A comparative evaluation of image-to-image translation methods for stain transfer in histopathology

Igor Zingman, Sergio Frayle, Ivan Tankoyeu, Sergey Sukhanov, Fabian Heinemann
Medical Imaging with Deep Learning, PMLR 227:1509-1525, 2024.

Abstract

Image-to-image translation (I2I) methods allow the generation of artificial images that share the content of the original image but have a different style. With the advances in Generative Adversarial Networks (GANs)-based methods, I2I methods enabled the generation of artificial images that are indistinguishable from natural images. Recently, I2I methods were also employed in histopathology for generating artificial images of in silico stained tissues from a different type of staining. We refer to this process as stain transfer. The number of I2I variants is constantly increasing, which makes a well justified choice of the most suitable I2I methods for stain transfer challenging. In our work, we compare twelve stain transfer approaches, three of which are based on traditional and nine on GAN-based image processing methods. The analysis relies on complementary quantitative measures for the quality of image translation, the assessment of the suitability for deep learning-based tissue grading, and the visual evaluation by pathologists. Our study highlights the strengths and weaknesses of the stain transfer approaches, thereby allowing a rational choice of the underlying I2I algorithms. Code, data, and trained models for stain transfer between H&E and Masson’s Trichrome staining will be made available online.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-zingman24a, title = {A comparative evaluation of image-to-image translation methods for stain transfer in histopathology}, author = {Zingman, Igor and Frayle, Sergio and Tankoyeu, Ivan and Sukhanov, Sergey and Heinemann, Fabian}, booktitle = {Medical Imaging with Deep Learning}, pages = {1509--1525}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/zingman24a/zingman24a.pdf}, url = {https://proceedings.mlr.press/v227/zingman24a.html}, abstract = {Image-to-image translation (I2I) methods allow the generation of artificial images that share the content of the original image but have a different style. With the advances in Generative Adversarial Networks (GANs)-based methods, I2I methods enabled the generation of artificial images that are indistinguishable from natural images. Recently, I2I methods were also employed in histopathology for generating artificial images of in silico stained tissues from a different type of staining. We refer to this process as stain transfer. The number of I2I variants is constantly increasing, which makes a well justified choice of the most suitable I2I methods for stain transfer challenging. In our work, we compare twelve stain transfer approaches, three of which are based on traditional and nine on GAN-based image processing methods. The analysis relies on complementary quantitative measures for the quality of image translation, the assessment of the suitability for deep learning-based tissue grading, and the visual evaluation by pathologists. Our study highlights the strengths and weaknesses of the stain transfer approaches, thereby allowing a rational choice of the underlying I2I algorithms. Code, data, and trained models for stain transfer between H&E and Masson’s Trichrome staining will be made available online.} }
Endnote
%0 Conference Paper %T A comparative evaluation of image-to-image translation methods for stain transfer in histopathology %A Igor Zingman %A Sergio Frayle %A Ivan Tankoyeu %A Sergey Sukhanov %A Fabian Heinemann %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-zingman24a %I PMLR %P 1509--1525 %U https://proceedings.mlr.press/v227/zingman24a.html %V 227 %X Image-to-image translation (I2I) methods allow the generation of artificial images that share the content of the original image but have a different style. With the advances in Generative Adversarial Networks (GANs)-based methods, I2I methods enabled the generation of artificial images that are indistinguishable from natural images. Recently, I2I methods were also employed in histopathology for generating artificial images of in silico stained tissues from a different type of staining. We refer to this process as stain transfer. The number of I2I variants is constantly increasing, which makes a well justified choice of the most suitable I2I methods for stain transfer challenging. In our work, we compare twelve stain transfer approaches, three of which are based on traditional and nine on GAN-based image processing methods. The analysis relies on complementary quantitative measures for the quality of image translation, the assessment of the suitability for deep learning-based tissue grading, and the visual evaluation by pathologists. Our study highlights the strengths and weaknesses of the stain transfer approaches, thereby allowing a rational choice of the underlying I2I algorithms. Code, data, and trained models for stain transfer between H&E and Masson’s Trichrome staining will be made available online.
APA
Zingman, I., Frayle, S., Tankoyeu, I., Sukhanov, S. & Heinemann, F.. (2024). A comparative evaluation of image-to-image translation methods for stain transfer in histopathology. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:1509-1525 Available from https://proceedings.mlr.press/v227/zingman24a.html.

Related Material