High-Resolution Boundary Detection for Medical Image Segmentation with Piece-Wise Two-Sample T-Test Augmented Loss

TL;DR

This paper introduces a novel loss function called PTA that enhances boundary detection in medical image segmentation by incorporating a statistical two-sample t-test, improving over traditional losses.

Contribution

The paper proposes the PTA loss, a new boundary-aware loss function that integrates a statistical t-test to better detect boundaries in medical images.

Findings

PTA loss improves boundary detection accuracy.

PTA outperforms benchmark loss functions.

Enhanced segmentation quality at boundaries.

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.