AI may be able to spare breast cancer patients from unnecessary radiation
A new AI algorithm developed by researchers at Case Western Reserve University can predict which malignant breast cancers will progress and benefit from additional treatment, according to a new study published in Breast Cancer Research.
A majority of women with ductal carcinoma in situ (DCIS), referred to as stage 0, have surgery to remove any remaining affected tissue; many of these patients receive radiation therapy that likely isn’t necessary due to their lower risk for progression.
“In short, we’re probably overtreating patients,” Anant Madabhushi, professor of biomedical engineering at Case Western’s School of Engineering, said in a statement. “That goes against prevailing wisdom, but that’s what our analysis is finding.”
DCIS is a common cancer with about 60,000 cases diagnosed in the U.S. each year. Researchers from the Cleveland-based institution used their tool to analyze the texture and orientation of lumpectomy samples taken from 62 DCIS patients.
They found those tumors typically characterized as indeterminate were more similar to low-risk for recurrence cancers as classified by the genetic test Oncotype DX.
And upon validating low-risk from high-risk features, the researchers were able to predict the likelihood of progression from DCIS to invasive ductal carcinoma in an independent group of 30 women.
“This could be a tool for determining who really needs the radiation, or who needs the gene test, which is also very expensive,” Madabhushi concluded.
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.