Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning

• Published in: BMC medical imaging Vol. 21; no. 1; pp. 189 - 7
• Main Authors: Yang, Fan, Tang, Zhi-Ri, Chen, Jing, Tang, Min, Wang, Shengchun, Qi, Wanyin, Yao, Chong, Yu, Yuanyuan, Guo, Yinan, Yu, Zekuan
• Format: Journal Article
• Language: English
• Published: London BioMed Central 08.12.2021; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Adult; Aged; Aged, 80 and over; Algorithms; Artificial intelligence; Classification; Coronaviruses; COVID-19; Data mining; Datasets; Deep Learning; Diagnosis; Diagnosis, Computer-Assisted; Digital imaging; Disease; Dust; Feature extraction; Female; Humans; Image classification; Imaging; Learning algorithms; Lungs; Machine learning; Male; Medical diagnosis; Medical imaging; Medical imaging equipment; Medicine; Medicine & Public Health; Middle Aged; Patients; Pneumoconiosis; Pneumoconiosis - diagnostic imaging; Pneumoconiosis diagnosis; Radiology; ResNet; Retrospective Studies; Semantics; Transfer learning; U-Net; X-Rays; Deep learning; Pneumoconiosis diagnosis; U-Net; X-rays; ResNet
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-021-00723-z

Purpose The objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms. Materials and methods 1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people. Results Among the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively. Conclusion The successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions.