FAU scientist receives $701,000 grant to revolutionize cancer treatment

While chemotherapy has advanced in personalization, personalized radiotherapy in cancer treatment remains underdeveloped. Current cancer treatments—including radiotherapy—are elaborate, lack personalization, and rely heavily on the expertise of medical teams. Medical image analysis and machine learning hold great promise for improving personalized oncology. However, challenges such as restricted high-quality data and data complexity remain.

Dr. Wazir Muhammad, principal investigator and assistant professor of physics in the Charles E. Schmidt College of Science at Florida Atlantic University, has been awarded a $701,000 grant from Precess Medical Derivatives, Inc., a medical physics and software application development firm, for a project that aims to revolutionize cancer treatment by making it more personalized and effective.

The project “Deciphering Digital Twins of Cancer Patients for Personalized Treatment” uses AI, specifically deep reinforcement learning (DRL), to analyze multimodal data and improve cancer characterization and treatment, ultimately improving patient outcomes.

Using personal health data, genetic information about the tumor, and patient treatment and follow-up data, digital twins will simulate diagnoses and treatment options to facilitate doctors choose the most effective treatments and monitor responses over time.

Wazir Muhammad, Ph.D., Principal Investigator and Assistant Professor, Department of Physics, Charles E. Schmidt College of Science at Florida Atlantic University

The project will facilitate address the challenges of data quality, complexity and integration with clinical workflows.

DRL is a powerful approach to using data-driven decision-making in healthcare, although its application requires careful consideration of ethical, safety, and interpretability issues specific to medical contexts. Although AI has shown promise in developing personalized cancer treatments, integration into routine clinical operate requires overcoming these significant technical and ethical hurdles.

“In oncology or medical applications, deep reinforcement learning can be used to optimize treatment strategies by learning from patient data and adjusting treatment plans based on observed outcomes,” Muhammad said. “It can also facilitate personalize treatment by taking into account individual patient characteristics and predicting the effectiveness of different interventions.”

The project will prototype a lively digital twin of cancer patients to better understand and treat cancer. The digital twin will operate observational data to represent the patient’s current state and predict future changes. It will combine simulation, model inference, data assimilation, and high-performance computing to bridge scales and processes.

“The goal of this model is to provide optimized treatment plans, aid in diagnosis and monitoring, and leverage patient data, including medical history, tumor histology, genomic and molecular profiling, prior treatment history, and radiosensitivity index, to improve treatment outcomes,” Muhammad said.

Creating a digital twin specific to a cancer patient requires a immense, coordinated effort among physicians, radiologists, medical physicists, modelers, clinicians, computational scientists, and software engineers. The three-year project will involve developing a process for anonymously collecting, categorizing, and analyzing multimodal patient data; building DRL models; and evaluating digital twins based on standard protocols.

Creating a digital twin in oncology will follow a structured five-step process including model design, personalization, testing, refinement and validation, and continuous improvement.

“Importantly, if the project proves successful, it could facilitate close the gap in access to healthcare across geographic and demographic groups,” Muhammad said.

The American Cancer Society estimates that there will be more than 2 million novel cancer cases in 2024. About 50% of all cancer patients in the U.S. receive radiation therapy as part of their treatment regimen.

“This critical grant to Dr. Muhammad represents a significant advancement in personalized radiation therapy and will serve to enable healthcare providers to tailor treatments to each patient’s unique tumor profile,” said Valery Forbes, Ph.D., dean of the FAU Charles E. Schmidt College of Science. “This novel approach promises to enhance treatment efficacy while minimizing side effects, ultimately improving outcomes and quality of life for people battling cancer.”