A total of 60 mammographic studies were retrospectively collected from Site 1 (EUC Mamocentrum Brno).

The acquisition of mammography studies from Site 1 was enabled by the contract for the transfer of mammography images for medical research purposes, signed on 14 January 2022.

A total of 28 mammographic studies were retrospectively collected from Site 2 (Hospital Šumperk, a.s.).

The acquisition of mammography studies from Institution 2 was enabled by the contract for the transfer of mammography images for medical research purposes, signed on 31 January 2023.

A total of 34 mammographic studies were retrospectively collected from Site 3 (Masaryk Memorial Cancer Institute).

The acquisition of mammography studies from Institution 3 was enabled by the amendment to the contract for the transfer of X-ray images for medical research purposes, signed on 21 February 2023, which follows the contract for the transfer of X-ray images for medical research purposes, signed on 3 January 2022.

Carebot AI MMG is a software solution that utilizes artificial intelligence methods, specifically deep learning and computer vision algorithms, to evaluate and localize suspicious regions of potential lesions during the interpretation of digital breast x-rays as part of standard mammography screening procedures. The Carebot AI MMG medical device is not intended for use in diagnostic mammography. The Carebot AI MMG is intended for use in women over the age of 18.

The predictive outputs of the Carebot AI MMG medical device are intended to aid decision-making in screening clinical practice, always in conjunction with other relevant patient information and based on the professional judgment of the examining clinician. The Carebot AI MMG is specifically designed to provide a supporting layer of analysis that helps in evaluating or prioritizing mammography images with additional patient information and the professional judgment of the examining physician.

A multicenter, multi-reader, retrospective study was designed to validate the clinical efficacy of the proposed Carebot AI MMG (also referred to as "DLAD"). Using a non-certified medical device, a test set of retrospectively collected mammography studies in standard projections (CC and MLO). The performance of the DLAD was evaluated against the ground truth for individual indications (breast density evaluation, breast lesion detection) using Accuracy.

Carebot AI MMG v2.2 classified mammography studies according to the ACR BI-RADS 5th edition, i.e. breast tissue density assessment into A/B/C/D classes. The performance of the Carebot AI MMG device was assessed relative to the ground truth and then compared with the performance of five independent radiologists with varying levels of experience (RAD 1-RAD 5). A rigorous statistical analysis was used in the BI-RADS breast density classification to evaluate the performance of each method - the proposed Carebot AI MMG v2.2 medical device and the compared radiologists in the multi-reader study. The analysis focused on key metrics including Accuracy, F1 Score (Macro-Averaged), Precision (Macro-Averaged), Recall (Macro-Averaged) and Cohen's Kappa (κ) to assess the strength of agreement. Given that all scans were evaluated by all radiologists in the comparison, a bootstrapping method that involves resampling the test data 1000 times.