Leveraging Semantic Asymmetry for Precise Gross Tumor Volume Segmentation of Nasopharyngeal Carcinoma in Planning CT
This work addresses the challenge of precise tumor segmentation for radiation therapy planning in nasopharyngeal carcinoma, offering a solution to reduce manual delineation and registration errors, though it is incremental as it builds on existing segmentation techniques with a novel symmetry-based approach.
The paper tackles the problem of segmenting gross tumor volume (GTV) for nasopharyngeal carcinoma in low-contrast planning CT images by proposing a 3D Semantic Asymmetry Tumor segmentation (SATs) method, which achieves at least a 2% absolute Dice score improvement and 12% average distance error reduction compared to state-of-the-art methods in external testing.
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.