Weakly supervised 3D deep learning for breast cancer classification and localization of the lesions in MR images

• Published in: Journal of magnetic resonance imaging Vol. 50; no. 4; pp. 1144 - 1151
• Main Authors: Zhou, Juan, Luo, Lu‐Yang, Dou, Qi, Chen, Hao, Chen, Cheng, Li, Gong‐Jie, Jiang, Ze‐Fei, Heng, Pheng‐Ann
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.10.2019; Wiley Subscription Services, Inc
• Subjects: Accuracy; Algorithms; Artificial neural networks; Breast cancer; Classification; Confidence intervals; Deep learning; Diagnosis; Field strength; Image classification; Image enhancement; Labels; Lesions; Localization; Machine learning; Magnetic resonance imaging; Malignancy; Medical diagnosis; Medical imaging; MRI; Neural networks; Radiology; Sensitivity; Statistical analysis; Statistical tests; weakly supervised localization; deep learning; breast cancer; MRI; weakly supervised localization
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.26721

Background The usefulness of 3D deep learning‐based classification of breast cancer and malignancy localization from MRI has been reported. This work can potentially be very useful in the clinical domain and aid radiologists in breast cancer diagnosis. Purpose To evaluate the efficacy of 3D deep convolutional neural network (CNN) for diagnosing breast cancer and localizing the lesions at dynamic contrast enhanced (DCE) MRI data in a weakly supervised manner. Study Type Retrospective study. Subjects A total of 1537 female study cases (mean age 47.5 years ±11.8) were collected from March 2013 to December 2016. All the cases had labels of the pathology results as well as BI‐RADS categories assessed by radiologists. Field Strength/Sequence 1.5 T dynamic contrast‐enhanced MRI. Assessment Deep 3D densely connected networks were trained under image‐level supervision to automatically classify the images and localize the lesions. The dataset was randomly divided into training (1073), validation (157), and testing (307) subsets. Statistical Tests Accuracy, sensitivity, specificity, area under receiver operating characteristic curve (ROC), and the McNemar test for breast cancer classification. Dice similarity for breast cancer localization. Results The final algorithm performance for breast cancer diagnosis showed 83.7% (257 out of 307) accuracy (95% confidence interval [CI]: 79.1%, 87.4%), 90.8% (187 out of 206) sensitivity (95% CI: 80.6%, 94.1%), 69.3% (70 out of 101) specificity (95% CI: 59.7%, 77.5%), with the area under the curve ROC of 0.859. The weakly supervised cancer detection showed an overall Dice distance of 0.501 ± 0.274. Data Conclusion 3D CNNs demonstrated high accuracy for diagnosing breast cancer. The weakly supervised learning method showed promise for localizing lesions in volumetric radiology images with only image‐level labels. Level of Evidence: 4 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1144–1151.