Stain-aware Domain Alignment for Imbalance Blood Cell Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Yongcheng, Cai, Lingcong, Lu, Ying, Fu, Xianghua, Han, Xiao, Li, Ma, Lai, Wenxing, Zhang, Xiangzhong, Fan, Xiaomao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913596680699904
author Li, Yongcheng
Cai, Lingcong
Lu, Ying
Fu, Xianghua
Han, Xiao
Li, Ma
Lai, Wenxing
Zhang, Xiangzhong
Fan, Xiaomao
author_facet Li, Yongcheng
Cai, Lingcong
Lu, Ying
Fu, Xianghua
Han, Xiao
Li, Ma
Lai, Wenxing
Zhang, Xiangzhong
Fan, Xiaomao
contents Blood cell identification is critical for hematological analysis as it aids physicians in diagnosing various blood-related diseases. In real-world scenarios, blood cell image datasets often present the issues of domain shift and data imbalance, posing challenges for accurate blood cell identification. To address these issues, we propose a novel blood cell classification method termed SADA via stain-aware domain alignment. The primary objective of this work is to mine domain-invariant features in the presence of domain shifts and data imbalances. To accomplish this objective, we propose a stain-based augmentation approach and a local alignment constraint to learn domain-invariant features. Furthermore, we propose a domain-invariant supervised contrastive learning strategy to capture discriminative features. We decouple the training process into two stages of domain-invariant feature learning and classification training, alleviating the problem of data imbalance. Experiment results on four public blood cell datasets and a private real dataset collected from the Third Affiliated Hospital of Sun Yat-sen University demonstrate that SADA can achieve a new state-of-the-art baseline, which is superior to the existing cutting-edge methods with a big margin. The source code can be available at the URL (\url{https://github.com/AnoK3111/SADA}).
format Preprint
id arxiv_https___arxiv_org_abs_2412_02976
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stain-aware Domain Alignment for Imbalance Blood Cell Classification
Li, Yongcheng
Cai, Lingcong
Lu, Ying
Fu, Xianghua
Han, Xiao
Li, Ma
Lai, Wenxing
Zhang, Xiangzhong
Fan, Xiaomao
Computer Vision and Pattern Recognition
Blood cell identification is critical for hematological analysis as it aids physicians in diagnosing various blood-related diseases. In real-world scenarios, blood cell image datasets often present the issues of domain shift and data imbalance, posing challenges for accurate blood cell identification. To address these issues, we propose a novel blood cell classification method termed SADA via stain-aware domain alignment. The primary objective of this work is to mine domain-invariant features in the presence of domain shifts and data imbalances. To accomplish this objective, we propose a stain-based augmentation approach and a local alignment constraint to learn domain-invariant features. Furthermore, we propose a domain-invariant supervised contrastive learning strategy to capture discriminative features. We decouple the training process into two stages of domain-invariant feature learning and classification training, alleviating the problem of data imbalance. Experiment results on four public blood cell datasets and a private real dataset collected from the Third Affiliated Hospital of Sun Yat-sen University demonstrate that SADA can achieve a new state-of-the-art baseline, which is superior to the existing cutting-edge methods with a big margin. The source code can be available at the URL (\url{https://github.com/AnoK3111/SADA}).
title Stain-aware Domain Alignment for Imbalance Blood Cell Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.02976