UMambaAdj: Advancing GTV Segmentation for Head and Neck Cancer in MRI-Guided RT with UMamba and nnU-Net ResEnc Planner

TL;DR

This paper introduces UMambaAdj, a novel deep learning method combining UMamba and nnU-Net ResEnc to improve GTV segmentation in MRI-guided radiotherapy for head and neck cancer, achieving high accuracy on challenge data.

Contribution

The study presents a new integrated approach, UMambaAdj, that enhances tumor segmentation accuracy by combining long-range dependency capture and residual feature extraction techniques.

Findings

Achieved an aggregated DSC of 0.751 for GTVp.

Achieved an aggregated DSC of 0.842 for GTVn.

Mean DSC of 0.796 on the challenge test set.

Abstract

Magnetic Resonance Imaging (MRI) plays a crucial role in MRI-guided adaptive radiotherapy for head and neck cancer (HNC) due to its superior soft-tissue contrast. However, accurately segmenting the gross tumor volume (GTV), which includes both the primary tumor (GTVp) and lymph nodes (GTVn), remains challenging. Recently, two deep learning segmentation innovations have shown great promise: UMamba, which effectively captures long-range dependencies, and the nnU-Net Residual Encoder (ResEnc), which enhances feature extraction through multistage residual blocks. In this study, we integrate these strengths into a novel approach, termed 'UMambaAdj'. Our proposed method was evaluated on the HNTS-MRG 2024 challenge test set using pre-RT T2-weighted MRI images, achieving an aggregated Dice Similarity Coefficient (DSCagg) of 0.751 for GTVp and 0.842 for GTVn, with a mean DSCagg of 0.796. This approach demonstrates potential for more precise tumor delineation in MRI-guided adaptive radiotherapy, ultimately improving treatment outcomes for HNC patients. Team: DCPT-Stine's group.