Computational analysis of whole slide images predicts PD-L1 expression and progression-free survival in immunotherapy-treated non-small cell lung cancer patients
Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20–30% of the pa...
Saved in:
| Published in | Journal of translational medicine Vol. 23; no. 1; pp. 510 - 13 |
|---|---|
| Main Authors | , , , , , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
London
BioMed Central
06.05.2025
BioMed Central Ltd BMC |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1479-5876 1479-5876 |
| DOI | 10.1186/s12967-025-06487-2 |
Cover
| Abstract | Background
Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20–30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies.
Methods
Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures.
Results
Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy.
Conclusion
Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. |
|---|---|
| AbstractList | Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies. Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures. Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy. Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies. Methods Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures. Results Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy. Conclusion Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies. Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures. Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy. Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20–30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies. Methods Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures. Results Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy. Conclusion Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies.BACKGROUNDImmune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies.Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures.METHODSData from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures.Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy.RESULTSHandcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy.Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images.CONCLUSIONOur models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. Abstract Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20–30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies. Methods Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures. Results Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy. Conclusion Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images. |
| ArticleNumber | 510 |
| Audience | Academic |
| Author | Coulombe, François Manem, Venkata SK Malo, Julie Routy, Bertrand Kolnohuz, Alona Lamaze, Fabien Orain, Michele Blais, Florence Belkaid, Wiam Elkrief, Arielle Tonneau, Marion Gagné, Andréanne Bilodeau, Steve Laplante, Mathieu Joubert, Philippe Yolchuyeva, Sevinj Williamson, Drew Dia, Abdou Khadir |
