Ultrasound Image
Ultrasound image analysis focuses on extracting meaningful information from ultrasound scans for medical diagnosis and treatment. Current research emphasizes developing robust deep learning models, including convolutional neural networks (CNNs), transformers, and generative adversarial networks (GANs), often combined in hybrid architectures, to improve image segmentation, classification, and noise reduction. These advancements aim to enhance diagnostic accuracy, particularly in areas with limited expert access, and facilitate automated tasks like lesion detection and report generation, ultimately improving patient care and workflow efficiency. The field is also actively exploring explainable AI (XAI) techniques to increase the transparency and trustworthiness of these powerful algorithms.
Papers
S-CycleGAN: Semantic Segmentation Enhanced CT-Ultrasound Image-to-Image Translation for Robotic Ultrasonography
Yuhan Song, Nak Young Chong
UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation
Zehui Lin, Zhuoneng Zhang, Xindi Hu, Zhifan Gao, Xin Yang, Yue Sun, Dong Ni, Tao Tan