Staining normalization in histopathology: Method benchmarking using multicenter dataset

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khan, Umair, Härkönen, Jouni, Friman, Marjukka, Latonen, Leena, Kuopio, Teijo, Ruusuvuori, Pekka
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918068975828992
author Khan, Umair
Härkönen, Jouni
Friman, Marjukka
Latonen, Leena
Kuopio, Teijo
Ruusuvuori, Pekka
author_facet Khan, Umair
Härkönen, Jouni
Friman, Marjukka
Latonen, Leena
Kuopio, Teijo
Ruusuvuori, Pekka
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2506_19106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Staining normalization in histopathology: Method benchmarking using multicenter dataset
Khan, Umair
Härkönen, Jouni
Friman, Marjukka
Latonen, Leena
Kuopio, Teijo
Ruusuvuori, Pekka
Image and Video Processing
Computer Vision and Pattern Recognition
Tissues and Organs
I.2.1; I.4.0
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
title Staining normalization in histopathology: Method benchmarking using multicenter dataset
topic Image and Video Processing
Computer Vision and Pattern Recognition
Tissues and Organs
I.2.1; I.4.0
url https://arxiv.org/abs/2506.19106