0561-Paper1419@2025@MICCAI

Total: 1

#1 Metastatic Lymph Node Station Classification in Esophageal Cancer via Prior-guided Supervision and Station-Aware Mixture-of-Experts [PDF] [Copy] [Kimi1] [REL]

Authors: Li Haoshen, Wang Yirui, Yu Qinji, Zhu Jie, Yan Ke, Guo Dazhou, Lu Le, Dong Bin, Zhang Li, Ye Xianghua, Wang Qifeng, Jin Dakai, Li Haoshen, Wang Yirui, Yu Qinji, Zhu Jie, Yan Ke, Guo Dazhou, Lu Le, Dong Bin, Zhang Li, Ye Xianghua, Wang Qifeng, Jin Dakai

Assessing lymph node (LN) metastasis in CT is critical for esophageal cancer treatment planning. While clinical criteria are commonly used, the diagnostic accuracy is low with sensitivities ranging from 39.7% to 67.2% in previous studies. Deep learning would have the potential to improve it by learning from large-scale accurately labeled data. However, from the surgical procedure in LN dissection, pathological report only indicates the number of dissected LNs in each lymph node station (LN-station) with the number of metastatic ones found in the respective LN-station. So, it is difficult to establish one-to-one pairing between LN instances observed in CT and their metastasis status confirmed in the pathological report. In contrast, gold reference labels on LN-station metastasis can be readily retrieved from pathology reports at scale. Hence, instead of distinguishing LN instance metastasis, we directly classify LN-station metastasis using pathology-confirmed station labels. We first segment mediastinal LN-stations automatically to serve as input for classification. Then, to improve classification performance, we automatically segment all visible LN instances in CT and design a new LN prior-guided attention loss to explicitly regularize the network to focus on regions of suspicious LN. Furthermore, considering the varying appearances and contexts of different LN-station, we propose a station-aware mixture-of-experts module, where the expert is trained to specialize in a group of LN-stations by learning to route each LN-station group tokens to the corresponding expert. We conduct five-fold cross-validation on 1,153 esophageal cancer patients with CT and pathology reports (the largest study to date), and our method significantly outperforms state-of-the-art approaches by 2.26% in AUROC.

Subject: MICCAI.2025