Leveraging Semantic Asymmetry for Precise Gross Tumor Volume Segmentation of Nasopharyngeal Carcinoma in Planning CT

2024-11-27

arXiv.org

AI Summary

Automatic gross tumor volume (GTV) segmentation in non-contrast CT for nasopharyngeal carcinoma (NPC) radiotherapy is hindered by low soft-tissue contrast and registration errors between MRI and CT, limiting segmentation accuracy. Method: This work proposes the first end-to-end segmentation framework leveraging anatomical symmetry priors. It explicitly models the bilateral symmetry of healthy nasopharyngeal structures as a learnable geometric-semantic constraint via a Siamese contrastive learning architecture. Key components include a voxel-wise contrastive loss, flip-invariance regularization, and a symmetry-aware feature distance metric—eliminating the need for MRI–CT registration. Contribution/Results: The method significantly enhances detection of subtle tumor boundaries. On an external test set, it achieves a ≥2% improvement in Dice score and a 12% reduction in mean surface distance error, establishing new state-of-the-art performance for automatic NPC GTV segmentation on non-contrast CT.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Privacy-enhancing technologies

Abstract

In the radiation therapy of nasopharyngeal carcinoma (NPC), clinicians typically delineate the gross tumor volume (GTV) using non-contrast planning computed tomography to ensure accurate radiation dose delivery. However, the low contrast between tumors and adjacent normal tissues necessitates that radiation oncologists manually delineate the tumors, often relying on diagnostic MRI for guidance. % In this study, we propose a novel approach to directly segment NPC gross tumors on non-contrast planning CT images, circumventing potential registration errors when aligning MRI or MRI-derived tumor masks to planning CT. To address the low contrast issues between tumors and adjacent normal structures in planning CT, we introduce a 3D Semantic Asymmetry Tumor segmentation (SATs) method. Specifically, we posit that a healthy nasopharyngeal region is characteristically bilaterally symmetric, whereas the emergence of nasopharyngeal carcinoma disrupts this symmetry. Then, we propose a Siamese contrastive learning segmentation framework that minimizes the voxel-wise distance between original and flipped areas without tumor and encourages a larger distance between original and flipped areas with tumor. Thus, our approach enhances the sensitivity of features to semantic asymmetries. % Extensive experiments demonstrate that the proposed SATs achieves the leading NPC GTV segmentation performance in both internal and external testing, emph{e.g.}, with at least 2% absolute Dice score improvement and 12% average distance error reduction when compared to other state-of-the-art methods in the external testing.

Problem

• Segments NPC tumors in low-contrast CT images
• Reduces reliance on MRI for tumor delineation
• Improves accuracy via semantic asymmetry learning

Innovation

• 3D Semantic Asymmetry Tumor segmentation method
• Siamese contrastive learning segmentation framework
• Enhances sensitivity to semantic asymmetries