资源环境科技发展态势分析平台

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful(1). Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives(2). 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.

A video-based deep learning algorithm-EchoNet-Dynamic-accurately identifies subtle changes in ejection fraction and classifies heart failure with reduced ejection fraction using information from multiple cardiac cycles.

Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease(1), screening for cardiotoxicity(2) and decisions regarding the clinical management of patients with a critical illness(3). However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training(4,5). Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.

ABBV-744, a selective inhibitor of the BD2 domains of BET family proteins, is effective against prostate cancer in mouse xenograft models, with lower toxicities than the dual-bromodomain BET inhibitor ABBV-075.

Proteins of the bromodomain and extra-terminal (BET) domain family are epigenetic readers that bind acetylated histones through their bromodomains to regulate gene transcription. Dual-bromodomain BET inhibitors (DbBi) that bind with similar affinities to the first (BD1) and second (BD2) bromodomains of BRD2, BRD3, BRD4 and BRDt have displayed modest clinical activity in monotherapy cancer trials. A reduced number of thrombocytes in the blood (thrombocytopenia) as well as symptoms of gastrointestinal toxicity are dose-limiting adverse events for some types of DbBi(1-5). Given that similar haematological and gastrointestinal defects were observed after genetic silencing of Brd4 in mice(6), the platelet and gastrointestinal toxicities may represent on-target activities associated with BET inhibition. The two individual bromodomains in BET family proteins may have distinct functions(7-9) and different cellular phenotypes after pharmacological inhibition of one or both bromodomains have been reported(10,11), suggesting that selectively targeting one of the bromodomains may result in a different efficacy and tolerability profile compared with DbBi. Available compounds that are selective to individual domains lack sufficient potency and the pharmacokinetics properties that are required for in vivo efficacy and tolerability assessment(10-13). Here we carried out a medicinal chemistry campaign that led to the discovery of ABBV-744, a highly potent and selective inhibitor of the BD2 domain of BET family proteins with drug-like properties. In contrast to the broad range of cell growth inhibition induced by DbBi, the antiproliferative activity of ABBV-744 was largely, but not exclusively, restricted to cell lines of acute myeloid leukaemia and prostate cancer that expressed the full-length androgen receptor (AR). ABBV-744 retained robust activity in prostate cancer xenografts, and showed fewer platelet and gastrointestinal toxicities than the DbBi ABBV-075(14). Analyses of RNA expression and chromatin immunoprecipitation followed by sequencing revealed that ABBV-744 displaced BRD4 from AR-containing super-enhancers and inhibited AR-dependent transcription, with less impact on global transcription compared with ABBV-075. These results underscore the potential value of selectively targeting the BD2 domain of BET family proteins for cancer therapy.