Deep neural network models for computational histopathology: A survey

TL;DR

This survey reviews over 130 deep learning methods applied to histopathology images, highlighting progress, challenges, datasets, and future directions in computational cancer pathology.

Contribution

It provides a comprehensive overview of deep learning techniques in histopathology, including methodological strategies, survival models, datasets, and identifies key challenges and future research avenues.

Findings

Deep learning has become the dominant approach in histopathology analysis.

Various machine learning strategies like supervised, weakly supervised, and transfer learning are used.

The survey highlights existing datasets and critical challenges in the field.

Abstract

Histopathological images contain rich phenotypic information that can be used to monitor underlying mechanisms contributing to diseases progression and patient survival outcomes. Recently, deep learning has become the mainstream methodological choice for analyzing and interpreting cancer histology images. In this paper, we present a comprehensive review of state-of-the-art deep learning approaches that have been used in the context of histopathological image analysis. From the survey of over 130 papers, we review the fields progress based on the methodological aspect of different machine learning strategies such as supervised, weakly supervised, unsupervised, transfer learning and various other sub-variants of these methods. We also provide an overview of deep learning based survival models that are applicable for disease-specific prognosis tasks. Finally, we summarize several existing open datasets and highlight critical challenges and limitations with current deep learning approaches, along with possible avenues for future research.