Radiol doi: 10.1097/00004424-199008000-00004 – volume: 52 start-page: 281 issue: 5 year: 2017 ident: ref6 article-title: Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs publication-title: Invest Radiol doi: 10.1097/RLI.0000000000000341 – volume: 284 start-page: 574 issue: 2 year: 2017 ident: ref9 article-title: Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks publication-title: Radiology doi: 10.1148/radiol.2017162326 – volume: 74 start-page: 949 issue: 886 year: 2001 ident: ref33 article-title: Error in radiology publication-title: Br J Radiol doi: 10.1259/bjr.74.886.740949 – volume: 5 start-page: 1233 issue: 8 year: 2010 ident: ref43 article-title: Screening for lung cancer with low-dose computed tomography: a systematic review and meta-analysis of the baseline findings of randomized controlled trials publication-title: J Thorac Oncol Off Publ Int Assoc Study Lung Cancer – volume: 141 start-page: 545 issue: 2 year: 2012 ident: ref1 article-title: Interpretation of plain chest roentgenogram publication-title: Chest doi: 10.1378/chest.10-1302 – volume: 29 start-page: 1095 issue: 4 year: 1958 ident: ref21 article-title: Estimation of the Means of Dependent Variables publication-title: Ann Math Stat doi: 10.1214/aoms/1177706443 – volume: 27 start-page: 43 issue: 1 year: 2013 ident: ref34 article-title: Looking for Cancer: Expertise Related Differences in Searching and Decision Making publication-title: Appl Cogn Psychol doi: 10.1002/acp.2869 – volume: 135 start-page: 469 issue: 31–32 year: 2005 ident: ref42 article-title: Active and passive screening for tuberculosis in Vaud Canton, Switzerland publication-title: Swiss Med Wkly – year: 2018 ident: ref27 article-title: MESS: Miscellaneous Esoteric Statistical Scripts – volume: 25 start-page: 994 issue: 9 year: 1990 ident: ref36 article-title: Visual skill. Correlation with detection of solitary pulmonary nodules publication-title: Invest Radiol doi: 10.1097/00004424-199009000-00006 – volume: 9 start-page: 339 issue: 3 year: 1980 ident: ref37 article-title: An analysis of perceptual and cognitive factors in radiographic interpretation publication-title: Perception doi: 10.1068/p090339 – volume: 120 start-page: 350 issue: 4 year: 2007 ident: ref41 article-title: TB in a low-incidence country: differences between new immigrants, foreign-born residents and native residents publication-title: Am J Med doi: 10.1016/j.amjmed.2006.10.025 – volume: 542 start-page: 115 issue: 7639 year: 2017 ident: ref4 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature doi: 10.1038/nature21056 – volume: 318 start-page: 2199 issue: 22 year: 2017 ident: ref5 article-title: Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer publication-title: JAMA doi: 10.1001/jama.2017.14585 – year: 2015 ident: ref48 article-title: Clinical Characteristics and Prognosis of Incidentally Detected Lung Cancers publication-title: Int J Surg Oncol – volume: 12 start-page: 77 year: 2011 ident: ref26 article-title: pROC: an open-source package for R and S+ to analyze and compare ROC curves publication-title: BMC Bioinformatics doi: 10.1186/1471-2105-12-77 – volume: 7 year: 2017 ident: ref47 article-title: Computer-aided Detection Fidelity