Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential

TL;DR

This review discusses how multiple instance learning enhances digital pathology by enabling deep neural networks to learn from weakly labeled whole slide images, highlighting recent advances, challenges, and future prospects.

Contribution

It provides a comprehensive overview of deep multiple instance learning methods in digital pathology, emphasizing recent developments and critical challenges.

Findings

Multiple instance learning effectively handles weakly labeled data in digital pathology.

Recent advances have improved the performance of deep MIL methods.

Challenges include data variability and annotation scarcity.

Abstract

Digital whole slides images contain an enormous amount of information providing a strong motivation for the development of automated image analysis tools. Particularly deep neural networks show high potential with respect to various tasks in the field of digital pathology. However, a limitation is given by the fact that typical deep learning algorithms require (manual) annotations in addition to the large amounts of image data, to enable effective training. Multiple instance learning exhibits a powerful tool for learning deep neural networks in a scenario without fully annotated data. These methods are particularly effective in this domain, due to the fact that labels for a complete whole slide image are often captured routinely, whereas labels for patches, regions or pixels are not. This potential already resulted in a considerable number of publications, with the majority published in the last three years. Besides the availability of data and a high motivation from the medical perspective, the availability of powerful graphics processing units exhibits an accelerator in this field. In this paper, we provide an overview of widely and effectively used concepts of used deep multiple instance learning approaches, recent advances and also critically discuss remaining challenges and future potential.