Apr 23 2021
A new study reports that a test that employs artificial intelligence (AI) to measure proteins found in certain patients suffering from advanced bowel cancer could enable more targeted treatment.
The main image is of a colorectal cancer. To the left of the black line is how the image would appear down a microscope. The image to the right of the line is how it would look once the artificial intelligence algorithm has been used to label the cancer cells with dots. The red dots highlight the cells which contain the EREG protein and the green dots are EREG negative. Image Credit: Copyright Roche Diagnostics.
A group of scientists from the University of Leeds joined hands with researchers at Roche Diagnostics to devise the new technique, which will enable patients and doctors to decide on the most ideal treatment options.
Samples from an earlier trial financially supported by Cancer Research UK were used by the researchers to analyze the levels of two proteins, called AREG and EREG, synthesized by certain colorectal cancers.
Algorithms powered by AI allowed the researchers to demonstrate that patients exhibiting higher levels of both these proteins obtained considerable benefit from a treatment that suppresses a different protein that is involved in cancer cell growth, called EGFR.
Of equal significance was evidence that patients presenting low levels of both the proteins did not benefit from the treatment.
At present, anti-EGFR treatments are administered only to patients with incurable, advanced bowel cancers. The researchers consider that in the future, their algorithm could be used to find patients in the earlier stages of the disease who could also benefit from the drugs.
As more treatment options become available for advanced colorectal cancer, it is becoming increasingly difficult for patients and their doctors to choose the treatment that’s right for them. This test will help patients navigate this decision-making process more easily.
Dr Christopher Williams, Study Lead Author, Division of Pathology and Data Analytics, University of Leeds
The recent publication of the results of the study in the Clinical Cancer Research journal is timely as it coincides with Bowel Cancer Awareness Month in the United Kingdom. The research was financially supported by Innovate UK and Roche Diagnostics, as well as by Yorkshire Cancer Research.
It was within the framework of a program in this field conducted by the National Pathology Imaging Co-operative.
As increasing numbers of complex tests are developed to target the right cancer treatments to the right patients, developing streamlined methods for delivering test results will be essential to improve cancer care. By using artificial intelligence to semi-automate the test process, we anticipate it may be easier for results to be delivered to patients faster to better influence treatment decisions.”
Kandavel Shanmugam, Study Senior Author and Senior Director of Medical Innovation, Roche Diagnostics
Roche is a global leader in diagnostics and pharmaceuticals, with a focus on promoting science to enhance people’s lives.
Journal Reference:
Williams, C. J. M., et al. (2021) Artificial intelligence-assisted amphiregulin and epiregulin immunohistochemistry predicts panitumumab benefit in RAS wild-type metastatic colorectal cancer. Clinical Cancer Research. doi.org/10.1158/1078-0432.CCR-21-0120.