No próximo dia 23 de Janeiro, pelas 11h00 na sala FC6 029 do DCC FCUP, Matthias Gobbert irá dar uma palestra intitulada "Machine Learning in Real-Time Imaging for Proton Beam Radiotherapy".
A palestra é organizada pelo DCC-FCUP.
Short Bio
Matthias K. Gobbert is Professor of Mathematics in the Department of Mathematics and Statistics at UMBC. He earned his Ph.D. in Mathematics from Arizona State University in 1996 and joined UMBC after one year as post-doc at the Institute for Mathematics and its Applications at the University of Minnesota. Dr. Gobbert's research interests include scientific and parallel computing, the numerical solution of partial differential equations, industrial mathematics, and most recently data science, typically in collaboration with application scientists. Dr. Gobbert has extensive experience in initiatives. He co-founded the Center for Interdisciplinary Research and Consulting, the UMBC High Performance Computing Facility, the REU Site: Interdisciplinary Program in High Performance Computing, the NSF initiative CyberTraining: Big Data + HPC + Atmospheric Physics at UMBC, and is now PI and co-director of the REU Site: Online Interdisciplinary Big Data Analytics in Science and Engineering. Dr. Gobbert also initiated both the departmental and the university partnerships with the University of Kassel in Kassel, Germany. Dr. Gobbert has been involved with over 200 publications, including over 40 in peer-reviewed journals, 40 in refereed proceedings, and 40 student publications and theses. For the work with a large number of students who were not his own thesis students, Dr. Gobbert received the University System of Maryland Board of Regents' Faculty Award for Excellence in Mentoring in 2010. Dr. Gobbert has to date graduated seven Ph.D. students, seven M.S. students, and has supervised twelve undergraduate theses for graduating with departmental honors. Dr. Gobbert has accumulated extensive experience in teaching with state-of-the-art technology. Dr. Gobbert uses a team-based active-learning teaching model, in which students work on problems in learning groups during class. Since starting online teaching full-time in 2020, the synchronous class meetings are used additionally for student presentations to maximize active student engagement..
Title
Machine Learning in Real-Time Imaging for Proton Beam Radiotherapy
Abstract
Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors, mitigating unnecessary radiation exposure to surrounding healthy tissues. Utilizing real-time imaging of prompt gamma rays can enhance the effectiveness of this therapy. Compton cameras are proposed for this purpose, capturing prompt gamma rays emitted by proton beams as they traverse a patient’s body. However, the Compton camera’s non-zero time resolution results in simultaneous recording of interactions, causing reconstructed images to be noisy and lacking the necessary level of detail to effectively assess proton delivery for the patient. In an effort to address the challenges posed by the Compton camera’s resolution and its impact on image quality, machine learning techniques, such as recurrent neural networks, are employed to classify and refine the generated data. These advanced algorithms can effectively distinguish various interaction types and enhance the captured information, leading to more precise evaluations of proton delivery during the patient’s treatment. The eventual goal is real-time image reconstruction of the proton beam during treatment. Towards this goal, the accuracy of the currently used neural networks has to be improved significantly more than current results. In addition to my students, this work is in collaboration with researchers in the Department of Radiation Oncology at the University of Maryland School of Medicine and at the company M3D, Inc.