Invited Talk by Prof. Moti Freiman, Technion on Wednesday March 27th 2024: Physically-primed Neural Networks in Quantitative Medical Image Analysis

Symbolic picture for the article. The link opens the image in a large view.

It’s a great pleasure to welcome Moti Freiman in our lab for an exciting presentation bringing together machine learning and physics for medical image analysis.

Title: Physically-primed Neural Networks in Quantitative Medical Image Analysis
Date: March 27th 2024, 9:30
Room: 02.133-113, Martensstr. 3 Erlangen

Abstract: The advent of Deep Neural Networks (DNNs) has marked considerable breakthroughs in Magnetic Resonance Imaging (MRI) analysis. These state-of-the-art methodologies are increasingly deployed to resolve intricate predicaments in quantitative MRI such as Diffusion-Weighted MRI, and quantitative cardiac T1 and T2 distribution mapping, delivering superior speed and precision over conventional techniques. Nonetheless, existing challenges such as mitigation of motion artifacts and enhancement of resilience against extremely low signal-to-noise ratios still remain, restricting their clinical utility.

To overcome these limitations, we introduce an innovative strategy integrating a physically-primed DNN architecture. This unique architecture embeds the signal decay model directly within the neural network, augmenting the network’s generalization capability and fostering the development of stable algorithms, which, in turn, produce refined predictions.

Our advanced methodology reveals extensive potential applications including early assessment of response to neoadjuvant chemotherapy in breast cancer patients, establishing motion-robust quantitative cardiac T1 mapping, and T2 distribution mapping for evaluating inflammation in animal models. The proposed approach opens new vistas for more nuanced and clinically viable solutions in the realm of quantitative MRI analysis, paving the way for enhanced diagnostic precision and patient outcomes.

Short Bio: Moti Freiman is an assistant professor of biomedical engineering at the Technion–Israel Institute of Technology. He is the director of the Technion’s computational MRI lab and the academic director of the Technion’s human MRI research center. Previously he was a staff research scientist at Philips Healthcare, an Instructor of Radiology at Harvard Medical School, and a post-doctoral fellow at the Computational Radiology lab at Boston Children’s Hospital. Dr. Freiman holds a PhD in Computer Science from the Hebrew University of Jerusalem. His main research interests include deep-learning-based methods for quantitative MRI analysis and reconstruction, Inflammatory bowel disease, and fetal imaging.