Grant Allows for AI Research to Improve Rectal Cancer Treatment Response

With the support of a three-year, $755,000 grant from the US Department of Defense’s Congressionally Directed Medical Research Programs, Case Western Reserve University researchers are testing the use of artificial intelligence in medical imaging to improve the treatment response for rectal cancer patients.

The research team wants to create guidance for patients who require surgery as part of their treatment. Colorectal cancer is the third most diagnosed cancer in the United States. According to the American Cancer Society, there will be more than 45,000 new cases of rectal cancer in 2021.

However, Case Western Reserve researchers claim that clinicians do not have a reliable method to predict which rectal cancer patients will respond positively to treatments, including chemotherapy and radiation. Therefore, most patients must undergo invasive surgery to remove the rectum and surrounding tissue.

“In too many cases, patients are being overtreated,” said lead researcher and member of the Center for Computational Imaging and Personalized Diagnostics (CCIPD), Satish Viswanath, said in a press release.

“Instead, if our AI technology is successful, we could tell the clinician right up front — based on a routine MRI (magnetic resonance imaging) scan — if a patient will do well with only chemoradiation and then can be observed, without having this serious surgery.”

In a collaborative effort with physicians from Cleveland Clinic, University Hospitals, and the Louis Stokes Cleveland VA Medical Center, the Case Western Reserve team will implement AI methods to thousands of digital images from the medical institutions.

According to previous research, up to 30 percent of individuals diagnosed with rectal cancer have unnecessary surgery. The surgery is often financially costly and impacts the patient’s quality of life afterward.

After surgery, patients may require a colostomy, which can cause changes in various areas, including sexual function and mental health, even if temporary.

The team will conduct the research on imaging data from more than 2,000 rectal cancer patients who have been treated at the hospitals over the last five years and test the AI on about 450 to 500 patients.

Throughout their research, the team will work to design and validate new types of radiomic tools to study how rectal tumors are related to chemoradiation response.

Radiomic refers to the growing number of AI-driven strategies to extract many features from medical images using data-characterization algorithms. The features can then assist in uncovering tumors and other characteristics typically not visible to the naked eye.

The research team has already made significant strides in using predictive analytic tools to determine treatment responses.

The lab, established in 2012, specializes in the detection, diagnosis, and characterization of cancers and other diseases by utilizing medical imaging, machine learning, and AI.

“With this award, his team will be able to validate these tools in a multi-institutional setting with CWRUs various affiliate medical partners, setting the stage for prospective clinical trials,” CCIPD Director Anant Madabhushi said.