| Author_xml | – sequence: 1 givenname: Abdou Khadir surname: Dia fullname: Dia, Abdou Khadir organization: Centre de Recherche du CHU de Québec - Université Laval – sequence: 2 givenname: Alona surname: Kolnohuz fullname: Kolnohuz, Alona organization: Quebec Heart & Lung Institute Research Center, Université Laval – sequence: 3 givenname: Sevinj surname: Yolchuyeva fullname: Yolchuyeva, Sevinj organization: Centre de Recherche du CHU de Québec - Université Laval, Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval – sequence: 4 givenname: Marion surname: Tonneau fullname: Tonneau, Marion organization: Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Université de médecine de Lille – sequence: 5 givenname: Fabien surname: Lamaze fullname: Lamaze, Fabien organization: Quebec Heart & Lung Institute Research Center – sequence: 6 givenname: Michele surname: Orain fullname: Orain, Michele organization: Quebec Heart & Lung Institute Research Center – sequence: 7 givenname: Andréanne surname: Gagné fullname: Gagné, Andréanne organization: Université Laval – sequence: 8 givenname: Florence surname: Blais fullname: Blais, Florence organization: Université Laval – sequence: 9 givenname: François surname: Coulombe fullname: Coulombe, François organization: Université Laval – sequence: 10 givenname: Julie surname: Malo fullname: Malo, Julie organization: Centre de Recherche du Centre Hospitalier Universitaire de Montréal – sequence: 11 givenname: Wiam surname: Belkaid fullname: Belkaid, Wiam organization: Centre de Recherche du Centre Hospitalier Universitaire de Montréal – sequence: 12 givenname: Arielle surname: Elkrief fullname: Elkrief, Arielle organization: Centre de Recherche du Centre Hospitalier Universitaire de Montréal – sequence: 13 givenname: Drew surname: Williamson fullname: Williamson, Drew organization: Department of Pathology and Laboratory Medicine, Emory University School of Medicine – sequence: 14 givenname: Bertrand surname: Routy fullname: Routy, Bertrand organization: Centre de Recherche du Centre Hospitalier Universitaire de Montréal – sequence: 15 givenname: Philippe surname: Joubert fullname: Joubert, Philippe organization: Quebec Heart & Lung Institute Research Center, Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval – sequence: 16 givenname: Mathieu surname: Laplante fullname: Laplante, Mathieu organization: Quebec Heart & Lung Institute Research Center, Université Laval – sequence: 17 givenname: Steve surname: Bilodeau fullname: Bilodeau, Steve organization: Centre de Recherche du CHU de Québec - Université Laval, Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Cancer Research Center, Université Laval, Big Data Research Center, Université Laval – sequence: 18 givenname: Venkata SK orcidid: 0000-0003-1427-2819 surname: Manem fullname: Manem, Venkata SK email: venkata.manem@crchudequebec.ulaval.ca organization: Centre de Recherche du CHU de Québec - Université Laval, Quebec Heart & Lung Institute Research Center, Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Cancer Research Center, Université Laval, Big Data Research Center, Université Laval |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40329352$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kl2L1DAUhousuB_6B7yQgjfedM1Hk7ZXsoxfCwN6odchTU47GdpkTNrR-Tn-U89sx2UXRAppe_K8L-ck72V25oOHLHtJyTWltXybKGtkVRAmCiLLuirYk-yCllVTiLqSZw--z7PLlLaEsFKUzbPsvCScNVywi-z3Koy7edKTC14PucblkFzKQ5f_3IQB8jQ4C7kbdQ8p30Wwzkwp__q-WNMcfmEhJZSi0OJu6E__RRcBtXPcuz3aOo8O4-zDtIGod4diiqAnsDlOVKRRD0NuAJdh9n1utDcQ8x32BH5Kz7OnnR4SvDi9r7LvHz98W30u1l8-3a5u1oURnE-FrIjmtLVcdIJaQmQLRjKuq65qGg5l1VHbdpIxSUrCoDGEA9dd24nWCkOBX2W3i68Neqt2EUeOBxW0U3eFEHul4-TMAIo1rRamYbIWtmSGNlK2xmpi67alrOXo9W7x2s3tCNbgHFEPj0wf73i3UX3YK8qIkE1D0OHNySGGHzOkSY0uHc9IewhzUpwRSmlFZYno6wXtNfbmfBfQ0hxxdVNzvH0qOEXq-h8UPhZGZzBYncP6I8GrhzPcN_83OwiwBTAxpBShu0coUceAqiWgCgOq7gKqjiK-iBLCvoeotmGOmLr0P9Uf5sPrqQ |
