Unit-Based Histopathology Tissue Segmentation via Multi-Level Feature Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shakarami, Ashkan, Farshad, Azade, Yeganeh, Yousef, Nicole, Lorenzo, Schüffler, Peter, Ghidoni, Stefano, Navab, Nassir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917058900393984
author Shakarami, Ashkan
Farshad, Azade
Yeganeh, Yousef
Nicole, Lorenzo
Schüffler, Peter
Ghidoni, Stefano
Navab, Nassir
author_facet Shakarami, Ashkan
Farshad, Azade
Yeganeh, Yousef
Nicole, Lorenzo
Schüffler, Peter
Ghidoni, Stefano
Navab, Nassir
contents We propose UTS, a unit-based tissue segmentation framework for histopathology that classifies each fixed-size 32 * 32 tile, rather than each pixel, as the segmentation unit. This approach reduces annotation effort and improves computational efficiency without compromising accuracy. To implement this approach, we introduce a Multi-Level Vision Transformer (L-ViT), which benefits the multi-level feature representation to capture both fine-grained morphology and global tissue context. Trained to segment breast tissue into three categories (infiltrating tumor, non-neoplastic stroma, and fat), UTS supports clinically relevant tasks such as tumor-stroma quantification and surgical margin assessment. Evaluated on 386,371 tiles from 459 H&E-stained regions, it outperforms U-Net variants and transformer-based baselines. Code and Dataset will be available at GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12427
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unit-Based Histopathology Tissue Segmentation via Multi-Level Feature Representation
Shakarami, Ashkan
Farshad, Azade
Yeganeh, Yousef
Nicole, Lorenzo
Schüffler, Peter
Ghidoni, Stefano
Navab, Nassir
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
We propose UTS, a unit-based tissue segmentation framework for histopathology that classifies each fixed-size 32 * 32 tile, rather than each pixel, as the segmentation unit. This approach reduces annotation effort and improves computational efficiency without compromising accuracy. To implement this approach, we introduce a Multi-Level Vision Transformer (L-ViT), which benefits the multi-level feature representation to capture both fine-grained morphology and global tissue context. Trained to segment breast tissue into three categories (infiltrating tumor, non-neoplastic stroma, and fat), UTS supports clinically relevant tasks such as tumor-stroma quantification and surgical margin assessment. Evaluated on 386,371 tiles from 459 H&E-stained regions, it outperforms U-Net variants and transformer-based baselines. Code and Dataset will be available at GitHub.
title Unit-Based Histopathology Tissue Segmentation via Multi-Level Feature Representation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.12427