Mayo Clinic study shows AI may improve prediction of colorectal cancer recurrence
In a multinational study led by a Mayo Clinic research team using artificial intelligence (AI), investigators developed an algorithm to improve the prediction of colorectal cancer recurrence. Study results are published in Gastroenterology.
Excluding skin cancers, colorectal cancer is the third most common cancer diagnosed in the U.S., according to the American Cancer Society.
Rish Pai, M.D., Ph.D., a pathologist at Mayo Clinic in Arizona and senior author, developed QuantCRC, a deep-learning segmentation algorithm, to identify different regions within tumors using nearly 6,500 digital slide images.
Fifteen parameters were recorded from each image of colorectal cancer and compared to the findings in the pathology report and health records. Then a prognostic model using QuantCRC was developed to predict recurrence-free survival.
The investigators used biospecimens of colorectal cancers from the Colon Cancer Family Registry participating locations in Australia, Canada and the U.S., including Mayo Clinic, to make up the internal training cohort. They validated the results with an external cohort of locations not participating in the Colon Cancer Family Registry in Canada and the U.S.
The algorithm can identify a subset of patients who may not need to receive chemotherapy, given the low probability of recurrence. It also can help identify those patients at high risk of recurrence that may benefit from more intensive treatment or follow-up.