| Cites_doi | 10.1016/j.softx.2022.101237 10.1016/j.cels.2015.12.004 10.1016/j.jbi.2018.07.015 10.1038/s41571-019-0252-y 10.1186/s13244-021-01115-1 10.1016/j.esmoop.2022.100465 10.1371/journal.pone.0260500 10.1038/nbt0816-888d 10.3390/cancers12123663 10.2478/popets-2019-0049 10.4103/jpi.jpi_24_19 10.1093/annonc/mdz108 10.1371/journal.pone.0212110 10.1038/s43018-022-00416-8 10.1016/j.jtho.2021.07.015 10.1200/JCO.22.02544 10.1038/s41698-022-00277-5 10.1371/journal.pone.0087357 10.1016/j.jtho.2018.09.006 10.1016/j.jaccao.2022.09.004 10.1016/j.jtocrr.2023.100602 10.1056/NEJMoa1504627 10.1038/s41571-022-00718-x 10.1016/j.cmpbup.2021.100004 10.1002/path.5966 10.3389/fonc.2022.1005805 10.1038/s41598-021-86113-5 10.1038/s41598-018-35501-5 10.1200/JCO.2011.38.7571 10.1126/sciadv.abn3966 10.1038/s41598-023-38076-y 10.1200/EDBK_158712 10.1158/1535-7163.MCT-14-0983 10.1186/s12967-024-04854-z 10.3390/jimaging4100123 10.1038/s41598-018-22254-4 10.3390/cancers16020348 10.21037/atm-22-4218 10.1158/1078-0432.CCR-12-2934 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2025 2025. The Author(s). COPYRIGHT 2025 BioMed Central Ltd. The Author(s) 2025 2025 |
| Copyright_xml | – notice: The Author(s) 2025 – notice: 2025. The Author(s). – notice: COPYRIGHT 2025 BioMed Central Ltd. – notice: The Author(s) 2025 2025 |
| DBID | C6C AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM DOA |
| DOI | 10.1186/s12967-025-06487-2 |
| DatabaseName | Springer Nature OA Free Journals CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: C6C name: Springer Nature OA Free Journals url: http://www.springeropen.com/ sourceTypes: Publisher – sequence: 2 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 3 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: 4 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1479-5876 |
| EndPage | 13 |
| ExternalDocumentID | oai_doaj_org_article_29ba5c92685d42c1966bcda0d8bb12b3 PMC12056990 A838761531 40329352 10_1186_s12967_025_06487_2 |
| Genre | Journal Article |
| GeographicLocations | Canada |
| GeographicLocations_xml | – name: Canada |
| GrantInformation_xml | – fundername: IVADO grantid: IVADO – fundername: Fonds de Recherche du Québec - Santé grantid: Fonds de Recherche du Québec - Santé funderid: http://dx.doi.org/10.13039/501100000156 – fundername: Fonds de Recherche du Québec - Santé grantid: Fonds de Recherche du Québec - Santé |
| GroupedDBID | --- 0R~ 29L 2WC 53G 5VS 6PF 7X7 88E 8FI 8FJ AAFWJ AAJSJ AASML AAWTL ABDBF ABUWG ACGFO ACGFS ACIHN ACIWK ACPRK ACUHS ADBBV ADUKV AEAQA AENEX AFKRA AFPKN AFRAH AHBYD AHMBA AHYZX ALMA_UNASSIGNED_HOLDINGS AMKLP AMTXH AOIJS BAPOH BAWUL BCNDV BENPR BFQNJ BMC BPHCQ BVXVI C6C CCPQU CS3 DIK DU5 E3Z EBD EBLON EBS ESX F5P FYUFA GROUPED_DOAJ GX1 HMCUK HYE IAO IHR INH INR ITC KQ8 M1P M~E O5R O5S OK1 OVT P2P PGMZT PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO PUEGO RBZ RNS ROL RPM RSV SBL SOJ TR2 TUS UKHRP WOQ WOW XSB ~8M AAYXX ALIPV CITATION CGR CUY CVF ECM EIF NPM PMFND 7X8 5PM |
| ID | FETCH-LOGICAL-c533t-670a31bd35f51d006bec623a7f7993e47f1dbf62260402e9c03e3afbf5bd5c1e3 |