of Pulmonary Nodules in Chest Radiograph publication-title: J Clin Imaging Sci doi: 10.4103/jcis.JCIS_75_16 – year: 2017 ident: ref24 article-title: boot: Bootstrap R (S-Plus) Functions – ident: ref14 doi: 10.1109/CVPR.2017.369 – year: 2018 ident: ref13 article-title: Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification – volume: 17 start-page: 1613 issue: 12 year: 2013 ident: ref8 article-title: Detection of tuberculosis using digital chest radiography: automated reading vs. interpretation by clinical officers publication-title: Int J Tuberc Lung Dis Off J Int Union Tuberc Lung Dis doi: 10.5588/ijtld.13.0325 – volume: 8 start-page: 556 issue: 8 year: 2011 ident: ref30 article-title: White Paper Report of the 2010 RAD-AID Conference on International Radiology for Developing Countries: Identifying Sustainable Strategies for Imaging Services in the Developing World publication-title: J Am Coll Radiol JACR doi: 10.1016/j.jacr.2011.01.011 – year: 2017 ident: ref22 – ident: ref16 doi: 10.1109/CVPR.2009.5206848 – volume: 272 start-page: 252 issue: 1 year: 2014 ident: ref46 article-title: Computer-aided detection improves detection of pulmonary nodules in chest radiographs beyond the support by bone-suppressed images publication-title: Radiology doi: 10.1148/radiol.14131315 – volume: 27 start-page: 58 issue: 1 year: 2012 ident: ref44 article-title: A comparison of four versions of a computer-aided detection system for pulmonary nodules on chest radiographs. publication-title: J Thorac Imaging doi: 10.1097/RTI.0b013e3181f240bc – volume: 26 start-page: 651 issue: 4 year: 2013 ident: ref45 article-title: Comparison of Computer-Aided Detection (CAD) Effectiveness in Pulmonary Nodule Identification Using Different Methods of Bone Suppression in Chest Radiographs publication-title: J Digit Imaging doi: 10.1007/s10278-012-9565-4 – year: 2012 ident: ref23 article-title: irr: Various Coefficients of Interrater Reliability and Agreement – year: 2017 ident: ref25 article-title: ConSpline: Partial Linear Least-Squares Regression using Constrained Splines |
| RelatedPersons | Ng, Matthew |
| RelatedPersons_xml | – fullname: Ng, Matthew |
| SSID | ssj0029090 |
| Score | 2.7117987 |
| Snippet | Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people... Background Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of... In their study, Pranav Rajpurkar and colleagues test a deep learning algorithm that classifies clinically important abnormalities in chest radiographs. BackgroundChest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of... Background Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of... |
| SourceID | plos doaj pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | e1002686 |
