Although conventional radiography is the method most frequently used for monitoring progression of osteoarthritis, it may not show osteoarthritic changes of the knee until late in the disease, and it may show involvement of only one or two compartments in patients who have tricompartmental disease. We compared radiography, CT, and MR imaging for assessing the extent and severity of osteoarthritis of the knee in 20 patients. Radiography included posteroanterior weight-bearing, true lateral, and sunrise patellar projections. Axial CT scans were reformatted in sagittal and coronal planes. MR imaging consisted of spin-echo (600-800/20; 2000/60, 120 [TR/TE]), and gradient-echo (600/30, theta = 30 degrees) sequences. The severity of osteoarthritic changes was graded from 0 to 3. MR frequently showed tricompartmental cartilage loss when radiography and CT showed only bicompartmental involvement in the medial and patellofemoral compartments. In the lateral compartment, MR showed a higher prevalence of cartilage l...

Despite the overall success of using artificial intelligence (AI) to assist radiologists in performing computer-aided patient diagnosis, it remains challenging to build good models with small datasets at individual sites. Because many medical images do not come with proper labelling for training, this requires radiologists to perform strenuous labelling work and to prepare the dataset for training. Placing such demands on radiologists is unsustainable, given the ever-increasing number of medical images taken each year. We propose an alternative solution using a relatively new learning framework. This framework, called federated learning, allows individual sites to train a global model in a collaborative effort. Federated learning involves aggregating training results from multiple sites to create a global model without directly sharing datasets. This ensures that patient privacy is maintained across sites. Furthermore, the added supervision obtained from the results of partnering sites improves the global model’s overall detection abilities. This alleviates the issue of insufficient supervision when training AI models with small datasets. Lastly, we also address the major challenges of adopting federated learning.

OBJECTIVE. The purpose of this study was to describe the significance of an avulsion fracture of the head of the fibula (“arcuate” sign) and its association with injuries of the knee on MR imaging.MATERIALS AND METHODS. We conducted a retrospective search of 2318 patients who underwent conventional radiography and MR imaging after an episode of knee trauma. Patients were included in this study if they had an avulsion fracture of the head of the fibula revealed on conventional radiography and underwent arthroscopy. Thirteen patients, all of whom were men, satisfied the inclusion criteria. Ten patients underwent further explorative surgery. The clinical, radiographic, MR imaging, and surgical findings were then reviewed.RESULTS. The avulsion fracture of the styloid process of the fibular head was apparently related to injuries of the arcuate complex in all 13 patients. Radiographically, the bony fragment was horizontally oriented and similar in size in most patients, ranging from 8 to 10 mm in length and fr...

Purpose. To assess the change in bone mineral density (BMD) after spinal cord injury (SCI) and to evaluate whether BMD loss can be reversed with the intervention of functional electric stimulation cycling exercises (FESCE). Methods. Fifteen males with SCI were included. Fifteen able-bodied males were also tested to compare BMD. In the SCI group, the FESCE was performed for six months, and then was discontinued in the subsequent six months. BMD was performed before the FESCE, immediately after six months of the FESCE, and at the end of the subsequent six months. Results. Before the FESCE, the BMD of the SCI subjects in every site, except the lumbar spine, was lower than that of the able-bodied subjects. After six months of FESCE, BMD of the distal femur (DF) and proximal tibia (PT) increased significantly, and BMD of the calcaneus (heel) showed a trend of increase. However, the BMD in the DF, PT, and heel decreased significantly after the subsequent six months without FESCE. The BMD of the femoral neck (FN) decreased progressively throughout the programme. Conclusions. Our study showed site-specific BMD changes after FESCE. The BMD loss in the DF and PT was partially reversed after six months of FESCE, but the effect faded once the exercise was discontinued.