A Review of Deep Learning-Based Medical Image Segmentation

Abstract

Medical image segmentation, the process of precisely delineating regions of interest (e.g. organs, lesions, cells) within medical images, is a pivotal technique in medical image analysis. It finds widespread application in computer-aided diagnosis, surgical planning, radiation therapy, and pathological analysis, thus playing a crucial role in enabling precision medicine and enhancing the quality of clinical care. Traditional medical image segmentation methods often rely on hand-crafted features and rule-based approaches, which struggle to handle the inherent complexity and variability of medical imagery, leading to limitations in segmentation accuracy and robustness. Recently, deep learning methodologies, driven by their powerful capabilities in automatic feature learning and non-linear modelling, have overcome the limitations of traditional methods and achieved significant advancements in the field of medical image segmentation. This review provides a comprehensive overview and summary of recent progress in deep learning-based medical image segmentation, with a particular focus on fully supervised learning paradigms leveraging convolutional neural networks, transformers, and the segment anything model. We delve into the underlying principles, network architectures, advantages, and limitations of these approaches. Furthermore, we systematically compare their performance across diverse imaging modalities, anatomical structures, and pathological targets. We also present a curated compilation of commonly used datasets, evaluation metrics, and loss functions relevant to medical image segmentation. Finally, we discuss future research directions and potential challenges, offering insights into the evolving landscape of this critical field.