Impact of Deep Learning denoising and ultra-high density coil array on prostate diffusion imaging

作者：Sherry Huang, Xinzeng Wang, Milica Medved, Clyve Follante, Yun-Jeong Stickle, Patricia Lan, Ambereen Yousuf, Roger Engelmann, Fraser Robb, Arnaud Guidon, Grace Lee, Aytekin Oto · 发表于：Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 年份：2025 · DOI：10.58530/2025/0101 · 研究领域：Advanced Neuroimaging Techniques and Applications、Advanced MRI Techniques and Applications、MRI in cancer diagnosis

Motivation: Multiparametric-MRI (mpMRI) of the prostate is integral in the detection, staging, treatment planning, and targeting for prostate cancer. Particularly diffusion weight imaging (DWI) provides a strong correlation with cancer grade. However, DWI, particularly at high b-value suffers from low SNR. Goal(s): To improve image quality of DWI, particularly at high-b-value, for prostate MRI-guided clinical care. Approach: This study employs a novel body-conforming high-density 50-Channel pelvic coil with additional perineal coverage and Deep Learning (DL) based reconstruction for denoising diffusion images. Results: High density pelvic coil and DL-based reconstruction improves the image quality demonstrated in reader score and statistical measurements. Impact: This study shows a clinically feasible approach by combining a novel 50-channel pelvic coil with perineal coverage with DL based reconstruction for an improved DWI imaging in prostate MR.