The utility of color normalization for AI‐based diagnosis of hematoxylin and eosin‐stained pathology images

Abstract

The color variation of hematoxylin and eosin (H&E)-stained tissues has presented a challenge for applications of artificial intelligence (AI) in digital pathology. Many color normalization algorithms have been developed in recent years in order to reduce the color variation between H&E images. However, previous efforts in benchmarking these algorithms have produced conflicting results and none have sufficiently assessed the efficacy of the various color normalization methods for improving diagnostic performance of AI systems. In this study, we systematically investigated eight color normalization algorithms for AI-based classification of H&E-stained histopathology slides, in the context of using images both from one center and from multiple centers. Our results show that color normalization does not consistently improve classification performance when both training and testing data are from a single center. However, using four multi-center datasets of two cancer types (ovarian and pleural) and objective functions, we show that color normalization can significantly improve the classification accuracy of images from external datasets (ovarian cancer: 0.25 AUC increase, p = 1.6 e-05; pleural cancer: 0.21 AUC increase, p = 1.4 e-10). Furthermore, we introduce a novel augmentation strategy by mixing color-normalized images using three easily accessible algorithms that consistently improves the diagnosis of test images from external centers, even when the individual normalization methods had varied results. We anticipate our study to be a starting point for reliable use of color normalization to improve AI-based, digital pathology-empowered diagnosis of cancers sourced from multiple centers.

Computational tumor stroma reaction evaluation led to novel prognosis-associated fibrosis and molecular signature discoveries in high-grade serous ovarian carcinoma

“…Many previous studies introduced color normalization methods to minimize staining inconsistencies ( 29 , 37 ). Though it is hard to measure the preservation of diagnostic information after image transformation, many integrative studies investigating cancer subtype classification and prognosis association achieved optimistic performances by introducing image normalization ( 38 , 39 ). From this point of view, color normalization could be beneficial for assorted research cohort from miscellaneous data sources, especially from multiple institutions.…”

Whole Slide Image Quality in Digital Pathology: Review and Perspectives

“…In contrast to the previously mentioned studies, they reported a significant gain in performance with the color normalization of [113]. Finally, in [141], the influence of several color normalization algorithms [100], [103], [106], [108], [111], [113] has been studied for the classification of three different histological cancer H&E WSIs (ovarian, breast, and pleural) using a ResNet18 network. Their finding is that color normalization does not improve performance when WSIs are from the same center.…”

Multi-modality artificial intelligence in digital pathology

“…To enhance the generalization of the model, validation experiments on data from multiple sources are necessary. Meanwhile data batch effects [ 194 ] place high demands on data preprocessing [ 195 ]. For addressing the data noise problem, standardized data preprocessing systems [ 196 , 197 ] or uniform collection standards should be proposed accordingly.…”