Universitat Politècnica de Catalunya - BarcelonaTech (UPC), Barcelona East Engineering School, Department of Mathematics, Barcelona, Spain.
Hospital Clínic of Barcelona-IDIBAPS, Biochemistry and Molecular Genetics Department, CORE Laboratory, Biomedical Diagnostic, Barcelona, Spain.
Comput Methods Programs Biomed. 2023 Oct;240:107629. doi: 10.1016/j.cmpb.2023.107629. Epub 2023 May 30.
Combining knowledge of clinical pathologists and deep learning models is a growing trend in morphological analysis of cells circulating in blood to add objectivity, accuracy, and speed in diagnosing hematological and non-hematological diseases. However, the variability in staining protocols across different laboratories can affect the color of images and performance of automatic recognition models. The objective of this work is to develop, train and evaluate a new system for the normalization of color staining of peripheral blood cell images, so that it transforms images from different centers to map the color staining of a reference center (RC) while preserving the structural morphological features.
The system has two modules, GAN1 and GAN2. GAN1 uses the PIX2PIX technique to fade original color images to an adaptive gray, while GAN2 transforms them into RGB normalized images. Both GANs have a similar structure, where the generator is a U-NET convolutional neural network with ResNet and the discriminator is a classifier with ResNet34 structure. Digitally stained images were evaluated using GAN metrics and histograms to assess the ability to modify color without altering cell morphology. The system was also evaluated as a pre-processing tool before cells undergo a classification process. For this purpose, a CNN classifier was designed for three classes: abnormal lymphocytes, blasts and reactive lymphocytes.
Training of all GANs and the classifier was performed using RC images, while evaluations were conducted using images from four other centers. Classification tests were performed before and after applying the stain normalization system. The overall accuracy reached a similar value around 96% in both cases for the RC images, indicating the neutrality of the normalization model for the reference images. On the contrary, it was a significant improvement in the classification performance when applying the stain normalization to the other centers. Reactive lymphocytes were the most sensitive to stain normalization, with true positive rates (TPR) increasing from 46.3% - 66% for the original images to 81.2% - 97.2% after digital staining. Abnormal lymphocytes TPR ranged from 31.9% - 95.7% with original images to 83% - 100% with digitally stained images. Blast class showed TPR ranges of 90.3% - 94.4% and 94.4% - 100%, for original and stained images, respectively.
The proposed GAN-based normalization staining approach improves the performance of classifiers with multicenter data sets by generating digitally stained images with a quality similar to the original images and adaptability to a reference staining standard. The system requires low computation cost and can help improve the performance of automatic recognition models in clinical settings.
将临床病理学家的知识与深度学习模型相结合，是对血液中循环细胞进行形态分析的一个新兴趋势，可提高血液和非血液疾病诊断的客观性、准确性和速度。然而，不同实验室之间染色方案的可变性会影响图像的颜色和自动识别模型的性能。本研究的目的是开发、训练和评估一种新的外周血细胞图像染色标准化系统，使其能够将来自不同中心的图像转换为参考中心（RC）的颜色染色，同时保留结构形态特征。
该系统有两个模块，即 GAN1 和 GAN2。GAN1 使用 PIX2PIX 技术将原始彩色图像淡化为自适应灰度，而 GAN2 将其转换为 RGB 标准化图像。两个 GAN 具有相似的结构，生成器是带有 ResNet 的 U-NET 卷积神经网络，鉴别器是带有 ResNet34 结构的分类器。使用 GAN 指标和直方图评估数字化染色图像，以评估在不改变细胞形态的情况下改变颜色的能力。还评估了该系统作为细胞进行分类过程之前的预处理工具。为此，设计了一个用于三类的 CNN 分类器：异常淋巴细胞、原始细胞和反应性淋巴细胞。
所有 GAN 和分类器的训练都是使用 RC 图像进行的，而评估则是使用来自其他四个中心的图像进行的。在应用染色标准化系统之前和之后进行分类测试。在 RC 图像的情况下，整体准确率达到相似的约 96%，表明标准化模型对参考图像是中立的。相反，当将染色标准化应用于其他中心时，分类性能有显著提高。反应性淋巴细胞对染色标准化最为敏感，原始图像的真阳性率（TPR）从 46.3%增加到 66%，数字化染色后的 TPR 从 81.2%增加到 97.2%。异常淋巴细胞的 TPR 范围为 31.9%至 95.7%，原始图像为 83%至 100%，数字化染色图像为 83%至 100%。原始图像的 Blast 类 TPR 范围为 90.3%至 94.4%，数字化染色图像的 TPR 范围为 94.4%至 100%。
提出的基于 GAN 的标准化染色方法通过生成与原始图像质量相似且适应参考染色标准的数字化染色图像，提高了多中心数据集分类器的性能。该系统需要较低的计算成本，并有助于提高临床环境中自动识别模型的性能。
