International evaluation of an AI system for breast cancer screening.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Mouse Lung Fibroblast Resistance to Fas-Mediated Apoptosis Is Dependent on the Baculoviral Inhibitor of Apoptosis Protein 4 and the Cellular FLICE-Inhibitory Protein.

A characteristic feature of idiopathic pulmonary fibrosis (IPF) is accumulation of apoptotic resistant fibroblasts/myofibroblasts in the fibroblastic foci. As caveolin (Cav)-null mice develop pulmonary fibrosis (PF), we hypothesized that the participating fibroblasts display an apoptosis-resistant phenotype. To test this hypothesis and identify the molecular mechanisms involved we isolated lung fibroblasts from Cav-null mice and examined the expression of several inhibitors of apoptosis (IAPs), of c-FLIP, of Bcl-2 proteins and of the death receptor CD95/Fas. We found significant increase in XIAP and c-FLIP constitutive protein expression with no alteration of Bcl-2 and lower levels of CD95/Fas. The isolated fibroblasts were then treated with the CD95/Fas ligand (FasL) to induce apoptosis. While the morphological and biochemical alterations induced by FasL were similar in wild-type (wt) and Cav-null mouse lung fibroblasts, the time course and the extent of the alterations were greater in the Cav-null fibroblasts. Several salient features of Cav-null fibroblasts response such as loss of membrane potential, fragmentation of the mitochondrial continuum concurrent with caspase-8 activation, and subsequent Bid cleavage, prior to caspase-3 activation were detected. Furthermore, M30 antigen formation, phosphatidylserine expression and DNA fragmentation were caspase-3 dependent. SiRNA-mediated silencing of XIAP and c-FLIP, individually or combined, enhanced the sensitivity of lung fibroblasts to FasL-induced apoptosis. Pharmacological inhibition of Bcl-2 had no effect. Together our findings support a mechanism in which CD95/Fas engagement activates caspase-8, inducing mitochondrial apoptosis through Bid cleavage. XIAP and c-FLIP fine tune this process in a cell-type specific manner.