Hard Negative Sample Mining for Whole Slide Image Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Wentao, Hu, Xiaoling, Abousamra, Shahira, Prasanna, Prateek, Chen, Chao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916421781422080
author Huang, Wentao
Hu, Xiaoling
Abousamra, Shahira
Prasanna, Prateek
Chen, Chao
author_facet Huang, Wentao
Hu, Xiaoling
Abousamra, Shahira
Prasanna, Prateek
Chen, Chao
contents Weakly supervised whole slide image (WSI) classification is challenging due to the lack of patch-level labels and high computational costs. State-of-the-art methods use self-supervised patch-wise feature representations for multiple instance learning (MIL). Recently, methods have been proposed to fine-tune the feature representation on the downstream task using pseudo labeling, but mostly focusing on selecting high-quality positive patches. In this paper, we propose to mine hard negative samples during fine-tuning. This allows us to obtain better feature representations and reduce the training cost. Furthermore, we propose a novel patch-wise ranking loss in MIL to better exploit these hard negative samples. Experiments on two public datasets demonstrate the efficacy of these proposed ideas. Our codes are available at https://github.com/winston52/HNM-WSI
format Preprint
id arxiv_https___arxiv_org_abs_2410_02212
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hard Negative Sample Mining for Whole Slide Image Classification
Huang, Wentao
Hu, Xiaoling
Abousamra, Shahira
Prasanna, Prateek
Chen, Chao
Computer Vision and Pattern Recognition
Weakly supervised whole slide image (WSI) classification is challenging due to the lack of patch-level labels and high computational costs. State-of-the-art methods use self-supervised patch-wise feature representations for multiple instance learning (MIL). Recently, methods have been proposed to fine-tune the feature representation on the downstream task using pseudo labeling, but mostly focusing on selecting high-quality positive patches. In this paper, we propose to mine hard negative samples during fine-tuning. This allows us to obtain better feature representations and reduce the training cost. Furthermore, we propose a novel patch-wise ranking loss in MIL to better exploit these hard negative samples. Experiments on two public datasets demonstrate the efficacy of these proposed ideas. Our codes are available at https://github.com/winston52/HNM-WSI
title Hard Negative Sample Mining for Whole Slide Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.02212