Beyond the silence: A comprehensive exploration of long non-coding RNAs as genetic whispers and their essential regulatory functions in cardiovascular disorders.

Long non-coding RNAs (lncRNAs) are RNA molecules that regulate gene expression at several levels, including transcriptional, post-transcriptional, and translational. They have a length of more than 200 nucleotides and cannot code. Many human diseases have been linked to aberrant lncRNA expression, highlighting the need for a better knowledge of disease etiology to drive improvements in diagnostic, prognostic, and therapeutic methods. Cardiovascular diseases (CVDs) are one of the leading causes of death worldwide. LncRNAs play an essential role in the complex process of heart formation, and their abnormalities have been associated with several CVDs. This Review article looks at the roles and relationships of long non-coding RNAs (lncRNAs) in a wide range of CVDs, such as heart failure, myocardial infarction, atherosclerosis, and cardiac hypertrophy. In addition, the review delves into the possible uses of lncRNAs in diagnostics, prognosis, and clinical treatments of cardiovascular diseases. Additionally, it considers the field's future prospects while examining how lncRNAs might be altered and its clinical applications.

Dual-consistency semi-supervision combined with self-supervision for vessel segmentation in retinal OCTA images.

Optical coherence tomography angiography(OCTA) is an advanced noninvasive vascular imaging technique that has important implications in many vision-related diseases. The automatic segmentation of retinal vessels in OCTA is understudied, and the existing segmentation methods require large-scale pixel-level annotated images. However, manually annotating labels is time-consuming and labor-intensive. Therefore, we propose a dual-consistency semi-supervised segmentation network incorporating multi-scale self-supervised puzzle subtasks(DCSS-Net) to tackle the challenge of limited annotations. First, we adopt a novel self-supervised task in assisting semi-supervised networks in training to learn better feature representations. Second, we propose a dual-consistency regularization strategy that imposed data-based and feature-based perturbation to effectively utilize a large number of unlabeled data, alleviate the overfitting of the model, and generate more accurate segmentation predictions. Experimental results on two OCTA retina datasets validate the effectiveness of our DCSS-Net. With very little labeled data, the performance of our method is comparable with fully supervised methods trained on the entire labeled dataset.