Ahmad awarded $2.3M R01 grant

The National Institute of Biomedical Imaging and Bioengineering (NIBIB), National Institutes of Health (NIH) has awarded a four-year, $2.3 million R01 grant to assistant professor Rizwan Ahmad and team in developing and validating a comprehensive, robust deep learning framework that improves MRI reconstruction beyond the limits of existing technology. The project title is “A comprehensive deep learning framework for MRI reconstruction,” and begins July 1, 2021 – March 31, 2025.

Principal investigators: Assistant Professor Rizwan Ahmad (Biomedical Engineering) and Professor Philip Schniter (Electrical and Computer Engineering).

Co-investigators: Associate Professor Karolina Zareba (Cardiovascular Medicine), Professor Orlando Simonetti (Radiology and Cardiovascular Medicine), Research Associate Professor Guy Brock (Biomedical Informatics), Mai-Lan Ho, MD (Nationwide Children’s Hospital), and Assistant Professor Florian Knoll (Radiology, New York University).

Brief description: The primary goal of this investigation is to develop and validate a comprehensive, robust deep learning (DL) framework that improves MRI reconstruction beyond the limits of existing technology. The proposed framework uses “plug-and-play” algorithms to combine physics-driven MR acquisition models with state-of-the-art learned image models, which are instantiated by image denoising subroutines. To fully exploit the rich structure of MR images, we propose to use DL-based denoisers that are trained in an application-specific manner. The proposed framework, termed PnP-DL, offers advantages over other existing DL methods, as well as compressed sensing (CS). Compared to existing DL methods for MRI reconstruction, PnP-DL is more immune to inevitable variations in the forward model, such as changes in the coil sensitivities or undersampling pattern, allowing it to generalize across applications and acquisition settings. Compared to CS, PnP-DL recovers images faster, with higher quality, and with potentially superior diagnostic value. Successful completion of this project will demonstrate that PnP-DL outperforms state-of-the-art methods in terms of image quality while exhibiting a level of robustness and broad applicability that has eluded other DL-based MRI reconstruction methods. The acceleration and image quality improvement afforded by these developments will benefit almost all MRI applications, including pediatric imaging, where reducing sedation is a pressing need, and high-dimensional imaging applications (e.g., whole-heart 4D flow imaging), which are too slow for routine clinical use.

Congratulations Dr. Ahmad and team!