Medical image segmentation is a fundamental task in the field of medical imaging, enabling the accurate identification and delineation of structures such as organs, tissues, and lesions within medical images. These segmented regions are essential for diagnostic purposes, treatment planning, and disease monitoring. Over the years, medical image segmentation has evolved significantly, driven by advances in imaging technologies and computational techniques. Traditional methods, such as thresholding, region-growing, and active contours, have been supplemented and, in some cases, replaced by more sophisticated machine learning (ML) and deep learning (DL) approaches. Convolutional neural networks (CNNs) and their variants, including U-Net and Transformer-based models, have shown remarkable success in automating and improving segmentation tasks. This survey paper provides a comprehensive review of the various segmentation techniques, categorizing them into classical and deep learning-based methods. It discusses the strengths, limitations, and challenges of each approach, including issues related to data quality, class imbalance, and the generalizability of models. Furthermore, the paper highlights recent advancements in the field, emerging trends, and future directions for further enhancing segmentation accuracy, robustness, and efficiency in clinical applications. This work aims to serve as a valuable resource for researchers and clinicians looking to understand the current state of medical image segmentation and its potential future developments.
Qi et al. (2025) studied this question.