A Two-Stage Coarse-to-Fine Ensembling Segmentation Framework with Multi-Channel CT Enhancement for Head and Neck Tumor and Lymph Segmentation in PET and CT Image

Chuanyi Huang, Lisheng Wang

Keywords: Head an Neck Cancer Automatic segmentation; Coarse-to-Fine Segmentation ; Multi-Channel CT Enhancement ; nnUNet; SegResNet

Abstract: Head and neck (H\&N) cancer segmentation from PET/CT is challenging due to heterogeneous imaging protocols across centers and the small proportion of tumor and lymph node volumes relative to the full field-of-view. We propose a two-stage coarse-to-fine framework for automatic segmentation of primary tumors (GTVp) and metastatic lymph nodes (GTVn) in the HECKTOR 2025 challenge. The framework first applies a head localization stage using an nnUNet to extract a coarse region-of-interest (ROI). In the fine segmentation stage, we integrate predictions from two complementary backbones: nnUNetResEncUNetLarge and MONAI-based SegResNet, both trained with five-fold cross-validation. To further enhance tumor delineation, especially on CT modality and across centers, we introduce multi-channel CT representations by concatenating raw CT, its squared intensity, cubic-root intensity, and PET as four input channels for nnUNetResEncUNetLarge. This design improves sensitivity to tumor intensity patterns and robustness against inter-center heterogeneity. The framework was evaluated quantitatively on the official test set of task 1 for the HECKTOR2025 challenge, achieving a GTVp DSC of 0.7341, a GTVn aggregated DSC of 0.7312, and a GTVn aggregated F1 score of 0.7260 as team SJTU\_lab426.

Submission Number: 1