Applying a multi-task and multi-instance framework to predict axillary lymph node metastases in breast cancer.
Authors
Affiliations (11)
Affiliations (11)
- Department of Pharmacy, The Second Xiangya Hospital, Central South University, Changsha, 410000, China.
- Hunan Provincial Engineering Research Centre of Translational Medicine and Innovative Drug, Changsha, 410000, China.
- Department of General Surgery, The Second Xiangya Hospital of Central South University, Changsha, 410000, China.
- Clinical Research Center for Breast Disease in Hunan Province, Changsha, 410011, China.
- School of Computer Science, Central South University, Changsha, 410006, China.
- The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, 450008, China.
- Department of Ultrasound Diagnosis, The Second Xiangya Hospital of Central South University, Changsha, 410000, China.
- School of Computer Science, Central South University, Changsha, 410006, China. [email protected].
- Department of Pharmacy, The Second Xiangya Hospital, Central South University, Changsha, 410000, China. [email protected].
- Hunan Provincial Engineering Research Centre of Translational Medicine and Innovative Drug, Changsha, 410000, China. [email protected].
- Clinical Research Center for Breast Disease in Hunan Province, Changsha, 410011, China. [email protected].
Abstract
Deep learning (DL) models have shown promise in predicting axillary lymph node (ALN) status. However, most existing DL models were classification-only models and did not consider the practical application scenarios of multi-view joint prediction. Here, we propose a Multi-Task Learning (MTL) and Multi-Instance Learning (MIL) framework that simulates the real-world clinical diagnostic scenario for ALN status prediction in breast cancer. Ultrasound images of the primary tumor and ALN (if available) regions were collected, each annotated with a segmentation label. The model was trained on a training cohort and tested on both internal and external test cohorts. The proposed two-stage DL framework using one of the Transformer models, Segformer, as the network backbone, exhibits the top-performing model. It achieved an AUC of 0.832, a sensitivity of 0.815, and a specificity of 0.854 in the internal test cohort. In the external cohort, this model attained an AUC of 0.918, a sensitivity of 0.851 and a specificity of 0.957. The Class Activation Mapping method demonstrated that the DL model correctly identified the characteristic areas of metastasis within the primary tumor and ALN regions. This framework may serve as an effective second reader to assist clinicians in ALN status assessment.