High-Resolution Boundary Detection for Medical Image Segmentation with Piece-Wise Two-Sample T-Test Augmented Loss
Abstract
Deep learning methods have contributed substantially to the rapid advancement of medical image segmentation, the quality of which relies on the suitable design of loss functions. Popular loss functions, including the cross-entropy and dice losses, often fall short of boundary detection, thereby limiting high-resolution downstream applications such as automated diagnoses and procedures. We developed a novel loss function that is tailored to reflect the boundary information to enhance the boundary detection. As the contrast between segmentation and background regions along the classification boundary naturally induces heterogeneity over the pixels, we propose the piece-wise two-sample t-test augmented (PTA) loss that is infused with the statistical test for such heterogeneity. We demonstrate the improved boundary detection power of the PTA loss compared to benchmark losses without a t-test component.
Cite
@article{arxiv.2211.02419,
title = {High-Resolution Boundary Detection for Medical Image Segmentation with Piece-Wise Two-Sample T-Test Augmented Loss},
author = {Yucong Lin and Jinhua Su and Yuhang Li and Yuhao Wei and Hanchao Yan and Saining Zhang and Jiaan Luo and Danni Ai and Hong Song and Jingfan Fan and Tianyu Fu and Deqiang Xiao and Feifei Wang and Jue Hou and Jian Yang},
journal= {arXiv preprint arXiv:2211.02419},
year = {2022}
}