Virtual histopathology methods in medical imaging - a systematic review

Abstract

Virtual histopathology is an emerging technology in medical imaging that utilizes advanced computational methods to analyze tissue images for more precise disease diagnosis. Traditionally, histopathology relies on manual techniques and expertise, often resulting in time-consuming processes and variability in diagnoses. Virtual histopathology offers a more consistent, and automated approach, employing techniques like machine learning, deep learning, and image processing to simulate staining and enhance tissue analysis. This review explores the strengths, limitations, and clinical applications of these methods, highlighting recent advancements in virtual histopathological approaches. In addition, important areas are identified for future research to improve diagnostic accuracy and efficiency in clinical settings.

Keywords: Computational pathology; Dual contrastive learning; Image-to-image translation; Medical image processing; Virtual histopathology.

Fig. 1

Articles selection through various stages of review

Fig. 2

Graphical workflow of literature analysis

Fig. 3

Typical steps for machine learning in digital pathological image analysis. After preprocessing, various ML approaches can be applied

Fig. 4

Various magnification levels show different structures even for the same histopathological image; taken from [6]

Fig. 5

Schematic of the standard histological staining and deep learning-based virtual staining

Fig. 6

Overview of steps involved in visual path approach for virtual histopathology

Fig. 7

Overview of technical approach for virtual histopathology

Fig. 8

Overview of image-to-image approaches for virtual histopathology