Accuracy of breast density assessment using artificial intelligence by convolutional neural network for carriers of UGT1A1 polymorphisms with Gilbert's Syndrome - a pilot study.

In contrast, specificity was high, reaching 95.8% (95% CI 78.9%‒99.9%) in the total sample, and 100.0% in both the Gilbert and control groups, a suggestive trend that the CNN may be effective in correctly classifying non-dense breasts, though the preliminary nature of these results still necessitates further validation with larger cohorts.

also in 203 other papers