Publications by authors named "Kyoung Yeon Lee"

Background: This study aimed to assess the outcomes of conservative management in patients with thoracolumbar fractures classified with a Thoracolumbar Injury Classification and Severity (TLICS) score of 4 or 5, and to analyze initial imaging findings and clinical risk factors associated with treatment failure.

Methods: In this retrospective analysis, patients with thoracolumbar fractures and a TLICS score of 4 or 5, determined through MRI from January 2017 to December 2020, were included. Patients undergoing conservative treatment were categorized into two groups: Group 1 (treatment success) and Group 2 (treatment failure), based on initial and 6-month follow-up outcomes.

View Article and Find Full Text PDF

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise.

Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics-compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)-from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT).

View Article and Find Full Text PDF

Background: Neurosarcoidosis is rare, and among its manifestations, nerve root involvement has been reported in only a few cases. Therefore, magnetic resonance imaging (MRI) findings of neurosarcoidosis, particularly those involving nerve roots, are scarce in the literature.

Methods: We presented the case of neurosarcoidosis involving cervical nerve roots and cranial nerves, alongside a systematic literature review.

View Article and Find Full Text PDF

Purpose: To investigate factors that distinguish COVID-19 vaccine-related axillary lymphadenopathy from malignancy or other etiologies.

Methods: From June 2021 to April 2022, 3859 consecutive female patients had breast and axillary ultrasound (US) at our institution. After exclusions, 592 patients were included in the study.

View Article and Find Full Text PDF
Article Synopsis
  • This study developed a deep learning algorithm to automatically detect and locate posterior ligamentous complex (PLC) injuries in patients with acute thoracolumbar fractures using MRI images.
  • The algorithm was tested on a dataset of 500 patients and showed strong diagnostic performance with area under the curves (AUCs) of 0.928 for internal validation and 0.916 for external validation, comparable to experienced radiologists.
  • The algorithm also notably improved the performance of radiology trainees in diagnosing PLC injuries, highlighting its potential as a supportive tool in medical imaging.
View Article and Find Full Text PDF

The fingers are among the most commonly injured structures in traumatic injuries resulting from sports and work. Finger injuries encompass a broad spectrum of injuries to bone and soft tissues, including tendons, ligaments, and cartilage. The high resolution of 3T MRI with dedicated surface coils allows for optimal assessment of the intricate soft tissue structures of the fingers.

View Article and Find Full Text PDF
Article Synopsis
  • Spinal Cord Infarction (SCI) is challenging to diagnose due to its rarity, unclear causes, and lack of established diagnostic guidelines, with limited research using advanced imaging techniques.
  • A case study of a 56-year-old man with heart arrhythmia showed symptoms like right visual field loss and left arm pain, revealing brain infarctions and atypical SCI on MRI scans that resembled multiple sclerosis.
  • The study suggests that using Diffusion-Weighted Imaging (DWI) in spinal MRIs can aid in diagnosing SCI in its early phases and help distinguish it from acute multiple sclerosis.
View Article and Find Full Text PDF