Metasurface Biosensors Enabling Single-Molecule Sensing of Cell-Free DNA.

In this study, we have revealed that highly fluorescence (FL)-enhancing all-dielectric metasurface biosensors are capable of detecting single-target DNA, which is cell-free DNA (cfDNA) specific to the human practice effect. The ultimately high-precision detection was achieved in a scheme combining the metasurface biosensors with a short-time nucleic acid amplification technique, that is, a reduced-cycle polymerase chain reaction (PCR). In this combined scheme, we obtained a series of FL signals at a single-molecule concentration, reflecting the Poisson distribution, and moreover elucidated that the FL signals exhibit the single-molecule cfDNA detection with more than 84% statistical confidence in an automated FL detection system and with 99.

Detection of aspiration from images of a videofluoroscopic swallowing study adopting deep learning.

Objectives: A videofluoroscopic swallowing study (VFSS) is conducted to detect aspiration. However, aspiration occurs within a short time and is difficult to detect. If deep learning can detect aspirations with high accuracy, clinicians can focus on the diagnosis of the detected aspirations.

The well-developed actin cytoskeleton and Cthrc1 expression by actin-binding protein drebrin in myofibroblasts promote cardiac and hepatic fibrosis.

Fibrosis is mainly triggered by inflammation in various tissues, such as heart and liver tissues, and eventually leads to their subsequent dysfunction. Fibrosis is characterized by the excessive accumulation of extracellular matrix proteins (e.g.

Self-Supervised Adversarial Learning with a Limited Dataset for Electronic Cleansing in Computed Tomographic Colonography: A Preliminary Feasibility Study.

Existing electronic cleansing (EC) methods for computed tomographic colonography (CTC) are generally based on image segmentation, which limits their accuracy to that of the underlying voxels. Because of the limitations of the available CTC datasets for training, traditional deep learning is of limited use in EC. The purpose of this study was to evaluate the technical feasibility of using a novel self-supervised adversarial learning scheme to perform EC with a limited training dataset with subvoxel accuracy.