| IEDL.DBID | C6C |
| ISSN | 1479-5876 |
| IngestDate | Wed Aug 27 01:26:25 EDT 2025 Thu Aug 21 18:27:44 EDT 2025 Fri Sep 05 17:16:11 EDT 2025 Tue Jun 17 22:00:15 EDT 2025 Tue Jun 10 20:53:43 EDT 2025 Sat May 10 01:40:41 EDT 2025 Tue Jul 01 05:01:03 EDT 2025 Sat Sep 06 07:28:35 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | 2025. The Author(s). Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c533t-670a31bd35f51d006bec623a7f7993e47f1dbf62260402e9c03e3afbf5bd5c1e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-1427-2819 |
| OpenAccessLink | https://doi.org/10.1186/s12967-025-06487-2 |
| PMID | 40329352 |
| PQID | 3201117164 |
| PQPubID | 23479 |
| PageCount | 13 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_29ba5c92685d42c1966bcda0d8bb12b3 pubmedcentral_primary_oai_pubmedcentral_nih_gov_12056990 proquest_miscellaneous_3201117164 gale_infotracmisc_A838761531 gale_infotracacademiconefile_A838761531 pubmed_primary_40329352 crossref_primary_10_1186_s12967_025_06487_2 springer_journals_10_1186_s12967_025_06487_2 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2025-05-06 |
| PublicationDateYYYYMMDD | 2025-05-06 |
| PublicationDate_xml | – month: 05 year: 2025 text: 2025-05-06 day: 06 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: England |
| PublicationTitle | Journal of translational medicine |
| PublicationTitleAbbrev | J Transl Med |
| PublicationTitleAlternate | J Transl Med |
| PublicationYear | 2025 |
| Publisher | BioMed Central BioMed Central Ltd BMC |
| Publisher_xml | – name: BioMed Central – name: BioMed Central Ltd – name: BMC |
| References | J Brahmer (6487_CR4) 2015; 373 CM Booth (6487_CR9) 2012; 30 M Salvi (6487_CR14) 2021; 1 A Marcolini (6487_CR13) 2022; 20 K Bera (6487_CR39) 2019; 16 T Löfstedt (6487_CR18) 2019; 14 D Xia (6487_CR42) 2018; 8 6487_CR25 SJ Antonia (6487_CR1) 2016; 35 X Wang (6487_CR6) 2022; 8 6487_CR24 6487_CR22 S Yolchuyeva (6487_CR36) 2023; 4 A Demircioğlu (6487_CR20) 2021; 12 T Aiba (6487_CR27) 2021; 16 AS Kornilov (6487_CR17) 2018; 4 S Tan (6487_CR30) 2022; 4 S Trebeschi (6487_CR37) 2019; 30 SP Patel (6487_CR33) 2015; 14 M Zerunian (6487_CR38) 2021; 11 MA Siciliano (6487_CR31) 2022; 7 L Sha (6487_CR40) 2019; 10 RL Korn (6487_CR10) 2013; 19 V Brancato (6487_CR16) 2022; 12 RS Vanguri (6487_CR5) 2022; 3 6487_CR8 A Liberzon (6487_CR26) 2015; 1 A Kapil (6487_CR41) 2018; 8 6487_CR19 S Yolchuyeva (6487_CR34) 2023; 13 I Otano (6487_CR2) 2023; 20 6487_CR15 A Olivares-Hernández (6487_CR32) 2023; 11 6487_CR11 NL Bray (6487_CR12) 2016; 34 RJ Urbanowicz (6487_CR23) 2018; 85 VS Viswanathan (6487_CR43) 2022; 257 R Ding (6487_CR7) 2022; 6 Y Yang (6487_CR28) 2021; 16 BC Ross (6487_CR21) 2014; 9 S Yolchuyeva (6487_CR35) 2024; 22 H Yu (6487_CR29) 2019; 14 GV Scagliotti (6487_CR3) 2023; 41 |
| References_xml | – volume: 20 start-page: 101237 year: 2022 ident: 6487_CR13 publication-title: SoftwareX doi: 10.1016/j.softx.2022.101237 – volume: 1 start-page: 417 year: 2015 ident: 6487_CR26 publication-title: Cell Syst doi: 10.1016/j.cels.2015.12.004 – volume: 85 start-page: 168 year: 2018 ident: 6487_CR23 publication-title: J Biomed Inf doi: 10.1016/j.jbi.2018.07.015 – volume: 16 start-page: 703 year: 2019 ident: 6487_CR39 publication-title: Nat Rev Clin Oncol doi: 10.1038/s41571-019-0252-y – ident: 6487_CR8 – volume: 12 