FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images

TL;DR

FocalUNETR introduces a boundary-aware transformer architecture that enhances prostate segmentation in CT images by capturing local and global features, significantly improving accuracy over existing methods.

Contribution

The paper proposes a novel focal transformer model with boundary-induced label regression for improved CT prostate segmentation, addressing boundary ambiguity and long-range context limitations.

Findings

Achieved higher Dice Similarity Coefficient

Reduced Hausdorff Distance and Average Symmetric Surface Distance

Outperformed competing methods on private and public datasets

Abstract

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}.