Publications by authors named "Junran Wu"
Background: Delay in diagnosing metastatic epidural spinal cord compression (MESCC) adversely impacts clinical outcomes. High-grade MESCC is frequently overlooked on routine staging CT scans. We aim to assess the potential of our deep learning model (DLM) in detecting high-grade MESCC and reducing diagnostic delays.
View Article and Find Full Text PDFBackground Context: Cervical spine MRI is essential for evaluating degenerative cervical spondylosis (DCS) but is time-consuming to report and subject to interobserver variability. The integration of artificial intelligence in medical imaging offers potential solutions to enhance productivity and diagnostic consistency.
Purpose: To assess whether a transformer-based deep learning model (DLM) can improve the efficiency and accuracy of radiologists in reporting DCS MRIs.
Article Synopsis
- A deep learning model was developed to detect and classify cervical cord signal abnormalities, spinal canal, and neural foraminal stenosis on MRI, aimed at improving reporting efficiency and consistency for cervical spondylosis.
- The study analyzed 504 cervical spine MRIs from a patient sample with a mean age of 58, using 90% for training and 10% for internal testing, with additional external testing on another 100 MRIs.
- Results showed the DL model achieved substantial agreement with human readers, outperforming them in classifying spinal canal and foraminal stenosis, and exhibited a high recall of 92.3% for cord signal abnormalities, demonstrating its potential effectiveness in clinical practice.
Article Synopsis
- - The study presents a detailed analysis of how stock price trends are influenced by mutual excitement, using a unique multi-dimensional Hawkes model that focuses on dual moving average crossovers as key events.
- - Through statistical measurements, it was found that these crossover events are more consistent than a typical Poisson process, revealing patterns of self-excitation and cross-excitation among different stock sectors.
- - The research led to the development of a pair trading strategy that leverages the identified mutual excitation mechanism, showing promising backtesting results with real market data that suggest potential profitability in stock trading.