hecktor 2025 report

baixiang zhao, Surajit Ray

Keywords: radiotherapy planning, multi-modality neural network, survival analysis.

TL;DR: This is the technical report of the AI_state team for the HECKTOR 2025 challenge, covering all three tasks.

Abstract: In this paper, we present our submission to the HECKTOR 2025 challenge, addressing all three tasks using PET and CT imaging together with electronic health record data. The tasks include segmentation of primary tumors and lymph nodes, survival prediction, and HPV-status classification. For the first task, we used a U-Net style SegResNet and achieved a Dice score of 0.52 for predicting the primary tumor volume and an aggregated Dice score of 0.38 for lymph node volume on the validation set. For survival prediction, we designed a multimodal model that combines imaging features with clinical data, reaching a C-index of 0.6482 on the validation cohort. We applied the same model to HPV-status classification, which resulted in a balanced accuracy of 0.4655. Our experiments show that combining features across multiple folds improves performance, while imbalanced classes reduce accuracy. We also note that adding more information, such as radiotherapy planning data and tumor volume, which may be important for prognosis, could further improve results in future work.

Submission Number: 5