An international team of researchers, including from Case Western Reserve University, has received a $3.3 million grant from the National Cancer Institute to apply the investigative and predictive capabilities of artificial intelligence in oral cancer treatment decisions.
The five-year grant supports the group’s work to use AI to help physicians customize treatments for patients with oral squamous cell carcinomas, which research shows is the eighth most common cancer type worldwide with numbers steadily increasing in the United States, India and other parts of Asia, according to a news release.
The team — made up of researchers from CWRU and partners in the United States and India — will be led by Anant Madabhushi, the Donnell Institute Professor of Biomedical Engineering at CWRU and head of the Center for Computational Imaging and Personalized Diagnostics (CCIPD), and James Lewis Jr., a professor of pathology, microbiology and immunology at Vanderbilt University Medical Center.
Madabhushi and his research team at the CCIPD (a global leader in AI-driven precision medicine research) hold more than 60 patents, many of which are tied to their work with various cancers, according to the release. The team also will study anticipated differences in the appearance of oral cancer among patients of different races, which is a fast-developing aspect of Madabhushi’s AI-based investigations.
Madabhushi and Lewis will work with a number of partners, including Cleveland Clinic, University Hospitals, the San Francisco VA Health System and Tata Memorial Centre in Mumbai, India.
Physicians currently place oral carcinoma patients into one of three categories: those requiring surgery, those requiring surgery and radiation, or those who will need surgery, followed by radiation and chemotherapy.
“That’s the gold standard right now: a system that puts patients in those very broad categories,” Madabhushi said in a provided statement. “For clinicians and pathologists, this is limiting because it relies on a limited number of parameters. But our machines are looking at the appearance of cells, their spatial architecture and interplay between different cell types, to parse out those patients who should actually be in another category.”
For instance, he said, their AI research has found a subset of early stage patients who are currently placed in the surgery alone category but are actually at a much higher risk and should be offered radiation therapy as well, but the current parameters don’t call for that.
Researchers will use advanced computer vision and machine learning techniques to identify cancer and immune cells on digitized images of oral squamous cell carcinoma tissue slides, provided by clinical partners. The images will be used to train the AI algorithms to predict outcomes and treatment benefit, according to the release.
Datasets from completed prospective, randomized, clinical trials of oral squamous cell carcinoma patients (at the Tata Memorial Center and from the cancer clinical cooperative group NRG Oncology) will allow for validation of the AI tools, according to the release.
According to the National Institute of Health (NIH), oral cancers, which include cancers of the mouth and the back of the throat, develop on the tongue, tissue lining the mouth and gums, under the tongue, at the base of the tongue and the area of the throat at the back of the mouth.
Oral carcinoma accounts for roughly 3% of all cancers diagnosed annually in the United States, according to the release, which notes that nearly 400,000 new cases are diagnosed annually worldwide.
Other members of the research team include: Drs. Shlomo Koyfman, David Adelstein, and Deborah Chute at the Taussig Cancer Center at Cleveland Clinic; Dr. Ted Teknos, president of Seidman Cancer Center at UH; Dr. Stephen Connelly of the San Francisco VA Health System; and Drs. Sarbani Ghosh-Laskar and Swapnil Rane of the Tata Memorial Centre.