Topic: Artificial Intelligence Advances Breast Cancer Detection
With artificial intelligence technology, medical professionals can quickly and accurately sort through breast MRIs in patients with dense breast tissue to eliminate those without cancer.
Mammography has assisted in reducing breast cancer-related deaths by providing early detection when cancer is still treatable. However, it is less sensitive in women with extremely dense breast tissue than fatty breast tissue.
Additionally, women with extremely dense breasts are three to six times more likely to develop breast cancer than women with almost entirely fatty breasts and two times more likely than the average woman.
Supplemental screening in women with dense breast tissue increased the sensitivity of cancer detection. Research from the Denise Tissue and Early Breast Neoplasm Screening (DENSE) Trial supported the use of supplemental screening with MRI.
“The DENSE trial showed that additional MRI screening for women with extremely dense breasts was beneficial,” study lead author Erik Verburg, MSc, said in a press release. “On the other hand, the DENSE trial confirmed that the vast majority of screened women do not have any suspicious findings on MRI.”
While most MRIs show the normal anatomical and physiological variation that may not require radiological review, researchers created an artificial intelligence method to reduce the radiologist’s workload.
Verburg and his colleagues set out to determine the feasibility of an automated triaging method based on deep learning. The team used breast MRI data from the DENSE trial to develop and train the deep learning algorithm to distinguish between breasts with and without lesions. The model was trained with data from seven hospitals and tested on data from eight hospitals.
“More than 4,500 MRI datasets of extremely dense breasts were included. Of the 9,162 breasts, 838 had at least one lesion, of which 77 were malignant, and 8,324 had no lesions,” the press release stated.
The deep learning model considered 90.7 percent of the MRIs with lesions to be non-normal and triaged them to radiological review. The model dismissed about 40 percent of lesion-free MRIs without missing any cancers.
Topic Discussed: Artificial Intelligence Advances Breast Cancer Detection