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

## TL;DR

This study evaluated an AI tool for classifying breast cancer risk in mammograms of Mexican women and found it to be reasonably accurate and consistent with expert radiologists.

## Contribution

The study provides a performance evaluation of an AI-CAD system in a Mexican population using the Mammo-MX database.

## Key findings

- The AI system achieved a mean sensitivity of 0.81 in differentiating low and high risk mammograms.
- The AI showed substantial agreement with human radiologists in breast density classifications.
- The system demonstrated 0.71 accuracy in classifying mammograms as low or high risk.

## Abstract

Background/Objectives: 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. Methods: 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. Results: 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, p = 0.001). Conclusions: AI enables accurate, standardized, observer independent classification.