Staining normalization in histopathology: Method benchmarking using multicenter dataset
This work addresses the challenge of stain inconsistency for pathologists and AI-based analysis in histopathology, though it is incremental as it benchmarks existing methods rather than introducing new ones.
The authors tackled the problem of staining variation in histopathology images by benchmarking eight normalization methods on a unique multi-center dataset, finding that deep learning methods like CycleGAN and Pix2pix variants performed competitively but with no single method dominating across all metrics.
Hematoxylin and Eosin (H&E) has been the gold standard in tissue analysis for decades, however, tissue specimens stained in different laboratories vary, often significantly, in appearance. This variation poses a challenge for both pathologists' and AI-based downstream analysis. Minimizing stain variation computationally is an active area of research. To further investigate this problem, we collected a unique multi-center tissue image dataset, wherein tissue samples from colon, kidney, and skin tissue blocks were distributed to 66 different labs for routine H&E staining. To isolate staining variation, other factors affecting the tissue appearance were kept constant. Further, we used this tissue image dataset to compare the performance of eight different stain normalization methods, including four traditional methods, namely, histogram matching, Macenko, Vahadane, and Reinhard normalization, and two deep learning-based methods namely CycleGAN and Pixp2pix, both with two variants each. We used both quantitative and qualitative evaluation to assess the performance of these methods. The dataset's inter-laboratory staining variation could also guide strategies to improve model generalizability through varied training data