Abstract
The aim was to determine whether an artificial intelligence (AI)-based, computer-aided detection (CAD) software can be used to reduce false positive per image (FPPI) on mammograms as compared to an FDA-approved conventional CAD. A retrospective study was performed on a set of 250 full-field digital mammograms between January 1, 2013, and March 31, 2013, and the number of marked regions of interest of two different systems was compared for sensitivity and specificity in cancer detection. The count of false-positive marks per image (FPPI) of the two systems was also evaluated as well as the number of cases that were completely mark-free. All results showed statistically significant reductions in false marks with the use of AI-CAD vs CAD (confidence interval = 95%) with no reduction in sensitivity. There is an overall 69% reduction in FPPI using the AI-based CAD as compared to CAD, consisting of 83% reduction in FPPI for calcifications and 56% reduction for masses. Almost half (48%) of cases showed no AI-CAD markings while only 17% show no conventional CAD marks. There was a significant reduction in FPPI with AI-CAD as compared to CAD for both masses and calcifications at all tissue densities. A 69% decrease in FPPI could result in a 17% decrease in radiologist reading time per case based on prior literature of CAD reading times. Additionally, decreasing false-positive recalls in screening mammography has many direct social and economic benefits.
Highlights
Any method to improve the performance of mammography interpretation could tremendously affect patient care, radiologist workflow, and system costs
Summary Statement The use of an artificial intelligence-based computer-aided detection software for mammography resulted in statistically significant improvement in specificity without reduction in sensitivity for breast cancer detection
Study Population A retrospective study was performed on a set of 250 two-dimensional (2D) full-field digital mammograms (FFDM) collected from a tertiary academic institution based in the USA which specializes in cancer healthcare
Summary
Any method to improve the performance of mammography interpretation could tremendously affect patient care, radiologist workflow, and system costs. J Digit Imaging (2019) 32:618–624 and mid-2000s showed variable ability of computer-aided detection (CAD) to improve diagnostic performance [1,2,3,4,5,6,7,8,9,10]. More recent studies show that CAD may not improve the diagnostic ability of mammography in any performance metric including sensitivity, specificity, positive predictive value, recall rate, or benign biopsy rate [11, 12]. Several recent studies have even shown an increase in callback rates and an increase in false-positive recalls from screening after implementation of CAD [11]. The largest disadvantage of using currently available CAD systems is the high rate of false-positive marks. High FPPI is a common complaint of radiologists when reviewing CAD marks
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have