Generally, colorectal cancer is likely to return in a significant number of patients within three to five years of treatment. In light of this, a Mayo Clinic research team is using artificial intelligence (AI) for generating an algorithm to get ahead on detecting colorectal cancer resurgence.
The developed algorithm is called QuantCRC, and it’s able to pinpoint different regions in the cancer tumors through using close to 6,500 digital slide snapshots.
“QuantCRC can identify different regions within the tumor and extract quantitative data from these regions,” says study senior author Dr. Rish Pai, a pathologist at Mayo Clinic in Arizona, and developer of the algorithm. “The algorithm converts an image into a set of numbers that is unique to that tumor. The large number of tumors that we analyzed allowed us to learn which features were most predictive of tumor behavior. We can now apply what we have learned to new colon cancers to predict how the tumor will behave.”
The investigators utilized the technology in a multinational study by examining different colorectal cancer biospecimens from the Colon Cancer Family Registry. Participating locations include those in the U.S., Canada, and Australia. They then validated their results with an outside cohort of locations not participating in part of the registry in Canada and the U.S.
Fifteen parameters were examined and noted from every image captured, and then they were compared to patient findings in their health records and pathology reports. From this, QuantCRC was able to be used to predict survival odds in recurrence-free cases.
Not only can this technology serve as a valuable tool for measuring recurrence-free survival, but it’s even able to identify patients who do need chemotherapy or to be put on more aggressive intervention and monitoring measures. “For patients with colon cancer, the algorithm gives oncologists another tool to help guide therapy and follow-up,” says Dr. Pai.
The international team of researchers unanimously agreed that their QuantCRC is a vital asset to improving colon cancer outcomes. Further, it can help some patients in remission with low chance of recurrence have more peace of mind by providing an informed, evidence-backed message that their illness is likely to not return.
In the future, Dr. Pai hopes to take this research to new heights. He plans to use the technology to take his understanding of cancer recurrence mechanisms and apply it to treatment. He also aims to be able to predict the response to common treatments other than chemotherapy, like immunotherapy and radiation.
This study is published in the journal Gastroenterology.