Publications by authors named "Yankai Chen"

Article Synopsis
  • Coronary artery disease (CAD) is a major global health issue, and combining coronary X-ray angiography (XA) with optical coherence tomography (OCT) can enhance diagnosis and treatment by providing detailed images of coronary anatomy and plaque structure.
  • The new framework, AutoFOX, employs a deep learning model called TransCAN to accurately align 3D vascular images, achieving impressive alignment precision, especially at critical anatomical points.
  • AutoFOX also includes innovative methods for reconstructing side branches and utilizes a diverse dataset for validation, demonstrating strong accuracy and reliability in assessing bifurcation lesions, which is essential for improving CAD management and procedures.
View Article and Find Full Text PDF

Background The prognostic value of coronary CT angiography (CTA)-derived quantitative flow ratio (CT-QFR) remains unknown. Purpose To determine the prognostic value of CT-QFR in predicting the long-term outcomes of patients with suspected coronary artery disease (CAD) in comparison with invasive coronary angiography (ICA)/SPECT and to determine the influence of prior percutaneous coronary intervention (PCI) on the prognostic value of CT-QFR. Materials and Methods In this secondary analysis of the prospective international CORE320 study, 379 participants who underwent coronary CTA and SPECT within 60 days before ICA between November 2009 and July 2011 were included for follow-up.

View Article and Find Full Text PDF

Magnetic resonance imaging (MRI) of the knee is the recommended diagnostic method before invasive arthroscopy surgery. Nevertheless, interpreting knee MRI scans is a time-consuming process that is vulnerable to inaccuracies and inconsistencies. We proposed a multitask learning network MCSNet which efficiently introduces segmentation prior features and enhances classification results through multiscale feature fusion and spatial attention modules.

View Article and Find Full Text PDF
Article Synopsis
  • Coronary computed tomography angiography (CCTA) combined with Murray law-based quantitative flow ratio (CT-μFR) is a new non-invasive technique for quickly determining fractional flow reserve (FFR) in patients with coronary artery disease, though its effectiveness required validation.
  • A trial involving 260 patients assessed the accuracy of onsite CT-μFR compared to invasive methods, focusing on its ability to detect significant coronary stenosis (narrowing of blood vessels).
  • Results showed CT-μFR had a patient-level accuracy of 89.6%, surpassing the target accuracy of 72% and proving to be as effective as invasive methods in specific cases, confirming its potential as a reliable diagnostic tool.
View Article and Find Full Text PDF

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label newly selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep active learning (DAL), remain scarce.

View Article and Find Full Text PDF

Because of the widespread application of anesthetic drugs in the fields of animal breeding and transportation, demand for the rapid, sensitive detection of anesthetic drugs in animal meat is increasing. The complex animal meat matrix contains various interfering substances, such as proteins, fats, and phospholipids, along with anesthetic drug residues at very low concentrations. Therefore, adopting appropriate pretreatment methods is necessary to improve the sensitivity of detection.

View Article and Find Full Text PDF
Article Synopsis
  • - The study aimed to assess and compare the diagnostic accuracy of coronary CT angiography-based quantitative flow ratio (CT-QFR) against invasive coronary angiography-based Murray law QFR (μQFR), using fractional flow reserve (FFR) as the gold standard for identifying significant arterial blockages.
  • - A total of 191 vessels from 167 patients were analyzed, revealing that while CT-QFR had a slightly lower correlation with FFR compared to μQFR, the differences were not statistically significant; both methods significantly outperformed traditional diameter stenosis measurements from CTA.
  • - The diagnostic performance of CT-QFR was 88% overall, with high sensitivity and specificity, particularly effective in non-calcified lesions, while also
View Article and Find Full Text PDF

Understanding multicomponent binding interactions in protein-ligand, protein-protein, and competition systems is essential for fundamental biology and drug discovery. Hand-deriving equations quickly become unfeasible when the number of components is increased, and direct analytical solutions only exist to a certain complexity. To address this problem and allow easy access to simulation, plotting, and parameter fitting to complex systems at equilibrium, we present the Python package PyBindingCurve.

View Article and Find Full Text PDF

Activation of the epidermal growth factor receptor (EGFR) is crucial for development, tissue homeostasis, and immunity. Dysregulation of EGFR signaling is associated with numerous diseases. EGFR ubiquitination and endosomal trafficking are key events that regulate the termination of EGFR signaling, but their underlying mechanisms remain obscure.

View Article and Find Full Text PDF

The behavior of liquids in two-dimensional (2-D) graphene oxide (GO) nanopores is important for developing GO-based nanoscience and nanofluidics. Herein, molecular dynamics simulation was carried out to study the equilibrium structures and shear viscosity for water and ethanol confined within 2-D GO nanochannels. It was observed that both species obviously exhibit structured features near GO surfaces.

View Article and Find Full Text PDF

A method for the determination of 29 imidazoles and their metabolites in pork by liquid chromatography-tandem mass spectrometry has been developed. The samples were extracted with ethyl acetate, and then defatted with -hexane after concentration of the extracts. The analytes were separated on a C reversed-phase column with 0.

View Article and Find Full Text PDF

A simple analysis of chlorophenols (2-chlorophenol, 2,4-dichlorophenol, 2,4,6-trichlorophenol, and pentachlorophenol) and phenol was accomplished by coupling a pressurized CEC with amperometric detection (AD). Efficient and reproducible separation of these compounds was achieved within 9 min on a capillary monolithic stationary phase bonded with octadecyl ligands and sulfonate groups, where the selectivity and the retention of analytes can be functionally controlled by optimizing experimental variables, including organic modifier content, mobile phase pH, ionic strength, working electrode potential, separation voltage, and supplementary pressure. A mixed-mode retention mechanism consisting of reverse-phase chromatographic partition, electrostatic repulsion, and electrophoresis is considered to play roles in the separation.

View Article and Find Full Text PDF