Breast Ultrasound
Breast ultrasound is a crucial diagnostic tool for detecting and characterizing breast lesions, with research focusing on improving the accuracy and efficiency of image analysis. Current efforts utilize deep learning models, including U-Net variations, transformers (like ViT), and novel architectures like Mamba-based networks, often incorporating techniques like contrastive learning and knowledge distillation to enhance performance with limited labeled data. These advancements aim to improve the speed and accuracy of breast cancer diagnosis, potentially assisting radiologists and leading to earlier and more effective interventions.
Papers
Morphology-Enhanced CAM-Guided SAM for weakly supervised Breast Lesion Segmentation
Xin Yue, Xiaoling Liu, Qing Zhao, Jianqiang Li, Changwei Song, Suqin Liu, Zhikai Yang, Guanghui Fu
LightBTSeg: A lightweight breast tumor segmentation model using ultrasound images via dual-path joint knowledge distillation
Hongjiang Guo, Shengwen Wang, Hao Dang, Kangle Xiao, Yaru Yang, Wenpei Liu, Tongtong Liu, Yiying Wan