Medical Image Segmentation
Medical image segmentation aims to automatically delineate specific anatomical structures or regions of interest within medical images, facilitating accurate diagnosis and treatment planning. Current research heavily focuses on improving segmentation accuracy and efficiency using advanced architectures like U-Net and its variants, Vision Transformers, and Large Language Models, often incorporating techniques such as multi-scale feature extraction, attention mechanisms, and test-time training. These advancements are crucial for improving diagnostic capabilities, accelerating clinical workflows, and enabling more precise and personalized medicine. Furthermore, research is actively addressing challenges like limited annotated data through semi-supervised learning and the use of foundation models for improved generalization across different imaging modalities and clinical settings.
Papers
Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
Xiangyi Yan, Junayed Naushad, Chenyu You, Hao Tang, Shanlin Sun, Kun Han, Haoyu Ma, James Duncan, Xiaohui Xie
Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
Chenyu You, Weicheng Dai, Yifei Min, Lawrence Staib, James S. Duncan
FMG-Net and W-Net: Multigrid Inspired Deep Learning Architectures For Medical Imaging Segmentation
Adrian Celaya, Beatrice Riviere, David Fuentes
Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation
Zheyuan Zhang, Bin Wang, Lanhong Yao, Ugur Demir, Debesh Jha, Ismail Baris Turkbey, Boqing Gong, Ulas Bagci