Joint Localization and Classification of Breast Cancer in B-Mode Ultrasound Imaging via Collaborative Learning With Elastography

• Published in: IEEE journal of biomedical and health informatics 2022-09, Vol.26 (9), p.4474-4485
• Main Authors: Ding, Weichang, Wang, Jun, Zhou, Weijun, Zhou, Shichong, Chang, Cai, Shi, Jun
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Breast cancer; Cams; Classification; Collaborative learning; collaborative learning with multi-scale consistency; Convolutional neural networks; Deep learning; Diagnosis; Learning; Localization; Location awareness; Network management systems; Neural networks; Optimization; Stiffness; tumor classification; tumor localization; Tumors; Ultrasonic imaging; Ultrasound
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2022.3186933

Convolutional neural networks (CNNs) have been successfully applied in the computer-aided ultrasound diagnosis for breast cancer. Up to now, several CNN-based methods have been proposed. However, most of them consider tumor localization and classification as two separate steps, rather than performing them simultaneously. Besides, they suffer from the limited diagnosis information in the B-mode ultrasound (BUS) images. In this study, we develop a novel network ResNet-GAP that incorporates both localization and classification into a unified procedure. To enhance the performance of ResNet-GAP, we leverage stiffness information in the elastography ultrasound (EUS) modality by collaborative learning in the training stage. Specifically, a dual-channel ResNet-GAP network is developed, one channel for BUS and the other for EUS. In each channel, multiple class activity maps (CAMs) are generated using a series of convolutional kernels of different sizes. The multi-scale consistency of the CAMs in both channels are further considered in network optimization. Experiments on 264 patients in this study show that the newly developed ResNet-GAP achieves an accuracy of 88.6%, a sensitivity of 95.3%, a specificity of 84.6%, and an AUC of 93.6% on the classification task, and a 1.0NLF of 87.9% on the localization task, which is better than some state-of-the-art approaches.