HECKTOR2025 Challenge Report: Fully Automated Diagnoses of HPV Status using PET/CT Images and Clinical Information

Muzi Guo, Tianen Yu, Jian He, Lei Xiang

Keywords: HECKTOR2025, classification challenge, PET/CT, deep learning

TL;DR: We propose a multimodal deep learning framework integrating PET/CT images and clinical data for HPV status prediction for HECKTOR 2025 task 3 challenge.

Abstract: Accurate prediction of human papillomavirus (HPV) status is essential for risk stratification and personalized treatment planning in head and neck cancer. In this work, we propose a multi-modal deep learning framework to classify HPV status using the HECKTOR25 Task 3 dataset, which provides 3D FDG-PET and CT scans with clinical data. Our approach leverages a 3D ResNet-18 architecture for imaging feature extraction, combined with a fully connected network to encode clinical variables, followed by multimodal fusion for final prediction. To address the significant class imbalance problem, we implemented a weighted cross-entropy loss. On internally held-out test splits, the model achieved a specificity of 0.9167 and a balanced accuracy of 0.9017, demonstrating robust intra-dataset performance. However, evaluation on the organizers external dataset—which contains cases from centers not included in the training data—yielded reduced performance (validation specificity 0.9048, balanced accuracy 0.6765), highlighting the challenges of cross-center generalization. These findings underscore the potential of multimodal deep learning for HPV status prediction and indicate that further strategies are required to enhance model robustness to inter-center variability.

Submission Number: 10