Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches

TL;DR

This survey reviews the development, taxonomy, and performance of generalist models in medical image segmentation, comparing them with task-specific approaches and discussing future research directions and challenges.

Contribution

It provides a comprehensive taxonomy, performance analysis, and comparison of generalist models in medical image segmentation, highlighting challenges and future perspectives.

Findings

Generalist models show competitive performance with task-specific models.

Zero-shot and few-shot capabilities are emerging in medical segmentation.

Challenges include regulatory compliance, privacy, and trustworthy AI.

Abstract

Following the successful paradigm shift of large language models, leveraging pre-training on a massive corpus of data and fine-tuning on different downstream tasks, generalist models have made their foray into computer vision. The introduction of Segment Anything Model (SAM) set a milestone on segmentation of natural images, inspiring the design of a multitude of architectures for medical image segmentation. In this survey we offer a comprehensive and in-depth investigation on generalist models for medical image segmentation. We start with an introduction on the fundamentals concepts underpinning their development. Then, we provide a taxonomy on the different declinations of SAM in terms of zero-shot, few-shot, fine-tuning, adapters, on the recent SAM 2, on other innovative models trained on images alone, and others trained on both text and images. We thoroughly analyze their performances at the level of both primary research and best-in-literature, followed by a rigorous comparison with the state-of-the-art task-specific models. We emphasize the need to address challenges in terms of compliance with regulatory frameworks, privacy and security laws, budget, and trustworthy artificial intelligence (AI). Finally, we share our perspective on future directions concerning synthetic data, early fusion, lessons learnt from generalist models in natural language processing, agentic AI and physical AI, and clinical translation.