Anatomy-Privileged Distillation with Token Routing for MRI-Based Prediction of Perineural Invasion
Authors: Hyunsu Go, Youngung Han, Kyeonghun Kim, Junga Kim, Dohyun Kweon, Jinyong Jun, Sungha Park, Anna Jung, +10 more
Organizations: Seoul National University, Seoul, Republic of Korea · OUTTA, Seoul, Republic of Korea · Kyung Hee University, Seoul, Republic of Korea · Seoul National University School of Medicine, Seoul, Republic of Korea · Chung-Ang University, Seoul, Republic of Korea · Samsung Changwon Hospital, Changwon, Republic of Korea · Samsung Medical Center, Seoul, Republic of Korea · NVIDIA AI Technology Center, Taipei, Taiwan
Perineural invasion (PNI) is associated with poor postoperative outcomes in intrahepatic cholangiocarcinoma, but it is confirmed by surgical pathology. Existing preoperative imaging models often rely on radiologist-defined variables, contrast-enhanced imaging, or manual annotations. We propose an anatomy-privileged teacher--student framework for patient-level PNI prediction from T2-weighted MRI. During training, the teacher uses MRI with tumor and liver masks to learn dense token routing, and the student distills this guidance to retain and aggregate informative tokens under a fixed budget. Anatomical supervision is restricted to training, and the deployed model does not require masks at inference. In 155 patients, the proposed method achieved the highest mean AUROC of 0.750 among matched MRI-only baselines evaluated under the same protocol, with 1.43 GFLOPs and 8.02 ms per case on a Jetson Orin Nano Super Developer Kit.