Publications by authors named "B A Rim"
Background: Ankylosing Spondylitis is a chronic inflammatory rheumatic disease with both articular and extra-articular features. While cardiovascular involvement in Ankylosing spondylitis is rare, it can be life-threatening. This condition is typically associated with the HLAB27 antigen and often presents in the advanced stages of the disease.
View Article and Find Full Text PDFBackground: Endoscopic posterior cervical foraminotomy is gaining popularity among endoscopic spine surgeons for the treatment of radiculopathy caused by foraminal stenosis.
Methods: This study describes a technique using the lateral decubitus position for endoscopic posterior cervical foraminotomy under monitored anesthesia care and local anesthesia only.
Results: A total of 10 patients with contraindications to general anesthesia underwent the procedure, resulting in improvement in cervical radicular pain with no perioperative complications.
The deep learning approach has recently attracted much attention for its outstanding performance to assist in clinical diagnostic tasks, notably in computer-aided solutions. Computer-aided solutions are being developed using chest radiography to identify lung diseases. A chest X-ray image is one of the most often utilized diagnostic imaging modalities in computer-aided solutions since it produces non-invasive standard-of-care data.
View Article and Find Full Text PDFArticle Synopsis
- The paper discusses a deep learning method that utilizes transfer learning to classify lung diseases from chest X-ray images, aiming to enhance the accuracy and efficiency of computer-aided diagnostic systems.
- The proposed method employs an end-to-end learning approach using the EfficientNet v2-M model to directly analyze raw chest X-ray images for identifying diseases.
- Experiments on two different data sets (NIH and Cheonan Soonchunhyang University Hospital) demonstrated promising results, with accuracy rates around 82% and high specificity, especially for tuberculosis detection, showcasing the method's effectiveness in lung disease diagnosis.
Article Synopsis
- - The study focuses on improving the diagnosis of coronary artery disease by using three convolutional neural network (CNN) models to analyze CT images, which traditionally require time-consuming manual review by radiologists.
- - Researchers experimented with different types of CT images: original scans, images focused solely on the heart, and those segmented into nine parts to assess the presence of calcium buildup.
- - The best results came from using the Resnet 50 model on the cropped heart images, achieving an accuracy of 98.52%, suggesting that future advancements could lead to automated analysis of coronary artery calcium in CT scans.