WEDNESDAY, July 3, 2024 (HealthDay News) -- Artificial intelligence (AI)-assisted definition of prostate cancer contours reduces underestimation of the extent of prostate cancer, according to a study published in the July issue of The Journal of Urology.
Sakina Mohammed Mota, Ph.D., from Avenda Health, and colleagues compared physicians' performance using AI versus standard-of-care methods for tumor delineation in a multireader, multicase study. Cases were interpreted by seven urologists and three radiologists from five institutions with two to 23 years of experience. Fifty prostatectomy cases eligible for focal therapy were retrospectively assessed by each reader. Readers defined cancer contours cognitively, delineating tumor boundaries manually to encapsulate all clinically significant disease. After four or more weeks, the same cases were contoured using AI software.
The researchers found that the balanced accuracy (mean of voxel-wise sensitivity and specificity) of AI-assisted cancer contours was superior to cognitively defined and hemigland contours (84.7 percent versus 67.2 and 75.9 percent, respectively). Cancer extent was systemically underestimated by cognitively defined cancer contours, with a negative margin rate of 1.6 percent compared with 72.8 percent for AI-assisted cancer contours.
"Overall, the use of AI in cancer treatment could lead to more effective and personalized care for patients, with treatments that are better tailored to their individual needs and more successful in fighting the disease,” coauthor Wayne G. Brisbane, M.D., from the David Geffen School of Medicine in Los Angeles, said in a statement.
Several authors disclosed ties to Avenda Health.
Abstract/Full Text
