Li Yizhi, Chen Zonglin, Ding Ziyuan, Mei Danyang, Liu Zhenzhen, Wang Jia, Tang Kui, Yi Wenjun, Xu Yan, Liang Yixiong, Cheng Yan
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.
NPJ Precis Oncol. 2025 Jun 18;9(1):195. doi: 10.1038/s41698-025-00971-0.
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.
深度学习(DL)模型在预测腋窝淋巴结(ALN)状态方面已显示出前景。然而,大多数现有的DL模型都是仅用于分类的模型,并未考虑多视图联合预测的实际应用场景。在此,我们提出了一种多任务学习(MTL)和多实例学习(MIL)框架,该框架模拟了用于乳腺癌ALN状态预测的真实临床诊断场景。收集了原发肿瘤和ALN(如果可用)区域的超声图像,每个图像都标注有分割标签。该模型在一个训练队列上进行训练,并在内部和外部测试队列上进行测试。所提出的使用Transformer模型之一Segformer作为网络主干的两阶段DL框架,展现出表现最佳的模型。在内部测试队列中,它的曲线下面积(AUC)为0.832,灵敏度为0.815,特异性为0.854。在外部队列中,该模型的AUC为0.918,灵敏度为0.851,特异性为0.957。类激活映射方法表明,DL模型正确识别了原发肿瘤和ALN区域内转移的特征区域。该框架可作为有效的第二阅片者,协助临床医生进行ALN状态评估。