1.Double-action hemiarthroplastyversus total hip arthroplasty for intertrochanteric fracture in the elderly
Chinese Journal of Tissue Engineering Research 2015;(22):3482-3486
BACKGROUND:Doubld-action hemiarthroplasty and total hip arthroplasty are reliable methods to treat intertrochanteric fracture of femur in the elderly, but which is better remains controversial in the clinic. OBJECTIVE:To observe the practical effect of prosthetic replacement with different methods in treatment of intertrochanteric fracture of femur in the elderly, and to assess the clinical value. METHODS:A total of 54 elderly patients with intertrochanteric fracture of femur at the age of over 65 years old were randomly assigned to two groups. In the observation group (n=27), patients underwent graded cement double-action arthroplasty. In the control group (n=27), patients received cementless total hip arthroplasty. They were folowed up for 2 years. Harris scores were recorded in the two groups so as to assess the therapeutic effects. Folow-up recurrence rate, adverse events and host response to materials were analyzed. RESULTS AND CONCLUSION: The therapeutic effects were similar between the observation and control groups (89%, 81%;P > 0.05), but recurrence rate of 2-year folow-up was significantly lower in the observation group than in the control group (4%, 30%;P < 0.05). Moreover, dislocation, acetabular wear and loosening were not found. Results indicate that the midterm effects were similar between graded cement double-action arthroplasty and total hip arthroplasty in treatment of intertrochanteric fracture in the elderly, but graded cement double-action arthroplasty significantly decreases the recurrence rate.
2.Lower limb joint angle calculation algorithm based on convolutional neural network in X-ray films
Jingni LIU ; Yuwu SHENG ; Changxiu ZHAO ; Cunliang NIU ; Guoyuan HUANG ; Changdong XU ; Shanshan ZHAO ; Bin CHEN
Chinese Journal of Medical Physics 2024;41(8):996-999
A convolutional neural network-based algorithm is proposed for calculating lower limb joint angle in X-ray films.After identifying the region of interest of a specific category in X-ray films through Yolov5 object detection model,U-Net model is used to perform heat map regression for identifying the key feature points,and then the lower limb joint angle is calculated.The results show that the proposed algorithm has higher accuracy than the previous algorithms and can obtain accurate and reliable results,providing references for clinical research and practice.