start-page: 172 year: 2021 ident: 6487_CR20 publication-title: Insights Imaging doi: 10.1186/s13244-021-01115-1 – volume: 7 start-page: 100465 year: 2022 ident: 6487_CR31 publication-title: ESMO Open doi: 10.1016/j.esmoop.2022.100465 – volume: 16 start-page: e0260500 year: 2021 ident: 6487_CR27 publication-title: PLoS ONE doi: 10.1371/journal.pone.0260500 – volume: 34 start-page: 888 year: 2016 ident: 6487_CR12 publication-title: Nat Biotechnol doi: 10.1038/nbt0816-888d – ident: 6487_CR25 – ident: 6487_CR15 doi: 10.3390/cancers12123663 – ident: 6487_CR22 doi: 10.2478/popets-2019-0049 – volume: 10 start-page: 24 year: 2019 ident: 6487_CR40 publication-title: J Pathol Inf doi: 10.4103/jpi.jpi_24_19 – volume: 30 start-page: 998 year: 2019 ident: 6487_CR37 publication-title: Ann Oncol doi: 10.1093/annonc/mdz108 – volume: 14 start-page: e0212110 year: 2019 ident: 6487_CR18 publication-title: PLoS ONE doi: 10.1371/journal.pone.0212110 – volume: 3 start-page: 1151 year: 2022 ident: 6487_CR5 publication-title: Nat Cancer doi: 10.1038/s43018-022-00416-8 – volume: 16 start-page: 2109 year: 2021 ident: 6487_CR28 publication-title: J Thorac Oncol doi: 10.1016/j.jtho.2021.07.015 – volume: 41 start-page: 2458 year: 2023 ident: 6487_CR3 publication-title: J Clin Oncol doi: 10.1200/JCO.22.02544 – volume: 6 start-page: 33 year: 2022 ident: 6487_CR7 publication-title: NPJ Precis Oncol doi: 10.1038/s41698-022-00277-5 – volume: 9 start-page: e87357 year: 2014 ident: 6487_CR21 publication-title: PLoS ONE doi: 10.1371/journal.pone.0087357 – volume: 14 start-page: 25 year: 2019 ident: 6487_CR29 publication-title: J Thorac Oncol doi: 10.1016/j.jtho.2018.09.006 – volume: 4 start-page: 579 year: 2022 ident: 6487_CR30 publication-title: JACC CardioOncol doi: 10.1016/j.jaccao.2022.09.004 – volume: 4 start-page: 100602 year: 2023 ident: 6487_CR36 publication-title: JTO Clin Res Rep doi: 10.1016/j.jtocrr.2023.100602 – volume: 373 start-page: 123 year: 2015 ident: 6487_CR4 publication-title: N Engl J Med doi: 10.1056/NEJMoa1504627 – volume: 20 start-page: 143 year: 2023 ident: 6487_CR2 publication-title: Nat Rev Clin Oncol doi: 10.1038/s41571-022-00718-x – volume: 1 start-page: 100004 year: 2021 ident: 6487_CR14 publication-title: Comput Methods Programs Biomed Update doi: 10.1016/j.cmpbup.2021.100004 – volume: 257 start-page: 413 issue: 4 year: 2022 ident: 6487_CR43 publication-title: J Pathol doi: 10.1002/path.5966 – volume: 12 start-page: 1005805 year: 2022 ident: 6487_CR16 publication-title: Front Oncol doi: 10.3389/fonc.2022.1005805 – volume: 11 start-page: 6633 year: 2021 ident: 6487_CR38 publication-title: Sci Rep doi: 10.1038/s41598-021-86113-5 – volume: 8 start-page: 17343 year: 2018 ident: 6487_CR41 publication-title: Sci Rep doi: 10.1038/s41598-018-35501-5 – volume: 30 start-page: 1030 year: 2012 ident: 6487_CR9 publication-title: J Clin Oncol doi: 10.1200/JCO.2011.38.7571 – volume: 8 start-page: eabn3966 year: 2022 ident: 6487_CR6 publication-title: Sci Adv doi: 10.1126/sciadv.abn3966 – volume: 13 start-page: 11065 year: 2023 ident: 6487_CR34 publication-title: Sci Rep doi: 10.1038/s41598-023-38076-y – ident: 6487_CR24 – volume: 35 start-page: e450 year: 2016 ident: 6487_CR1 publication-title: Am Soc Clin Oncol Educ Book doi: 10.1200/EDBK_158712 – volume: 14 start-page: 847 year: 