Background and purpose — Deep-learning approaches based on convolutional neural networks (CNNs) are gaining interest in the medical imaging field. We evaluated the diagnostic performance of a CNN to discriminate femoral neck fractures, trochanteric fractures, and non-fracture using antero-posterior (AP) and lateral hip radiographs. Patients and methods — 1,703 plain hip AP radiographs and 1,220 plain hip lateral radiographs were included in the total dataset. 150 images each of the AP and lateral views were separated out and the remainder of the dataset was used for training. The CNN made the diagnosis based on: (1) AP radiographs alone, (2) lateral radiographs alone, or (3) both AP and lateral radiographs combined. The diagnostic performance of the CNN was measured by the accuracy, recall, precision, and F1 score. We further compared the CNN’s performance with that of orthopedic surgeons. Results — The average accuracy, recall, precision, and F1 score of the CNN based on both anteroposterior and lateral radiographs were 0.98, 0.98, 0.98, and 0.98, respectively. The accuracy of the CNN was comparable to, or statistically significantly better than, that of the orthopedic surgeons regardless of radiographic view used. In the CNN model, the accuracy of the diagnosis based on both views was significantly better than the lateral view alone and tended to be better than the AP view alone. Interpretation — The CNN exhibited comparable or superior performance to that of orthopedic surgeons to discriminate femoral neck fractures, trochanteric fractures, and non-fracture using both AP and lateral hip radiographs.

No abstract

No abstract

No abstract

Introduction: Condoliase is a newly approved drug that improves symptoms associated with lumbar disk herniation (LDH) by intradiscal administration. This study aimed to evaluate the mid-term outcomes of condoliase injection, examine the adverse events, including cases that required surgery after condoliase administration, and verify cases in which condoliase could be effective. Methods: We enrolled patients with LDH who were treated conservatively for at least six weeks and received condoliase. We assessed the visual analog scale (VAS) score, Japanese Orthopaedic Association Back Pain Evaluation Questionnaire, Oswestry Disability Index, disk height, and disk degeneration for up to 6 months, and we examined the complications. Furthermore, a 50% or more improvement in leg pain VAS score was considered effective. Factors related to symptom improvement were investigated by determining whether lower limb pain improved in six months. Results: In total, 84 patients were recruited (52 men, 32 women; mean age, 44.2 ± 17.1 [16-86 years]). The duration of illness was 6.7 ± 6.8 (1.5-30) months. All patient-based outcomes significantly improved at 4 weeks after the administration compared with pretreatment. The intervertebral disc height decreased significantly at four weeks after condoliase administration compared with that before administration. Progression of intervertebral disc degeneration occurred in 50% of the patients. Eleven patients underwent herniotomy due to poor treatment effects. Moreover, treatment in 77.4% of the patients was considered effective. A logistic regression analysis revealed that L5/S1 disk administration (p = 0.029; odds ratio, 5.94; 95% confidence interval, 1.20-29.45) were significantly associated with clinical effectiveness. Conclusions: Condoliase disk administration improved pain and quality of life over time. Condoliase disk administration was more effective in L5/S1 intervertebral administration.