Evaluation of the Diagnostic Accuracy of Comercially Available AI-CAD Solution in Mammography Screening in Mexican Women (Mammo-MX Database)

<b>Background/Objectives</b>: The objective of this study was to evaluate the performance of Breast-SlimView^®, a deep convolutional neural network for the automatic classification of BI-RADS and breast density in MLO (mediolateral oblique) and CC (craniocaudal) views. <b>Methods</b>: A total of 9560 mammographic images from 2390 Mexican women (age: 54.14 ± 8.72 years) were labeled according to ACR (American College of Radiology) density (A-D) and BI-RADS 1, 2, and 3 (low risk), and BI-RADS 4 and 5 (high risk). All mammograms in the test dataset were blinded and read by two radiologists, and the consensus was taken as the reference standard. The accuracy, sensitivity, and specificity of the automated AI-based classification system was evaluated against the consensus reached by expert radiologists. <b>Results</b>: The classification of MLO and CC projections had a mean sensitivity of 0.81 (95% CI: 0.797-0.829), a specificity of 0.70 (95% CI: 0.686-0.722), and an accuracy of 0.71 (95% CI: 0.698-0.734) in differentiating between low and high risk. Good agreement was observed with ACR breast density classifications A, B, C, and D. Agreement between AI and human readers was "substantial" (Pearson's chi-square, <i>p</i> = 0.001). <b>Conclusions</b>: AI enables accurate, standardized, observer independent classification.