2015 ident: 6487_CR33 publication-title: Mol Cancer Ther doi: 10.1158/1535-7163.MCT-14-0983 – volume: 22 start-page: 42 year: 2024 ident: 6487_CR35 publication-title: J Transl Med doi: 10.1186/s12967-024-04854-z – volume: 4 start-page: 123 year: 2018 ident: 6487_CR17 publication-title: J Imaging doi: 10.3390/jimaging4100123 – volume: 8 start-page: 3941 year: 2018 ident: 6487_CR42 publication-title: Sci Rep doi: 10.1038/s41598-018-22254-4 – ident: 6487_CR19 doi: 10.3390/cancers16020348 – volume: 11 start-page: 354 year: 2023 ident: 6487_CR32 publication-title: Ann Transl Med doi: 10.21037/atm-22-4218 – volume: 19 start-page: 2607 year: 2013 ident: 6487_CR10 publication-title: Clin Cancer Res doi: 10.1158/1078-0432.CCR-12-2934 – ident: 6487_CR11 |
| SSID | ssj0024549 |
| Score | 2.4287555 |
| Snippet | Background
Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for... Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients... Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for... Abstract Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and... |
| SourceID | doaj pubmedcentral proquest gale pubmed crossref springer |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Publisher |
| StartPage | 510 |
| SubjectTerms | Aged Analysis Apoptosis B7-H1 Antigen - metabolism Biological markers Biomedical and Life Sciences Biomedicine Cancer Carcinoma, Non-Small-Cell Lung - drug therapy Carcinoma, Non-Small-Cell Lung - metabolism Carcinoma, Non-Small-Cell Lung - pathology Carcinoma, Non-Small-Cell Lung - therapy Care and treatment Computational Biology - methods Development and progression Diagnosis Female Health aspects Humans Image Processing, Computer-Assisted Immunotherapy Lung cancer, Non-small cell Lung cancer, Small cell Lung Neoplasms - drug therapy Lung Neoplasms - immunology Lung Neoplasms - metabolism Lung Neoplasms - pathology Lung Neoplasms - therapy Machine Learning Male Medical imaging equipment Medicine/Public Health Middle Aged Molecular Pathology Patient outcomes Progression-Free Survival |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NaxQxGA7SQ_Ei1s_RKhEEDxo6-ZzMsVVLESseLPQWkkmCC7vTsrNL9ef4T32TyZROBb143E2ym8n79WTy5nkReh1jTDQfjuioORGaBmJV0MQGYRsrVG1lupx8-kWdnIlP5_L8RqmvlBM20gOPC3fAWgfdW6a09IJ1oDDKdd7WXjtHmcs8n3VbT5upiWUPtj3TFRmtDgaIauAQUulWCMFgVmwWhjJb_58--UZQup0weevUNAej4_voXkGR-HCc_R66E_oHaPe0nJM_RL_GYg3lRR-2hXkEX0R8lQriYkCXPuDFCrzJgC_XaeBmwF8_kM8Uhx8lObaHgR7nDK7xM4nrAGO34F5AQfGih19YbftyiesnyVnrweMeug4ru1zidC6Al-BQcJfUa40Lj-vwCJ0df_z2_oSUYgykA0S4IaqpLafOcxkl9SBfED5AJ9vEBiBOEE2k3kUFaA7cAgttV_PAbXRROi87GvhjtAP_Hp4iXHPtYsOFbLkT1Ps2sFpF0UAMSHz2qkJvJ9mYy5Fzw-S9ilZmlKQBSZosScMqdJTEd90z8WXnL0CLTNEi8y8tqtCbJHyTrBok3NlyOQEmnPixzKHmEDYgOtAK7c96gjV2s-ZXk_qY1JRS2PpwsR0MT1ArkROJCj0Z1el6zqLmALskPIueKdrsoeYt_eJ7JgOnDCAsQIoKvZt00hQ3NPxl1Z79j1V7ju6ybFPJrPbRzma9DS8Ao23cy2yOvwHU1juo priority: 102 providerName: Directory of Open Access Journals |
| Title | Computational analysis of whole slide images predicts PD-L1 expression and progression-free survival in immunotherapy-treated non-small cell lung cancer patients |
| URI | https://link.springer.com/article/10.1186/s12967-025-06487-2 https://www.ncbi.nlm.nih.gov/pubmed/40329352 https://www.proquest.com/docview/3201117164 https://pubmed.ncbi.nlm.nih.gov/PMC12056990 https://doaj.org/article/29ba5c92685d42c1966bcda0d8bb12b3 |
