Yi Yan, Wang Jiacheng, Li Zhenjiang, Wang Liansheng, Ding Xiuping, Zhou Qichao, Huang Yong, Li Baosheng
Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China.
Manteia Technologies Co., Ltd, Xiamen, Fujian, 361008, China.
Med Biol Eng Comput. 2025 Jun 9. doi: 10.1007/s11517-025-03391-1.
The accurate diagnosis of lymph node metastasis in esophageal squamous cell carcinoma is crucial in the treatment workflow, and the process is often time-consuming for clinicians. Recent deep learning models predicting whether lymph nodes are affected by cancer in esophageal cancer cases suffer from challenging node delineation and hence gain poor diagnosis accuracy. This paper proposes an innovative multi-task and multi-scale attention network (M ANet) to predict lymph node metastasis precisely. The network softly expands the regions of the node mask and subsequently utilizes the expanded mask to aggregate image features, thereby amplifying the node contexts. It additionally proposes a two-branch training strategy that compels the model to simultaneously predict metastasis probability and node masks, fostering a more comprehensive learning process. The node metastasis prediction performance has been evaluated on a self-collected dataset with 177 patients. Our model finally achieves a competitive accuracy of 83.7% on the test set comprising 577 nodes. With the adaptability to intricate patterns and ability to handle data variations, M ANet emerges as a promising tool for robust and comprehensive lymph node metastasis prediction in medical image analysis.
食管鳞状细胞癌中淋巴结转移的准确诊断在治疗流程中至关重要，而这一过程对临床医生来说通常很耗时。最近用于预测食管癌病例中淋巴结是否受癌症影响的深度学习模型面临着具有挑战性的淋巴结轮廓描绘问题，因此诊断准确率较低。本文提出了一种创新的多任务多尺度注意力网络（MANet）来精确预测淋巴结转移。该网络通过软扩展节点掩码区域，随后利用扩展后的掩码聚合图像特征，从而增强节点上下文信息。此外，它还提出了一种双分支训练策略，迫使模型同时预测转移概率和节点掩码，促进更全面的学习过程。已在一个包含177名患者的自收集数据集上评估了节点转移预测性能。我们的模型最终在包含577个节点的测试集上达到了83.7%的有竞争力的准确率。凭借对复杂模式的适应性和处理数据变化的能力，MANet成为医学图像分析中用于强大而全面的淋巴结转移预测的有前途的工具。
