What is it about?
This article presents a survey of how a branch of mathematics called Topology can be used to extract meaningful features from medical images. Topology in broad terms, studies the structure of shapes. The survey studies 30 articles applying this approach to tasks like tumour classification and cell segmentation, and assess how well these methods perform.
Featured Image
Photo by Logan Voss on Unsplash
Why is it important?
This article achieves a few things. First, it shows that there is a growing body of evidence that topology can help image analysis pipelines to identify medical and biological structures in a more human-like way. Second, the basics of topological methods for image analysis are introduced in simple terms, such that expertise in mathematical or computational fields is not required to understand. Third, it helps to draw the attention of researchers to topology-aided image analysis to further expand this field and identifies where the gaps of the current research are found, such that researchers are encouraged to focus their efforts towards these gaps.
Perspectives
Our hope for writing this article was primarily to help guide the medical imaging community to look at the field of topological methods for image analysis, and to guide the people who would be interested in lending their time and effort to expanding this field towards the gaps that are currently open. We hope this article helps to bring attention to a somewhat overlooked area of research.
Daniel Brito-Pacheco
City St. George's, University of London
Read the Original
This page is a summary of: Persistent Homology in Medical Image Processing: A Literature Review, ACM Transactions on Computing for Healthcare, June 2026, ACM (Association for Computing Machinery),
DOI: 10.1145/3820762.
You can read the full text:
Contributors
The following have contributed to this page
