Scientists Develop Artificial Intelligence for Mesothelioma Assessment
Research & Clinical Trials
Written by Tim Povtak | Edited By Walter Pacheco
Scientists in Scotland have developed a prototype imaging system using artificial intelligence that has proven effective with malignant mesothelioma, potentially revolutionizing the way patients will be treated in the future.
The pilot program could spark much-needed advances in diagnostics and therapeutics.
“Mesothelioma is such a complex, incredibly difficult disease,” Dr. Kevin Blythe, professor of respiratory medicine at University of Glasgow and respiratory physician at Queen Elizabeth University Hospital, told The Mesothelioma Center at Asbestos.com. “This could be a very important step toward helping patients in the future.”
The University of Glasgow and Canon Medical Research Europe worked together in developing the novel technology built around artificial intelligence, or AI. The computer software can detect and measure cancer cells more effectively than traditional imaging.
It could be used to more accurately – and quickly – assess a mesothelioma patient’s immediate response to drug treatments such as chemotherapy and immunotherapy.
AI Could Provide More Personalized Treatment
The project, which was launched in 2018, was focused intentionally on mesothelioma, a rare but aggressive malignancy, and one of the most difficult-to-measure with traditional CT scans.
Scotland, with a long history of shipbuilding and the use of asbestos in construction, has one of the world’s highest incidence rates of mesothelioma.
The findings are expected to provide a good foundation to produce similar tools for use in assessing more common cancers. Mesothelioma is typically more difficult to read than other tumors because of its more complex growth pattern.
“Measuring response with mesothelioma has always been incredibly difficult,” Blythe said. “In itself, artificial intelligence can’t change treatment, but it will help make better decisions with drug therapies.”
The system also will be used eventually to speed up the diagnostic process for mesothelioma, which could make a dramatic difference in future survival times. In the majority of cases today, mesothelioma is not diagnosed until the later stages, when treatment options are much more limited and mostly palliative.
Eliminating Human Error in Mesothelioma Assessment
The artificial intelligence cancer assessment tool has the potential to streamline clinical trials, making them less time-consuming, more accurate and less expensive, issues that often are cited as obstacles to new drug development for mesothelioma.
According to a recent press release from the University of Glasgow, the artificial intelligence was programed by inputting more than 100 mesothelioma CT scans. It responded by finding and measuring new tumors with acute accuracy, and without human input.
The program also would eliminate any human error. It should be better than humans in recognizing subtle changes that are invisible to the human eye.
Researchers believe the artificial intelligence tool will be available soon to help medical professionals everywhere find and measure mesothelioma with improved precision, which should lead to better, more personalized treatment.
“Accurate tumor volume measurements are much too time-consuming to perform by hand. Automating these measurements will open the way for clinical trials of new treatments by detecting even small changes in the tumor size,” said Dr. Keith Goatman, principal scientist at Canon Medical Research Europe. “Ultimately it could be used routinely in hospitals to decide the best treatment for each individual.”
Clinical findings from this project are expected to be published soon in one of the scientific journals, leading to the program dissemination. The project is part of Scotland’s Cancer Innovation Challenge.
“The speed and accuracy of the AI algorithm could have a wide-reaching impact on mesothelioma treatment,” Goatman said “This work is a strong first step towards real change in the treatment of all cancers – and not just mesothelioma.”
