Search

This review provides an overview of current applications of deep learning methods within breast radiology. The diagnostic capabilities of deep learning in breast radiology continue to improve, giving rise to the prospect that these methods may be integrated not only into detection and classification of breast lesions, but also into areas such as risk estimation and prediction of tumor responses to therapy. Remaining challenges include limited availability of high-quality data with expert annotations and ground truth determinations, the need for further validation of initial results, and unresolved medicolegal considerations. KEY POINTS: • Deep learning (DL) continues to push the boundaries of what can be accomplished by artificial intelligence (AI) in breast imaging with distinct advantages over conventional computer-aided detection. • DL-based AI has the potential to augment the capabilities of breast radiologists by improving diagnostic accuracy, increasing efficiency, and supporting clinical decision-making through prediction of prognosis and therapeutic response. • Remaining challenges to DL implementation include a paucity of prospective data on DL utilization and yet unresolved medicolegal questions regarding increasing AI utilization.

The purpose of this study was to determine whether splenohepatopexy (SHP) or omental transposition (OP) could reverse the portal hypertension (PH) induced by portal vein ligation (PVL). Fifty-eight Wistar rats divided into four groups: in group A (22 rats) PH was produced by calibrated PVL. In group B (8 rats), SHP was performed. Group C animals (13 rats) underwent SHP and PVL. In group D (15 rats) both PVL and OP were done. In all of the rats, the portal pressures (PP) were measured before and after the production of PVL. For SHP, small areas on the spleen and liver capsula were stripped off, and these two areas were placed together. In group D, an omentum patch was tied on the prepared liver surface. Twelve weeks after surgery, the PP were measured again and portal angiography was done. The liver, omentum and spleen were histopathologically examined. In all of the groups, the PP after PVL were significantly higher than before PVL. Twelve weeks after surgery, the PP of SHP and OP groups were significantly lower than those with PVL alone. Angiographic study showed many collaterals between transposed tissue and liver. Histopathologically, the collaterals of animals with SHP or OP were found to be well developed to allow sufficient flow for PP reduction. Both SHP and OP may reverse the increased PP in PVL model of PH. In the future; these methods may be alternative techniques for PP reduction in human beings as well.