Micro Ultrasound
Micro-ultrasound, a high-resolution ultrasound technique, is revolutionizing prostate cancer detection by providing significantly improved image detail compared to traditional methods. Current research focuses on developing robust deep learning models, including transformer-based UNets and ensemble methods, to accurately segment the prostate and detect cancerous tissue, addressing challenges like data variability across clinical centers and limitations in labeled data through techniques like self-supervised learning and co-teaching. These advancements aim to improve the accuracy and reliability of prostate cancer diagnosis, potentially leading to earlier detection and more effective treatment planning. The development of accurate image registration techniques between micro-ultrasound and histopathology images further enhances diagnostic capabilities.
Papers
MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images
Hongxu Jiang, Muhammad Imran, Preethika Muralidharan, Anjali Patel, Jake Pensa, Muxuan Liang, Tarik Benidir, Joseph R. Grajo, Jason P. Joseph, Russell Terry, John Michael DiBianco, Li-Ming Su, Yuyin Zhou, Wayne G. Brisbane, Wei Shao
Image Registration of In Vivo Micro-Ultrasound and Ex Vivo Pseudo-Whole Mount Histopathology Images of the Prostate: A Proof-of-Concept Study
Muhammad Imran, Brianna Nguyen, Jake Pensa, Sara M. Falzarano, Anthony E. Sisk, Muxuan Liang, John Michael DiBianco, Li-Ming Su, Yuyin Zhou, Wayne G. Brisbane, Wei Shao