Development of a deep learning-based automated diagnostic system (DLADS) for classifying mammographic lesions - a first large-scale multi-institutional clinical trial in Japan.
Authors
Affiliations (11)
Affiliations (11)
- Department of Medical Oncology, Toranomon Hospital, Tokyo, Japan.
- Department of Breast Surgical Oncology, Tokyo Medical University Hospital, 6-7-1 Nishishinjuku, Shinjuku-Ku, Tokyo, 160-0023, Japan. [email protected].
- Breast Cancer Center, Shonan Memorial Hospital, Kanagawa, Japan.
- Yotsuya Medical Cube, Tokyo, Japan.
- Department of Breast Surgery, Hyogo Cancer Center, Hyogo, Japan.
- Department of Radiology, Tsukuba Memorial Hospital, Ibaraki, Japan.
- Yuko Breast Clinic Meieki, Aichi, Japan.
- Department of Radiological Technology, Faculty of Health Sciences, Gifu University of Medical Science, Gifu, Japan.
- Department of Radiology, St. Luke's International Hospital, Tokyo, Japan.
- Department of Breast Imaging and Breast Interventional Radiology, Shizuoka Cancer Center Hospital, Shizuoka, Japan.
- Division of Medical Oncology, National Cancer Center Hospital East, Chiba, Japan.
Abstract
Recently, western countries have built evidence on mammographic artificial Intelligence-computer-aided diagnosis (AI-CADx) systems; however, their effectiveness has not yet been sufficiently validated in Japanese women. In this study, we aimed to establish a Japanese mammographic AI-CADx system for the first time. We retrospectively collected screening or diagnostic mammograms from 63 institutions in Japan. We then randomly divided the images into training, validation, and test datasets in a balanced ratio of 8:1:1 on a case-level basis. The gold standard of annotation for the AI-CADx system is mammographic findings based on pathologic references. The AI-CADx system was developed using SE-ResNet modules and a sliding window algorithm. A cut-off concentration gradient of the heatmap image was set at 15%. The AI-CADx system was considered accurate if it detected the presence of a malignant lesion in a breast cancer mammogram. The primary endpoint of the AI-CADx system was defined as a sensitivity and specificity of over 80% for breast cancer diagnosis in the test dataset. We collected 20,638 mammograms from 11,450 Japanese women with a median age of 55 years. The mammograms included 5019 breast cancer (24.3%), 5026 benign (24.4%), and 10,593 normal (51.3%) mammograms. In the test dataset of 2059 mammograms, the AI-CADx system achieved a sensitivity of 83.5% and a specificity of 84.7% for breast cancer diagnosis. The AUC in the test dataset was 0.841 (DeLong 95% CI; 0.822-0.859). The Accuracy was almost consistent independent of breast density, mammographic findings, type of cancer, and mammography vendors (AUC (range); 0.639-0.906). The developed Japanese mammographic AI-CADx system diagnosed breast cancer with a pre-specified sensitivity and specificity. We are planning a prospective study to validate the breast cancer diagnostic performance of Japanese physicians using this AI-CADx system as a second reader. UMIN, trial number UMIN000039009. Registered 26 December 2019, https://www.umin.ac.jp/ctr/.