Unsupervised many-to-many stain translation for histological image augmentation to improve classification accuracy

URN to cite this document:: urn:nbn:de:bvb:355-epub-537371
DOI to cite this document:: 10.5283/epub.53737

Berijanian, Maryam ; Schaadt, Nadine S. ; Huang, Boqiang ; Lotz, Johannes ; Feuerhake, Friedrich ; Merhof, Dorit

License: Creative Commons Attribution Non-commercial No Derivatives 4.0
PDF - Published Version
(2MB)

Date of publication of this fulltext: 13 Feb 2023 17:22

Alternative links to fulltext:DOI Publisher

Details

Preview

Export bibliographical data

Abstract

Abstract

Background
Deep learning tasks, which require large numbers of images, are widely applied in digital pathology. This poses challenges especially for supervised tasks since manual image annotation is an expensive and laborious process. This situation deteriorates even more in the case of a large variability of images. Coping with this problem requires methods such as image augmentation and synthetic image generation. In this regard, unsupervised stain translation via GANs has gained much attention recently, but a separate network must be trained for each pair of source and target domains. This work enables unsupervised many-to-many translation of histopathological stains with a single network while seeking to maintain the shape and structure of the tissues.
Methods
StarGAN-v2 is adapted for unsupervised many-to-many stain translation of histopathology images of breast tissues. An edge detector is incorporated to motivate the network to maintain the shape and structure of the tissues and to have an edge-preserving translation. Additionally, a subjective test is conducted on medical and technical experts in the field of digital pathology to evaluate the quality of generated images and to verify that they are indistinguishable from real images. As a proof of concept, breast cancer classifiers are trained with and without the generated images to quantify the effect of image augmentation using the synthetized images on classification accuracy.
Results
The results show that adding an edge detector helps to improve the quality of translated images and to preserve the general structure of tissues. Quality control and subjective tests on our medical and technical experts show that the real and artificial images cannot be distinguished, thereby confirming that the synthetic images are technically plausible. Moreover, this research shows that, by augmenting the training dataset with the outputs of the proposed stain translation method, the accuracy of breast cancer classifier with ResNet-50 and VGG-16 improves by 8.0% and 9.3%, respectively.
Conclusions
This research indicates that a translation from an arbitrary source stain to other stains can be performed effectively within the proposed framework. The generated images are realistic and could be employed to train deep neural networks to improve their performance and cope with the problem of insufficient numbers of annotated images.

Owner only: item control page

Download Statistics

Altmetric

Alternative Statistics (altmetrics)

More literature (via CORE)

Details

Preview

Export bibliographical data

Abstract

Abstract

Download Statistics

Downloads

Alternative Statistics (altmetrics)

More literature (via CORE)

University Library