CTI-Unet: Cascaded Threshold Integration for Improved U-Net Segmentation of Pathology Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Mingyang, Liang, Yuqiu, Wang, Jiacheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913783010557952
author Zhu, Mingyang
Liang, Yuqiu
Wang, Jiacheng
author_facet Zhu, Mingyang
Liang, Yuqiu
Wang, Jiacheng
contents Chronic kidney disease (CKD) is a growing global health concern, necessitating precise and efficient image analysis to aid diagnosis and treatment planning. Automated segmentation of kidney pathology images plays a central role in facilitating clinical workflows, yet conventional segmentation models often require delicate threshold tuning. This paper proposes a novel \textit{Cascaded Threshold-Integrated U-Net (CTI-Unet)} to overcome the limitations of single-threshold segmentation. By sequentially integrating multiple thresholded outputs, our approach can reconcile noise suppression with the preservation of finer structural details. Experiments on the challenging KPIs2024 dataset demonstrate that CTI-Unet outperforms state-of-the-art architectures such as nnU-Net, Swin-Unet, and CE-Net, offering a robust and flexible framework for kidney pathology image segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05640
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CTI-Unet: Cascaded Threshold Integration for Improved U-Net Segmentation of Pathology Images
Zhu, Mingyang
Liang, Yuqiu
Wang, Jiacheng
Image and Video Processing
Computer Vision and Pattern Recognition
Chronic kidney disease (CKD) is a growing global health concern, necessitating precise and efficient image analysis to aid diagnosis and treatment planning. Automated segmentation of kidney pathology images plays a central role in facilitating clinical workflows, yet conventional segmentation models often require delicate threshold tuning. This paper proposes a novel \textit{Cascaded Threshold-Integrated U-Net (CTI-Unet)} to overcome the limitations of single-threshold segmentation. By sequentially integrating multiple thresholded outputs, our approach can reconcile noise suppression with the preservation of finer structural details. Experiments on the challenging KPIs2024 dataset demonstrate that CTI-Unet outperforms state-of-the-art architectures such as nnU-Net, Swin-Unet, and CE-Net, offering a robust and flexible framework for kidney pathology image segmentation.
title CTI-Unet: Cascaded Threshold Integration for Improved U-Net Segmentation of Pathology Images
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.05640