A new breast-image analysis technique may help reduce unnecessary breast biopsies, costs and patient anxiety, a new study suggests.
The technique, called three-compartment breast (3CB) imaging, uses noncontrast dual-energy mammography to determine the biological tissue composition (water, lipid, and protein) of a suspicious breast mass, researchers explain in Radiology, online December 11.
Nurse giving mammogram. Source: Getty
For the study, Dr. Karen Drukker of the University of Chicago and colleagues studied 109 women with suspicious breast masses on dual-energy mammography. Biopsy results showed 35 masses to be invasive cancers and 74 to be benign.
3CB images were derived from the mammograms and analyzed along with mammography radiomics, a method that uses artificial intelligence algorithms to analyze features and patterns in images.
Combing 3CB image analysis and mammography radiomics improved the ability to predict cancer in breast masses deemed suspicious by the radiologist.
The combined method improved the positive predictive value (PPV) from 32% for visual interpretation alone to 49%, with 36% fewer total biopsies. The 3CB-radiomics method missed one of the 35 cancers, for a 97% sensitivity rate.
"These results are very promising. The callback rate with mammography is much higher than ideal. Combining 3CB image analysis with mammography radiomics, the reduction in recalls was substantial," Dr. Drukker said in a news release.
"Because 3CB imaging can be performed with conventional mammography or breast tomosynthesis equipment with minimal changes in workflow and minor modifications, and with only a 10% higher dose, the potential exists for wide application of 3CB imaging in diagnostic breast imaging and perhaps also in screening," the team writes.
"Our study showed that more investigation into the application of 3CB imaging is warranted, and we have initiated a research study incorporating 3CB imaging into breast tomosynthesis," they conclude.
The study had no commercial funding and the authors have indicated no relevant disclosures.