A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation

2025-02-09

AI Summary

Medical image segmentation is severely hindered by low lesion contrast, ill-defined boundaries, and high morphological variability. To address these challenges, this work systematically reviews the evolution of U-Net and its variants for medical image segmentation, and— for the first time— elucidates the synergistic mechanisms among four key architectural innovations: skip connections, residual connections, 3D extensions, and Transformer integration. We propose a modality-aware data classification framework and a structural evolution modeling approach, establishing a comprehensive model performance–applicability mapping across major benchmarks including BraTS, ISIC, and LiTS. Furthermore, we introduce a mechanism-driven model attribution analysis paradigm, enabling data-modality-specific model adaptation strategies and interpretable optimization pathways. This study provides both theoretical foundations and practical guidelines for designing robust, adaptable medical image segmentation models.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multimodal Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Medical images often exhibit low and blurred contrast between lesions and surrounding tissues, with considerable variation in lesion edges and shapes even within the same disease, leading to significant challenges in segmentation. Therefore, precise segmentation of lesions has become an essential prerequisite for patient condition assessment and formulation of treatment plans. Significant achievements have been made in research related to the U-Net model in recent years. It improves segmentation performance and is extensively applied in the semantic segmentation of medical images to offer technical support for consistent quantitative lesion analysis methods. First, this paper classifies medical image datasets on the basis of their imaging modalities and then examines U-Net and its various improvement models from the perspective of structural modifications. The research objectives, innovative designs, and limitations of each approach are discussed in detail. Second, we summarize the four central improvement mechanisms of the U-Net and U-Net variant algorithms: the jump-connection mechanism, residual-connection mechanism, 3D-UNet, and transformer mechanism. Finally, we examine the relationships among the four core enhancement mechanisms and commonly utilized medical datasets and propose potential avenues and strategies for future advancements. This paper provides a systematic summary and reference for researchers in related fields, and we look forward to designing more efficient and stable medical image segmentation network models based on the U-Net network.

Problem

• Improves medical image segmentation accuracy
• Analyzes U-Net structural modifications
• Proposes future U-Net enhancement strategies

Innovation

• U-Net and its variants
• Jump-connection mechanism
• Residual-connection mechanism