Publications by authors named "Rikke V Boel"
Background: Hip and knee osteoarthritis (OA) patients demonstrate distinct gait patterns, yet detecting subtle abnormalities with wearable sensors remains uncertain. This study aimed to assess a predictive model's efficacy in distinguishing between hip and knee OA gait patterns using accelerometer data.
Method: Participants with hip or knee OA underwent overground walking assessments, recording lower limb accelerations for subsequent time and frequency domain analyses.
Article Synopsis
- This study developed a computer vision method to accurately detect and outline the proximal femur in radiographs for patients with Legg-Calvé-Perthes disease (LCPD), aiming to improve the assessment of femoral head deformity crucial for LCPD outcomes.
- The researchers utilized a pretrained YOLOv5 model for object detection on over 2000 radiographs and applied a U-Net convolutional neural network for segmenting the proximal femur on 800 manually annotated images, achieving high accuracy rates.
- The results indicate that the fully automatic detection and segmentation system can significantly enhance the reliability of LCPD diagnosis and prognosis, showcasing the potential of computer vision in medical imaging.