FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images
This work addresses the problem of unclear prostate boundaries in CT images for medical treatment planning, representing an incremental improvement over existing methods.
The authors tackled the challenge of precise prostate segmentation in CT images, which suffers from unclear boundaries and limited global context capture, by proposing a focal transformer-based architecture with an auxiliary boundary-induced label regression task, achieving higher Dice Similarity Coefficient and lower Hausdorff Distance on private and public datasets.
Computed Tomography (CT) based precise prostate segmentation for treatment planning is challenging due to (1) the unclear boundary of the prostate derived from CT's poor soft tissue contrast and (2) the limitation of convolutional neural network-based models in capturing long-range global context. Here we propose a novel focal transformer-based image segmentation architecture to effectively and efficiently extract local visual features and global context from CT images. Additionally, we design an auxiliary boundary-induced label regression task coupled with the main prostate segmentation task to address the unclear boundary issue in CT images. We demonstrate that this design significantly improves the quality of the CT-based prostate segmentation task over other competing methods, resulting in substantially improved performance, i.e., higher Dice Similarity Coefficient, lower Hausdorff Distance, and Average Symmetric Surface Distance, on both private and public CT image datasets. Our code is available at this \href{https://github.com/ChengyinLee/FocalUNETR.git}{link}.