RESUMO
Objective To explore the feasibility of the deep convolutional neural network (DCNN) judging the indications and prognosis of the total knee arthroplasty based on the trained DCNN computer learning system.Methods C1FAR-10 DCNN model based on TensorFlow (an open source system,Google,USA) optimized by Alex Krizhevsky were constructed.There were 400 cases with knee osteoarthritis from different databases used for analysis.Three hundred patients underwent total knee arthroplasty,while 100 did not.X-ray of 200 preoperative cases from the 400 cases and their enlarged image (50 times) were applied for training DCNN,while the enlarged images from other 200 cases were used to test the DCNN.The correlation and the regression between judgment of the DCNN and clinical truth were analyzed.The clinical truths were rechecked three times and were confirmed by treatment results.Pearson correlation and linear regression analysis were used.The relation test of the software was only used as a reference.Results There was no significant difference between the baseline of cases for learning and test.After learning 200 cases,the DCNN judged the 10 000 cases enlarged from remaining 200 cases.The correlation between the DCNN judgment and the clinical truth was not significant (r=0.000,F=0.001,P=0.970).False positive was observed in 1 681 cases,false negative in 3 296.After enlarged to 10 000 images,the correlation between the two judgments was significant (F=11 228.735,P=0.000,r=0.727 and R2=0.529).The software detection precision was 0.860.Conclusion DCNN can be applied in judging the indications of the total knee arthroplasty.Large sample size can improve the accuracy of the judgment significantly.
RESUMO
Objective To compare the clinical results of open reduction and plate internal fixation and percutaneous kirschner-wire fixation in the management of distal radius fractures. Methods A retrospective comparison was done on clinical data of 110 patients with distal radius fractures who were treated by plate internal fixation and that of 107 by pereutaneous kirschner-wire fixation from January 2002 to June 2007. Results All patients were followed up for 5-12 months. According to Gartland and Werley scoring system, the excellent rate was 86.4% in plate internal fixation group, which was significantly higher than 74.8% in percutaneous kirschner-wire fixation group (P <0.05). As for type C3 fractures, the excellent rate of the two groups were 76.9% and 70.0%, with no statistical difference (P >0.05). Conclusions Compared with percutaneous kirschner-wire fixation, plate internal fixation is better in treatment of distal radius fractures, but has poor results in management of type C3 fractures.
RESUMO
Objective To compare clinical outcomes of clavicular hook plate and coracoclavicu-lar screw fixation in treatment of acrmioclavicular dislocation (Tossy Ⅲ). Methods From August 2003 to January 2008,38 patients with acromioclavicular dislocation (Tossy Ⅲ) were randomly divided into two groups that were treated with coracoclavicular screw and clavicular hook plate fixation respective-ly. The range of shoulder movement was restricted after operation until the fixation was removed three months later. The shoulder function was evaluated by using Japanese Orthopedic Association (JOA) sco-ring system. The functional scores were compared before and after removal of the internal fixation in two groups. Results All patients were followed up, which showed no statistical difference upon final shoulder function of two groups. There was no loosening or migration of internal fixators. No redislocation occurred after removal of internal fixations. Seven patients complained shoulder pain and three had severe shoulder pain affecting sleep quality in coracoclavicular screw group. The pain was alleviated after remov-al of fixation. Conclusions Coraeeclavicular screw and clavicular hook plate fixation have similar clinical effect in treatment of acromioclavicular dislocation (Tossy Ⅲ), with satisfactory recovery of shoul-der function. Many complications of acromioclavicular fixations can be avoided by restriction of shoulder movement after operation and early functional exercise after removal of fixation.