TY - JOUR
T1 - Learnable color space conversion and fusion for stain normalization in pathology images
AU - Ke, Jing
AU - Zhou, Yijin
AU - Shen, Yiqing
AU - Guo, Yi
AU - Liu, Ning
AU - Han, Xiaodan
AU - Shen, Dinggang
PY - 2025
Y1 - 2025
N2 - Variations in hue and contrast are common in H&E-stained pathology images due to differences in slide preparation across various institutions. Such stain variations, while not affecting pathologists much in diagnosing the biopsy, pose significant challenges for computer-assisted diagnostic systems, leading to potential underdiagnosis or misdiagnosis, especially when stain differentiation introduces substantial heterogeneity across datasets from different sources. Traditional stain normalization methods, aimed at mitigating these issues, often require labor-intensive selection of appropriate templates, limiting their practicality and automation. Innovatively, we propose a Learnable Stain Normalization layer, i.e. LStainNorm, designed as an easily integrable component for pathology image analysis. It minimizes the need for manual template selection by autonomously learning the optimal stain characteristics. Moreover, the learned optimal stain template provides the interpretability to enhance the understanding of the normalization process. Additionally, we demonstrate that fusing pathology images normalized in multiple color spaces can improve performance. Therefore, we extend LStainNorm with a novel self-attention mechanism to facilitate the fusion of features across different attributes and color spaces. Experimentally, LStainNorm outperforms the state-of-the-art methods including conventional ones and GANs on two classification datasets and three nuclei segmentation datasets by an average increase of 4.78% in accuracy, 3.53% in Dice coefficient, and 6.59% in IoU. Additionally, by enabling an end-to-end training and inference process, LStainNorm eliminates the need for intermediate steps between normalization and analysis, resulting in more efficient use of hardware resources and significantly faster inference time, i.e up to hundreds of times quicker than traditional methods. The code is publicly available at https://github.com/yjzscode/Optimal-Normalisation-in-Color-Spaces.
AB - Variations in hue and contrast are common in H&E-stained pathology images due to differences in slide preparation across various institutions. Such stain variations, while not affecting pathologists much in diagnosing the biopsy, pose significant challenges for computer-assisted diagnostic systems, leading to potential underdiagnosis or misdiagnosis, especially when stain differentiation introduces substantial heterogeneity across datasets from different sources. Traditional stain normalization methods, aimed at mitigating these issues, often require labor-intensive selection of appropriate templates, limiting their practicality and automation. Innovatively, we propose a Learnable Stain Normalization layer, i.e. LStainNorm, designed as an easily integrable component for pathology image analysis. It minimizes the need for manual template selection by autonomously learning the optimal stain characteristics. Moreover, the learned optimal stain template provides the interpretability to enhance the understanding of the normalization process. Additionally, we demonstrate that fusing pathology images normalized in multiple color spaces can improve performance. Therefore, we extend LStainNorm with a novel self-attention mechanism to facilitate the fusion of features across different attributes and color spaces. Experimentally, LStainNorm outperforms the state-of-the-art methods including conventional ones and GANs on two classification datasets and three nuclei segmentation datasets by an average increase of 4.78% in accuracy, 3.53% in Dice coefficient, and 6.59% in IoU. Additionally, by enabling an end-to-end training and inference process, LStainNorm eliminates the need for intermediate steps between normalization and analysis, resulting in more efficient use of hardware resources and significantly faster inference time, i.e up to hundreds of times quicker than traditional methods. The code is publicly available at https://github.com/yjzscode/Optimal-Normalisation-in-Color-Spaces.
KW - Learnable color space conversion
KW - Pathology image analysis
KW - Stain normalization
UR - http://www.scopus.com/inward/record.url?scp=85213555794&partnerID=8YFLogxK
UR - https://ezproxy.uws.edu.au/login?url=https://doi.org/10.1016/j.media.2024.103424
U2 - 10.1016/j.media.2024.103424
DO - 10.1016/j.media.2024.103424
M3 - Article
AN - SCOPUS:85213555794
SN - 1361-8415
VL - 101
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 103424
ER -