The University of Texas MD Anderson Cancer Center, the Oden Institute for Computational Engineering and Sciences and the Texas Advanced Computing Center (TACC) at The University of Texas announced funding today for six cancer research projects as part of the Joint Center for Computational Oncology.
Launched in 2020, the collaborative effort aims to accelerate breakthroughs addressing unmet needs for cancer patients by combining MD Anderson's leadership in oncology and data science, the Oden Institute's expertise in computational science and TACC's high-performance computing strength.
This is the fifth round of funding since the program began and provides $50,000 to each new project, split between MD Anderson and UT Austin researchers. The projects also can utilize TACC's high performance computing platforms and are eligible for supplemental funding of post-doctoral fellows as funding allows.
Tom Yankeelov, Ph.D., director of the Center for Computational Oncology at the Oden Institute, and John D. Hazle, Ph.D., chair of Imaging Physics at MD Anderson, co-lead the effort.
"We had an excellent set of applications this year, and I am delighted to report that we were able to fund six projects, more than we have supported in previous years," Yankeelov said. "These projects represent innovative applications of mathematical and computational modeling to attack problems in cancers of the liver, rectum, breast and brain. We also have a project, led by two rising investigators, focused on overcoming the practical issues of integrating digital twin frameworks into the clinical workflow. It will be very exciting to see how these projects develop over the next year."
The 2024 research projects include:
· Integrating machine learning-based histopathology with biology-based models of high-grade glioma growth and response to radiotherapy
Led by David Hormuth, Ph.D., research scientist at the Center for Computational Oncology at the Oden Institute, and David Fuentes, Ph.D., associate professor of Imaging Physics at MD Anderson, this project seeks to combine novel machine learning techniques with existing mathematical modeling to predict tumor growth and treatment response for high-grade gliomas.
· Computational and preclinical modeling to predict liver growth in patients with liver malignancy undergoing portal vein blockade
Led by Edward Castillo, Ph.D., affiliated faculty at the Oden Institute and associate professor of biomedical engineering, Steven Huang, M.D., professor of Interventional Radiology at MD Anderson, and Marites Melancon, Ph.D., professor of Interventional Radiology at MD Anderson, this team hopes to develop an automated and robust computational model that uses liver perfusion images to assess liver hypertrophy following portal vein embolization.
· Fast comprehensive 3D imaging of rectal cancer
Jon Tamir, Ph.D., affiliated faculty at the Oden Institute and assistant professor of Electrical & Computer Engineering, Gaiane Rauch, M.D., Ph.D., professor of Diagnostic Radiology at MD Anderson, and Ken-Pin Hwang, Ph.D., associate professor of Imaging Physics at MD Anderson, are working to develop a machine learning-based 3D magnetic resonance imaging (MRI) rectal cancer imaging technique. Their eventual goal is to reduce scan time and alleviate the workload on radiologists.
· Predicting local rectal tumor relapse in patients receiving non-operative management
Jack Virostko, Ph.D., affiliated faculty at the Oden Institute and associate professor of Diagnostic Medicine at Dell Medical School, and Venkateswar Surabhi, M.B.B.S., professor of Diagnostic Radiology at MD Anderson, are tackling the problem of differentiating active rectal tumors in patients receiving non-operative management. Their plans include longitudinal surveillance MRI and developing biology-based mathematical models to predict rectal tumor recurrence.
· Foundational advancement toward practical integration of digital twins into a clinical workflow
Michael Kapteyn, Ph.D., research associate at the Oden Institute, and Chengyue Wu, Ph.D., assistant professor of Imaging Physics at MD Anderson, hope to integrate digital twin technology into oncology by developing a prototype cancer patient digital twins (CPDTs) deployment platform designed for integration into clinical workflow.
· Advancing high-grade glioma diagnosis and treatment: explainable MRI and genomic correlations of invasive non-enhancing tumors
James Carson, Ph.D., Life Sciences Computing Directorate at TACC, and Christopher Chad Quarles, Ph.D., professor of Cancer Systems Imaging at MD Anderson, aim to develop computational models to identify novel MRI-based biomarkers. Their goal is to enhance diagnostic precision and to ultimately improve future target therapies.
"This collaboration with UT Austin faculty underscores the importance of multidisciplinary approaches to overcome the toughest challenges in cancer research," Hazle said. "We hope these new projects will build on the successes of previous years and lead to impactful externally funded awards."
