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
Unsupervised Deformable Image Registration for Respiratory Motion Compensation in Ultrasound Images
FNU Abhimanyu, Andrew L. Orekhov, John Galeotti, Howie Choset
Unsupervised Deformable Ultrasound Image Registration and Its Application for Vessel Segmentation
FNU Abhimanyu, Andrew L. Orekhov, Ananya Bal, John Galeotti, Howie Choset
Deep Ultrasound Denoising Using Diffusion Probabilistic Models
Hojat Asgariandehkordi, Sobhan Goudarzi, Adrian Basarab, Hassan Rivaz
Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Images
Jian Wang, Liang Qiao, Shichong Zhou, Jin Zhou, Jun Wang, Juncheng Li, Shihui Ying, Cai Chang, Jun Shi
Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
AnLan Sun, Zhao Zhang, Meng Lei, Yuting Dai, Dong Wang, Liwei Wang