AI-Based Approach Reduces False Positives in Mammography

A team of researchers from the University of Pittsburgh (Pittsburgh, PA, USA) have developed an artificial intelligence (AI) approach based on deep learning convolutional neural network (CNN) that could identify nuanced mammographic imaging features specific for recalled but benign (false-positive) mammograms and distinguish such mammograms from those identified as malignant or negative.

The researchers conducted a study to find out whether deep learning could be applied to analyze a large set of mammograms in order to distinguish images from women with a malignant diagnosis, images from women who were recalled and were later determined to have benign lesions (false recalls), and images from women determined to be breast cancer-free at the time of screening.

The researchers used a total of 14,860 images of 3,715 patients from two independent mammography datasets, Full-Field Digital Mammography Dataset (FFDM - 1,303 patients) and Digital Dataset of Screening Mammography (DDSM - 2,412 patients). They built CNN models and used enhanced model training approaches to investigate six classification scenarios that would help distinguish images of benign, malignant, and recalled-benign mammograms. Upon combining the datasets from FFDM and DDSM, the area under the curve (AUC) to distinguish benign, malignant, and recalled-benign images ranged from 0.76 to 0.91. The higher the AUC, the better the performance, with a maximum of 1, according to Shandong Wu, PhD, assistant professor of radiology, biomedical informatics, bioengineering, intelligent systems, and clinical and translational science, and director of the Intelligent Computing for Clinical Imaging lab in the Department of Radiology at the University of Pittsburgh, Pennsylvania.

"We showed that there are imaging features unique to recalled-benign images that deep learning can identify and potentially help radiologists in making better decisions on whether a patient should be recalled or is more likely a false recall," said Wu. "Based on the consistent ability of our algorithm to discriminate all categories of mammography images, our findings indicate that there are indeed some distinguishing features/characteristics unique to images that are unnecessarily recalled. Our AI models can augment radiologists in reading these images and ultimately benefit patients by helping reduce unnecessary recalls."

Related Links:
University of Pittsburgh