Patch-Based Cervical Cancer Segmentation using Distance from Boundary of Tissue

TL;DR

This paper introduces a patch-based cervical cancer segmentation method that incorporates global boundary distance information to improve accuracy in classifying cancer regions in large Whole Slide Images.

Contribution

The novel use of Distance from Boundary of tissue (DfB) as global information enhances patch-based segmentation accuracy for cervical cancer in WSIs.

Findings

Improved segmentation performance over conventional methods.

Effective integration of global boundary information.

Validated on three-class cervical cancer classification.

Abstract

Pathological diagnosis is used for examining cancer in detail, and its automation is in demand. To automatically segment each cancer area, a patch-based approach is usually used since a Whole Slide Image (WSI) is huge. However, this approach loses the global information needed to distinguish between classes. In this paper, we utilized the Distance from the Boundary of tissue (DfB), which is global information that can be extracted from the original image. We experimentally applied our method to the three-class classification of cervical cancer, and found that it improved the total performance compared with the conventional method.