Search for: All records

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainty. 

Hypoxic reprogramming of vasculature relies on genetic, epigenetic, and metabolic circuitry, but the control points are unknown. In pulmonary arterial hypertension (PAH), a disease driven by hypoxia inducible factor (HIF)–dependent vascular dysfunction, HIF-2α promoted expression of neighboring genes, long noncoding RNA (lncRNA) histone lysineN-methyltransferase 2E-antisense 1 (KMT2E-AS1) and histone lysine N-methyltransferase 2E (KMT2E).KMT2E-AS1stabilized KMT2E protein to increase epigenetic histone 3 lysine 4 trimethylation (H3K4me3), driving HIF-2α–dependent metabolic and pathogenic endothelial activity. This lncRNA axis also increased HIF-2α expression across epigenetic, transcriptional, and posttranscriptional contexts, thus promoting a positive feedback loop to further augment HIF-2α activity. We identified a genetic association between rs73184087, a single-nucleotide variant (SNV) within aKMT2Eintron, and disease risk in PAH discovery and replication patient cohorts and in a global meta-analysis. This SNV displayed allele (G)–specific association with HIF-2α, engaged in long-range chromatin interactions, and induced the lncRNA-KMT2E tandem in hypoxic (G/G) cells. In vivo,KMT2E-AS1deficiency protected against PAH in mice, as did pharmacologic inhibition of histone methylation in rats. Conversely, forced lncRNA expression promoted more severe PH. Thus, theKMT2E-AS1/KMT2E pair orchestrates across convergent multi-ome landscapes to mediate HIF-2α pathobiology and represents a key clinical target in pulmonary hypertension.