Advancements in medical image segmentation: A review of transformer models

Abstract

Medical image segmentation is crucial for precise diagnosis, treatment planning, and disease monitoring in healthcare. Traditional methods often struggle with the complexity and variability inherent in medical images. However, recent advancements in deep learning, particularly Transformer models, have revolutionized the field. This comprehensive review explores the transformative impact of Transformer models on medical image segmentation. Beginning with an overview of the limitations of traditional approaches, the review introduces foundational Transformer architectures such as the Vision Transformer, Swin Transformer, and Pyramid Vision Transformer. Systematically categorizing Transformer-based segmentation techniques, it delves into their applications across diverse medical imaging tasks, including brain tumor segmentation, polyp detection, cardiac segmentation, and more. Additionally, the review examines the challenges and considerations in benchmarking Transformer models using evaluation metrics and benchmark datasets. By analyzing current research trends and insights, this review provides valuable guidance for researchers and practitioners seeking to harness the power of Transformer models in medical image segmentation.