Stain-Independent Deep Learning-Based Analysis of Digital Kidney Histopathology.

Bouteldja N, Hölscher DL, Klinkhammer BM, Buelow RD, Lotz J, Weiss N, Daniel C, Amann KU, Boor P (2023)

Publication Type: Journal article

Publication year: 2023

Journal

American Journal of Pathology American Society for Investigative Pathology (ASIP)

Book Volume: 193

Pages Range: 73-83

Journal Issue: 1

DOI: 10.1016/j.ajpath.2022.09.011

Abstract

Convolutional neural network (CNN)-based image analysis applications in digital pathology (eg, tissue segmentation) require a large amount of annotated data and are mostly trained and applicable on a single stain. Here, a novel concept based on stain augmentation is proposed to develop stain-independent CNNs requiring only one annotated stain. In this benchmark study on stain independence in digital pathology, this approach is comprehensively compared with state-of-the-art techniques including image registration and stain translation, and several modifications thereof. A previously developed CNN for segmentation of periodic acid-Schiff-stained kidney histology was used and applied to various immunohistochemical stainings. Stain augmentation showed very high performance in all evaluated stains and outperformed all other techniques in all structures and stains. Without the need for additional annotations, it enabled segmentation on immunohistochemical stainings with performance nearly comparable to that of the annotated periodic acid-Schiff stain and could further uphold performance on several held-out stains not seen during training. Herein, examples of how this framework can be applied for compartment-specific quantification of immunohistochemical stains for inflammation and fibrosis in animal models and patient biopsy specimens are presented. The results show that stain augmentation is a highly effective approach to enable stain-independent applications of deep-learning segmentation algorithms. This opens new possibilities for broad implementation in digital pathology.

Authors with CRIS profile

Christoph Daniel Department of Nephropathology Kerstin Ute Amann Professur für Nephropathologie

Involved external institutions

Fraunhofer-Institut für Bildgestützte Medizin (MEVIS) DE Germany (DE) Universitätsklinikum Aachen (UKA) DE Germany (DE)

How to cite

APA:

Bouteldja, N., Hölscher, D.L., Klinkhammer, B.M., Buelow, R.D., Lotz, J., Weiss, N.,... Boor, P. (2023). Stain-Independent Deep Learning-Based Analysis of Digital Kidney Histopathology. American Journal of Pathology, 193(1), 73-83. https://doi.org/10.1016/j.ajpath.2022.09.011

MLA:

Bouteldja, Nassim, et al. "Stain-Independent Deep Learning-Based Analysis of Digital Kidney Histopathology." American Journal of Pathology 193.1 (2023): 73-83.

BibTeX: Download