Ji Cunyuan, Oshima Kengo, Urata Takumi, Kimura Fumikazu, Ishii Keiko, Uehara Takeshi, Suzuki Kenji, Takeyama Saori, Yamaguchi Masahiro
Tokyo Institute of Technology, School of Engineering, Department of Information and Communications Engineering, Yokohama, Japan.
Shinshu University, School of Health Sciences, Department of Biomedical Laboratory Sciences, Matsumoto, Japan.
J Med Imaging (Bellingham). 2024 Jul;11(4):047501. doi: 10.1117/1.JMI.11.4.047501. Epub 2024 Jul 30.
Endometrial cancer (EC) is one of the most common types of cancer affecting women. While the hematoxylin-and-eosin (H&E) staining remains the standard for histological analysis, the immunohistochemistry (IHC) method provides molecular-level visualizations. Our study proposes a digital staining method to generate the hematoxylin-3,3'-diaminobenzidine (H-DAB) IHC stain of Ki-67 for the whole slide image of the EC tumor from its H&E stain counterpart.
We employed a color unmixing technique to yield stain density maps from the optical density (OD) of the stains and utilized the U-Net for end-to-end inference. The effectiveness of the proposed method was evaluated using the Pearson correlation between the digital and physical stain's labeling index (LI), a key metric indicating tumor proliferation. Two different cross-validation schemes were designed in our study: intraslide validation and cross-case validation (CCV). In the widely used intraslide scheme, the training and validation sets might include different regions from the same slide. The rigorous CCV validation scheme strictly prohibited any validation slide from contributing to training.
The proposed method yielded a high-resolution digital stain with preserved histological features, indicating a reliable correlation with the physical stain in terms of the Ki-67 LI. In the intraslide scheme, using intraslide patches resulted in a biased accuracy (e.g., ) significantly higher than that of CCV. The CCV scheme retained a fair correlation (e.g., ) between the LIs calculated from the digital stain and its physical IHC counterpart. Inferring the OD of the IHC stain from that of the H&E stain enhanced the correlation metric, outperforming that of the baseline model using the RGB space.
Our study revealed that molecule-level insights could be obtained from H&E images using deep learning. Furthermore, the improvement brought via OD inference indicated a possible method for creating more generalizable models for digital staining via per-stain analysis.
子宫内膜癌（EC）是影响女性的最常见癌症类型之一。虽然苏木精-伊红（H&E）染色仍是组织学分析的标准方法，但免疫组织化学（IHC）方法可提供分子水平的可视化。我们的研究提出了一种数字染色方法，用于从EC肿瘤的H&E染色对应物生成Ki-67的苏木精-3,3'-二氨基联苯胺（H-DAB）免疫组化全玻片图像染色。
我们采用颜色解混技术从染色的光密度（OD）生成染色密度图，并利用U-Net进行端到端推理。使用数字染色和物理染色的标记指数（LI）之间的皮尔逊相关性评估所提出方法的有效性，LI是指示肿瘤增殖的关键指标。我们的研究设计了两种不同的交叉验证方案：玻片内验证和跨病例验证（CCV）。在广泛使用的玻片内方案中，训练集和验证集可能包括来自同一张玻片的不同区域。严格的CCV验证方案严格禁止任何验证玻片用于训练。
所提出的方法产生了具有保留组织学特征的高分辨率数字染色，表明在Ki-67 LI方面与物理染色具有可靠的相关性。在玻片内方案中，使用玻片内补丁导致偏差精度（例如， ）显著高于CCV。CCV方案在从数字染色及其物理免疫组化对应物计算的LI之间保持了合理的相关性（例如， ）。从H&E染色推断免疫组化染色的OD增强了相关性指标，优于使用RGB空间的基线模型。
我们的研究表明，使用深度学习可以从H&E图像中获得分子水平的见解。此外，通过OD推断带来的改进表明了一种通过逐染色分析创建更通用数字染色模型的可能方法。
