Saved in:
Bibliographic Details
Main Authors: Wang, Jiamu, Kwak, Jin Tae
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.16160
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910840922308608
author Wang, Jiamu
Kwak, Jin Tae
author_facet Wang, Jiamu
Kwak, Jin Tae
contents In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce an efficient data augmentation method for pathology images, called USegMix. Given a set of pathology images, the proposed method generates a new, synthetic image in two phases. In the first phase, USegMix constructs a pool of tissue segments in an automated and unsupervised manner using superpixels and the Segment Anything Model (SAM). In the second phase, USegMix selects a candidate segment in a target image, replaces it with a similar segment from the segment pool, and blends them by using a pre-trained diffusion model. In this way, USegMix can generate diverse and realistic pathology images. We rigorously evaluate the effectiveness of USegMix on two pathology image datasets of colorectal and prostate cancers. The results demonstrate improvements in cancer classification performance, underscoring the substantial potential of USegMix for pathology image analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16160
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images
Wang, Jiamu
Kwak, Jin Tae
Computer Vision and Pattern Recognition
In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce an efficient data augmentation method for pathology images, called USegMix. Given a set of pathology images, the proposed method generates a new, synthetic image in two phases. In the first phase, USegMix constructs a pool of tissue segments in an automated and unsupervised manner using superpixels and the Segment Anything Model (SAM). In the second phase, USegMix selects a candidate segment in a target image, replaces it with a similar segment from the segment pool, and blends them by using a pre-trained diffusion model. In this way, USegMix can generate diverse and realistic pathology images. We rigorously evaluate the effectiveness of USegMix on two pathology image datasets of colorectal and prostate cancers. The results demonstrate improvements in cancer classification performance, underscoring the substantial potential of USegMix for pathology image analysis.
title USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.16160