Deep learning for digital pathology: A critical overview of methodological framework

Meghdad Sabouri Rad, Junze (Vincent) Huang, Mohammad Mehdi Hosseini, Rakesh Choudhary, Harmen Siezen, Ratilal Akabari, Tamara Jamaspishvili, Ola El-Zammar, Palak G Patel, Saverio J. Carello, Michel R. Nasr, Bardia Rodd,
Deep learning for digital pathology: A critical overview of methodological framework,
Journal of Pathology Informatics,
Volume 19,
2025,
100514,
ISSN 2153-3539,
https://doi.org/10.1016/j.jpi.2025.100514.
(https://www.sciencedirect.com/science/article/pii/S2153353925001002)
Abstract: Deep learning frameworks have transformed the field of digital pathology by automating complex tasks and revealing intricate patterns within histopathological data. These advanced methodologies provide exceptional accuracy and scalability, facilitating the analysis of high-dimensional whole-slide images with unparalleled precision. In this article, we present a comprehensive deep learning framework highlighting recent advancements in computational pathology. We critically examine mathematical innovations and offer a comparative analysis of various models demonstrating the significant and ongoing improvements in the field.
Keywords: Deep neural networks; Deep learning framework; Digital pathology; Machine learning framework