Mayo Clinic researchers in Phoenix used artificial intelligence to create an algorithm to better predict colorectal cancer recurrence, according to a multinational study published in Gastroenterology.
Five things to know:
1. Rish Pai, MD, PhD, Mayo Clinic pathologist and senior author of the study, developed QuantCRC, a deep-learning segmentation algorithm, to identify different regions within tumors using almost 6,500 digital slide images.
2. Investigators recorded 15 parameters from each colorectal cancer image and compared them to findings in the pathology report and health records. A prognostic model using QuantCRC was developed to predict recurrence-free survival.
3. Biospecimens of colorectal cancers from the Colon Cancer Family Registry locations in Australia, Canada and the U.S made up the internal training cohort. The results were validated with an external cohort of locations not participating in the Colon Cancer Family Registry in Canada and the U.S.
4. Dr. Pai said QuantCRC identifies regions within a tumor and derives data from those regions by converting an image into a set of numbers unique to that tumor.
"The large number of tumors that we analyzed allowed us to learn which features were most predictive of tumor behavior," Dr. Pai said. "We can now apply what we have learned to new colon cancers to predict how the tumor will behave."
5. Researchers said QuantCRC can be used to highlight a group of patients who may not need to undergo chemotherapy, given the low probability of recurrence, in addition to helping identify those at high risk of recurrence that may benefit from more intensive treatment.
Click here to read the full study.