| SubjectTerms | Algorithms Analysis Artificial neural networks Atelectasis Authorship Chest Chest x-rays Clinical Competence Comparative analysis Computer and Information Sciences Computer science Data mining Datasets Decision making Deep Learning Diabetic retinopathy Diagnosis, Computer-Assisted - methods Effusion Emphysema Hernia Hiatal hernia Humans Learning Lung cancer Lung diseases Lung nodules Machine learning Medical errors Medical imaging Medical imaging equipment Medicine and Health Sciences Methods Network architectures Neural networks Ng, Matthew Nodules Patients People and Places Physical Sciences Pleural effusion Pneumonia Pneumonia - diagnostic imaging Practice Predictive Value of Tests Radiographic Image Interpretation, Computer-Assisted - methods Radiography Radiography, Thoracic - methods Radiologists Radiology Reproducibility of Results Research and Analysis Methods Retrospective Studies Software Statistical analysis Supervision Systematic review Thorax Tuberculosis Visualization |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9NAEF6hHBAXxLuGFhaE4GRqO2uvzS0UqoLUIEFBuVn7TCIFO4qdY_87M96NFaNI7QHJh8j72VFm9vFtduYbQt6mBbIM2JaYjCchK7QKRSJ4mIhUMyNSKzs5hstpdvGLfZuls71SXxgT5uSBneFOJQzGTNjMWGZhIhU5dkngHMJKwaTVOPtGRbTbTPmtVhF1_66g_lgYJ5z7pLkxj0-9jz6sYbXpBEgzzKPeW5Q67f5-hh6tV3VziH7-G0W5tyydPyD3PZ-kE_c7HpI7pnpE7l76E_PH5PqzMWvqa0PMKVBU2pXIohuhl06ummoXbrdsPtIJ3Zh2U-_yL6nqyxTS2lIgi_RsYWZTM2upWM3rzbJd_KFtTX2yFX5F92KXWNQ8IVfnX67OLkJfciFU-Thqw4zr3GSaMV5EOKBTk3KmlI61snnENbd4UomKFMBzxwCxwDesUUCi4ljy8VMyqurKHBEqgXcBPuFSF6xQUkbSwIfIgL0F53FAxjuTl8rLkWNVjFXZnbFx2JY4C5boqNI7KiBh_9TayXHcgP-E3uyxKKbd3YAuVvouVt7UxQLyCvtC6TJT-ymhnKQZA8Kdp3lA3nQIFNSoMGJnLrZNU379_vsWoJ_T24B-DEDvPcjWYDMlfCoFWB7VvAbIdwPk3GmZHwIeD4AwyahB8xGOg52NmxKWAbgy2BzAk7uxcbj5dd-ML8WYvsrUW8BghCUK6LGAPHNDqfcTnt-jkl5A-GCQDRw5bKmWi04dPcOjfJ49_x-ef0HuAUHOMfc0iY7JqN1szQmQ0Fa-7Oabvwp2hLs priority: 102 providerName: Directory of Open Access Journals – databaseName: ProQuest Central Health & Medical Collection (via ProQuest) dbid: 7X7 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9NAEF5BkBAXHuVRQ4EFITi5tR171-aCQqEqSA0SFJSbtd5HEinYIXaO_Hdm1mu3RhFUyiHKfrajHc_st4_5hpBXSYYsA6YlmvHIjzMlfREJ7kciUbEWiSmsHMPZlJ1-jz_PkplbcKvdscouJtpArSqJa-RH8N7BhwEbebf-5WPVKNxddSU0rpMbITARLN3AZxcTriywayyoQuaHEecudW7MwyNnqcM1jDlWhpRhNvWlockq-PdxerReVfUuEvr3WcpLg9PJXXLbsUo6aV-De-SaLvfIna5iA3UOvEdunrmt9Pvk9wet19QVjZhT4K7U1s6iG6GWrY41Ve05vGX9lk7oRjebqkvMpLKvX0grQ4FF0uOFnk31rKFiNYeOaxY_aVNRl4WFj7A3bjOO6gfk_OTj-fGp72ox-DIdB43PuEo1U3HMswA9PdEJj6VUoZImDbjiBrcwUaoCCPAYIAaIiNES2FUYFnz8kIzKqtT7hBZAyAAf8UJlcSaLIig0fAk0mEBwHnpk3Fkhl06nHMtlrHK7-cZhvtJ2ao62y53tPOL3V61bnY7_4N-jgXssqmzbH6rNPHdOmxcwEDBhmDaxgUFcpBgOge8KU4i4MMojz_H1yNuU1T5W5JOExcDE0yT1yEuLQKWNEo_yzMW2rvNPX35cAfRtehXQ1wHojQOZCvpMCpdjAT2PMl8D5OsBct6KnO8CHgyAEH3koHkfXaPr4zq_8FO4snOX3c0v-ma8KR72K3W1BQwevURlvdgjj1rv6u2EG_sosecRPvC7gSGHLeVyYWXTGe7xc_b433_rCbkFnDjFdNMoOCCjZrPVT4F3NsUzG1z-AEOqga0 priority: 102 providerName: ProQuest |
| Title | Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/30457988 https://www.proquest.com/docview/2252256310 https://www.proquest.com/docview/2136550434 https://pubmed.ncbi.nlm.nih.gov/PMC6245676 https://doaj.org/article/b1116af6ef4f471a87301326afba4bfd http://dx.doi.org/10.1371/journal.pmed.1002686 |