| Volume | 23 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1baxQxFA7agvgi3h2tSwTBBw1OJpfJPnbXliK2lGJh8SUkkwQXdqdlZxf15_hPPclka6eK4MvCbpKdyznnO99MTr4g9DqEEGU-LFFBMcIV9cRIr4jx3NSGy9KIuDj5-EQenfOPMzHLMjlxLcz1-Xuq5PsO8hGEctx0FZInBATA7a4A4I3ePJXT37p68KCzXRTz13GDxJP0-f9E4Wtp6GaJ5I150pR-Du-je5k34v3e0A_QLd8-RHeO88z4I_Sz354hv9rDJmuN4IuAv8UtcDHwSefxfAn40eHLVRy47vDpB_KJYv89l8O2MNDhVLPVfydh5WHsBgAFXBLPW_iH5abNy7Z-kFSn7h1uoWu3NIsFjjMBeAEQgpvoUCuclVu7x-j88ODz9Ijk7RdIAxxwTWRdGkatYyII6sCiYG4gS6YONZAaz-tAnQ0S-BsAQeXHTck8M8EGYZ1oqGdP0A4c3T9DuGTKhppxMWaWU-fGvipl4DWgflSwlwV6u7WNvuxVNnR6OlFS95bUYEmdLKmrAk2i-a56RoXs9AM4js4Bp6uxBTcbV1IJx6sGgEbaxpnSKWtpZVmB3kTj6xjHYOHG5OUIcMJREUvvKwaJAvIBLdDeoCfEXzNofrV1Hx2bYtFa6y82nWaRXEU5Il6gp707XZ0zLxkQLQHXogaONrioYUs7_5rkv2kFpBVIRIHebX1SZ-Dp_nHXnv9f9xfobpWiJwbQHtpZrzb-JfCvtR2h2_WsHqHdycHJ6dkoheEovcuAz7PJl1-v_zA6 |
| linkProvider | Springer Nature |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1db9MwFLXQkIAXxDeBAUZC4gEi4thx3MdRmAq0Ew-btDfLjm2tUptNTSu2n8M_5V7HHctASDy2ttuk536c1PceE_ImhIAyHzZXQfFcKOZzI73KjRemNkIWpsLm5NmBnByJr8fVcZLJwV6Yq_v3TMkPHeQjcGU8dBWSJzgEhNubuHOJOvljOf6tqwcPOtummL-uGySeqM__ZxS-koaul0he2yeN6Wf_HrmbeCPd64G-T2749gG5NUs74w_Jz_54hvTXHjVJa4SeBvoDj8ClwCedp_MlxI-Onq1w4bqj3z_lU0b9eSqHbWGho7Fmq3-dh5WHtRsIKGCSdN7CJyw3bWrbushjnbp3tIWp3dIsFhR3AugCQght0KBWNCm3do_I0f7nw_EkT8cv5A1wwHUu68JwZh2vQsUcIApwA1kydaiB1HhRB-ZskMDfIBCUftQU3HMTbKisqxrm-WOyA9_unxJacGVDzUU14lYw50a-LGQQNUR9VLCXGXm3xUaf9SobOj6dKKl7JDUgqSOSuszIR4TvciYqZMc3wHB0cjhdjiyY2aiUqnKibCDQSNs4UzhlLSstz8hbBF-jHwPCjUntCHDBqIil9xSHRAH5gGVkdzAT_K8ZDL_emo_GISxaa_3pptMcyRXKEYmMPOnN6fKaRcGBaFVwL2pgaIObGo6085Mo_81KIK1AIjLyfmuTOgWe7h-_2rP_m_6K3J4czqZ6-uXg23Nyp4yehM60S3bWq41_AVxsbV9GJ_wFRV4upA |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1db9MwFLXQkCZeEN8EBhgJiQeIlsSO4z6OjmrANu2BSXuz7NiGSm1aJa2An8M_5V7HGctASDy2ttuk536c1PceE_LKe48yHyaVXrKUy9ylWjiZasd1pbnIdInNySen4uicf7woL6508Ydq92FLsu9pQJWmZrO_tr53cSn2O8hS4OB4FCukVHATCMI3UasLi_qmYvpbbQ8ef4ZWmb-uG6WjoNr_Z2y-kpyuF05e2z0NSWl2h9yObJIe9PDfJTdcc4_snsT98vvkZ39oQ_zDj-qoQEJXnn7Dg3EpsEzr6HwJUaWj6xYXbjp6dpge59R9j0WyDSy0NFRy9a9T3zpYu4UwA4ZK5w18wnLbxGauH2moXneWNjC1W-rFguL-AF1AYKE1mllLo55r94Ccz95_nh6l8VCGtAZmuElFlWmWG8tKX-YWcAYjAAqlK18B1XG88rk1XgCrg_BQuEmdMce0N740tqxzxx6SHfh295jQjEnjK8bLCTM8t3biikx4XkEuQF17kZA3AzZq3WtvqPDMIoXqkVSApApIqiIh7xC-y5momx3eWLVfVHRDVUwMGN-kELK0vKgh_AhTW51ZaUxeGJaQ1wi-Qu8GhGsdmxTgglEnSx1IBukDskSekL3RTPDKejT8cjAfhUNYyta41bZTDCkXihTxhDzqzenymnnGgH6VcC9yZGijmxqPNPOvQRQ8L4DKArVIyNvBJlUMR90_frUn_zf9Bdk9O5yp4w-nn56SW0VwJPSlPbKzabfuGRC0jXkefPAX8Uk29A |
| 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=Computational+analysis+of+whole+slide+images+predicts+PD-L1+expression+and+progression-free+survival+in+immunotherapy-treated+non-small+cell+lung+cancer+patients&rft.jtitle=Journal+of+translational+medicine&rft.au=Dia%2C+Abdou+Khadir&rft.au=Kolnohuz%2C+Alona&rft.au=Yolchuyeva%2C+Sevinj&rft.au=Tonneau%2C+Marion&rft.date=2025-05-06&rft.pub=BioMed+Central+Ltd&rft.issn=1479-5876&rft.eissn=1479-5876&rft.volume=23&rft.issue=1&rft_id=info:doi/10.1186%2Fs12967-025-06487-2&rft.externalDocID=A838761531 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1479-5876&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1479-5876&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1479-5876&client=summon |