A Swedish-developed AI system seems able to identify lymph node cancer in 90% of PET scan images, developers have reported.
Scientists at Chalmers University trained the AI system, known as Lars – Lymphoma Artificial Reader System – on ten years of archived images, made up of 17,000 images from more than 5,000 lymphoma patients.
Professor Ida Häggström worked with researchers at other centres, including Memorial Sloan Kettering Cancer Center in New York, Sahlgrenska Academy at the University of Gothenburg and Sahlgrenska University Hospital, Sweden.
The researchers have published their computer code but say that extensive clinical trials are now needed to validate the model. The model had to be trained to recognise treatment specific changes and identify whether these were cancer.
Professor Häggström said: “I have used what is known as supervised training, where images are shown to the computer model, which then assesses whether the patient has lymphoma or not. The model also gets to see the true diagnosis, so if the assessment is wrong, the computer model is adjusted so that it gradually gets better and better at determining the diagnosis.
“We haven’t programmed predetermined instructions in the model about what information in the image it should look at, but let it teach itself which image patterns are important in order to get the best predictions possible.
“In the study, we estimated the accuracy of the computer model to be about 90%, and especially in the case of images that are difficult to interpret, it could support radiologists in their assessments.”
Source:
Häggström I, Leithner D, Alvén J, Campanella G, Abusamra M, Zhang H, Chhabra S, Beer L, Haug A, Salles G, Raderer M, Staber PB, Becker A, Hricak H, Fuchs TJ, Schöder H, Mayerhoefer ME. (2023) “Deep learning for [¹⁸F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis.” Lancet Digital Health, doi: 10.1016/S2589-7500(23)00203-0
Link: https://www.thelancet.com/journals/landig/article/PIIS2589-7500(23)00203-0/fulltext
Disclaimer: The news stories shared on this site are used as a way to inform our members and followers of updates and relevant information happening in Haematology. The BSH does not endorse the content of news items from external sources, and is not in a position to verify the findings, accuracy or the source of any studies mentioned. Any medical or drugs information is provided as an information resource only, and is not to be relied on for any diagnostic or treatment purposes.
News service provided by Englemed News.