| Volume | 15 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fb9MwELa2Tpr2gvi9wCgGIXjKlKSOnSAh1I1NA7QCY0N9i5zEbiuVpCSpBA_879w5P0RQERNSVVX150Q65-zPOd93hDzzQ2QZsC1RXHg2C9PElp4Utif9lCnp69jIMZxP-NkVezf1p1ukrdnaGLDcuLXDelJXxfLw-7cfr8HhX5mqDcJtOx2uYP0wkqI84Ntkx0SM8DAf6-IKXuiYty6oS2a7nhBNMt3frrJHdjGSiJpevXXLyPt3k_hgtczLTQz1z4OWv61cpzfJjYZy0nH9jNwiWyq7TXbPm6D6HfLzjVIr2pSPmFFgsdRU0aKFTBe1ojVN6xN5i_IlHdNCVUXepmjSpKtkSHNNgU_S47maTtS0onI5y4tFNf9Kq5w2-Vh4C3PhOveovEsuT08uj8_spiqDnQQjp7K5SAPFU8ZE6KDP-8oXLElSN0104IhUaAxmomgFUOERQDRQEq0S4FmuG4vRPTLI8kztExoDNQO8J-I0ZGESx06s4IejwPRSCNcio9bkUdIolmPhjGVkwnACdi61BSMcs6gZM4vYXa9VrdjxD_wRjmaHRb1t80dezKLGfaMYlgQuNVeaaVjOZYATIzBfqWPJYp1a5DE-C1GdvNrNGtHY5ww4eeAHFnlqEKi5keGhnplcl2X09sOXa4A-T64DuuiBXjQgnYPNEtlkW4DlUfCrh3zeQ85qufNNwIMeEOahpNe8j37Q2riMYKWAD4f9A_RsfWNz85OuGS-Kx_4yla8Bg4cwUWOPWeR-7UrdOLWOaRHRc7LeQPZbssXcCKhzjPYL_uC_ez4ke0CcA8xJ9ZwDMqiKtXoE5LSKh2RbTMWQ7BydTD5eDM0rHvh-_ykYmpnoF1yVkxE |
| linkProvider | Scholars Portal |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLZGJwEvXMZlhcEM4vIUlqRJnCBNqLupZWtBo6C-WU7stJVKUppUiAd-Gv-NcxInLKiCvUzqQ1V_SSof-_hzfM53CHnhBsgyYFuiPGYbTiAjQ9iCGbZwpaOEG4eFHMNg6PU-O-_H7niD_KpyYTCssvKJhaOWaYTvyPdg3MHHAzbybvHNwKpReLpaldAQurSC3C8kxnRix6n68R22cNl-_wjs_dK2T45Hhz1DVxkwIr9j5obHpK886TgsMHEMu8plThRJS0axbzLJYjycQxEGoHYdgMSwxMYqAt5gWSHrwG2vkU0H35-0yObB8fDjeb3jC8ziJQ_KoBmWzZjO3eswa08PlTcLWPQKHVQP07kvrI1FCYF6oWgt5mm2jgX_Hcx5YXU8uUNuaVpLu-U4vEs2VLJFblclI6j2IFvk-kCf5d8jP4-UWlBdtWJCgTzTongXXQo5K4W0qSwDAWfZW9qlS5Uv0yozlEZ1AUWaxhRoLD2cqvFQjXMq5hOwXD79SvOU6jQwfERx4zLlKbtPRldhpgeklaSJ2iY0BEYIeJuFMnCCKAzNUMEXU4EJBGNWm3QqK_BIC6VjvY45L07_GGyYyk7laDuubdcmRn3VohQK-Q_-AA1cY1Hmu_ghXU649ho8hJXIE7GnYicGFiF89MdAuEUcCieMZZvs4vDgZc5s7ax41_Uc2Ar4rt8mzwsESn0kGEs0Eass4_0PXy4B-jS8DOi8AXqtQXEKfRYJneQBPY86Yw3kqwZyUqqsrwPuNIDg_qJG8zZOjaqPM_7HUcCV1XRZ3_ysbsabYrRhotIVYDD2E6X9nDZ5WM6u2k4YWYAaf23CGvOuYchmSzKbFrrtHgYZMO_Rv__WLrnRGw3O-Fl_ePqY3ASC7mPuq23ukFa-XKknQILz8Kl2NZTwK3ZuvwHVPMLx |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLZGkSZeuIzLAoMZxOUpNEmdOEFCqKxUK2MFsYH6FjmJ3VYqSWlSIR74Yfw7zkmcbEEV7GVSH6r6S1L52Mef43O-Q8hTN0CWAdsS6XHHZEESm8IR3HSEmzApXBWVcgzHY-_wC3s_cSdb5HedC4NhlbVPLB11ksX4jrwL4w4-HrCRrtJhEZ8GwzfL7yZWkMKT1rqcRjVEjuTPH7B9y1-PBmDrZ44zfHd6cGjqCgNm7PeswvR44ksvYYwHFo5fV7qcxXFiJ7HyLZ5whQdzKMAAtK4HEAXLq5IxcAbbjngPbnuFXOU9xrBqBJ-c7fUCq3y9gwJopu1wrrP2etzu6kHycgnLXamA6mEi97lVsSwe0CwRneUiyzfx37_DOM-ti8Ob5LomtLRfjcBbZEumO-RGXSyCat-xQ7aP9Sn-bfJrIOWS6noVUwq0mZZlu-hKJPNKQpsmVQjgPH9F-3Qli1VW54TSuCmdSDNFgcDSg5mcjOWkoGIxBTsVs2-0yKhOAMNHlDeukp3yO-T0Mox0l3TSLJW7hEbABQHv8CgJWBBHkRVJ-GJJMIHg3DZIr7ZCGGuJdKzUsQjLcz8OW6WqU0O0XahtZxCzuWpZSYT8B_8WDdxgUeC7_CFbTUPtL8II1iBPKE8qpoA_CB89MVBtoSLBIpUYZB-HR1hlyzZuKuy7HoNNgO_6BnlSIlDkI8XpMhXrPA9HH79eAHQyvgjocwv0QoNUBn0WC53eAT2PCmMt5PMWclrpq28C7rWA4PjiVvMuTo26j_PwzEXAlfV02dz8uGnGm2KcYSqzNWAw6hNF_ZhB7lWzq7ETxhSgup9BeGvetQzZbknns1Kx3cPwAu7d__ff2ifb4NLCD6Px0QNyDZi5j0mvjrVHOsVqLR8C-y2iR6WfoSS8ZL_2B4GSwI0 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+for+chest+radiograph+diagnosis%3A+A+retrospective+comparison+of+the+CheXNeXt+algorithm+to+practicing+radiologists&rft.jtitle=PLoS+medicine&rft.au=Rajpurkar%2C+Pranav&rft.au=Irvin%2C+Jeremy&rft.au=Ball%2C+Robyn+L.&rft.au=Zhu%2C+Kaylie&rft.date=2018-11-20&rft.pub=Public+Library+of+Science&rft.issn=1549-1277&rft.eissn=1549-1676&rft.volume=15&rft.issue=11&rft_id=info:doi/10.1371%2Fjournal.pmed.1002686&rft_id=info%3Apmid%2F30457988&rft.externalDocID=PMC6245676 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1549-1676&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1549-1676&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1549-1676&client=summon |