Ke Jing, Zhou Yijin, Shen Yiqing, Guo Yi, Liu Ning, Han Xiaodan, Shen Dinggang
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China; School of Computer Science and Engineering, University of New South Wales, Australia.
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China.
Med Image Anal. 2025 Apr;101:103424. doi: 10.1016/j.media.2024.103424. Epub 2024 Dec 24.
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.
由于不同机构在玻片制备方面存在差异，苏木精-伊红（H&E）染色的病理图像中色调和对比度的变化很常见。这种染色变化虽然在病理学家诊断活检时影响不大，但对计算机辅助诊断系统构成了重大挑战，可能导致潜在的漏诊或误诊，尤其是当染色差异在来自不同来源的数据集中引入大量异质性时。旨在缓解这些问题的传统染色归一化方法通常需要人工密集地选择合适的模板，限制了它们的实用性和自动化程度。创新性地，我们提出了一种可学习的染色归一化层，即LStainNorm，它被设计为病理图像分析中易于集成的组件。它通过自主学习最佳染色特征，最大限度地减少了人工模板选择的需求。此外，学习到的最佳染色模板提供了可解释性，以增强对归一化过程的理解。此外，我们证明融合在多个颜色空间中归一化的病理图像可以提高性能。因此，我们用一种新颖的自注意力机制扩展了LStainNorm，以促进跨不同属性和颜色空间的特征融合。实验表明，在两个分类数据集和三个细胞核分割数据集上，LStainNorm的性能优于包括传统方法和生成对抗网络（GAN）在内的现有方法，准确率平均提高4.78%，Dice系数提高3.53%，交并比（IoU）提高6.59%。此外，通过实现端到端的训练和推理过程，LStainNorm无需在归一化和分析之间进行中间步骤，从而更有效地利用硬件资源，推理时间显著加快，即比传统方法快数百倍。代码可在https://github.com/yjzscode/Optimal-Normalisation-in-Color-Spaces上公开获取。
