Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy

TL;DR

This paper systematically reviews deep learning-based interactive segmentation methods in medical imaging, providing a taxonomy, analyzing current practices, and highlighting the need for standardized benchmarks to advance the field.

Contribution

It offers a comprehensive taxonomy and systematic review of 121 methods, identifying gaps such as the lack of standardized comparisons in medical image segmentation.

Findings

Severe lack of standardized benchmarks across methods

Deep learning has significantly advanced interactive segmentation

Opportunities exist for improved evaluation protocols

Abstract

Interactive segmentation is a crucial research area in medical image analysis aiming to boost the efficiency of costly annotations by incorporating human feedback. This feedback takes the form of clicks, scribbles, or masks and allows for iterative refinement of the model output so as to efficiently guide the system towards the desired behavior. In recent years, deep learning-based approaches have propelled results to a new level causing a rapid growth in the field with 121 methods proposed in the medical imaging domain alone. In this review, we provide a structured overview of this emerging field featuring a comprehensive taxonomy, a systematic review of existing methods, and an in-depth analysis of current practices. Based on these contributions, we discuss the challenges and opportunities in the field. For instance, we find that there is a severe lack of comparison across methods which needs to be tackled by standardized baselines and benchmarks.