Search

BACKGROUND AND OBJECTIVE: Olecranon fractures are one of the most commonly seen orthopaedic injuries in the emergency room. Fractures of the Olecranon process of the Ulna typically occurs as a result of a motor-vehicle or motorcycle accident, a fall, or assault. The accepted management for Olecranon fractures is for Non displaced fractures short immobilization followed by gradually increasing range of motion. When displaced ,Open reduction and internal fixation with k-wires and figure of eight tension band wiring for simple transverse fractures and olecranon hook plate for comminuted fractures The present study is undertaken to evaluate the results of surgical management, the merits and demerits and to asses elbow joint motion and stability after the procedure.MATERIALS AND METHODS: It is a prospective study which was carried out from September 2010 to September 2012 in Bapuji Hospital and Chigateri General Hospital attached toJ.J.M Medical College, Davangere. In this study period of 25 cases of fracture olecranon treated by Tension band wiring with Kirshner wire for Simple transverse fractures and Olecranon hook plate for Communited fracturesRESULTS: In our series, majority of the patients were males, middle aged, with road traffic accident being the commonest mode of injury, Most of the cases were Type II B fractures i.e., oblique and transverse fractures according to Colton’s classification Surgery was performed with in 3.48 average days, Union was noted clinically and radiologically and functional evaluation was done by Mayo elbow performance score. Excellent results was present in 18 patients (72%), 4(16%) good and 3(12%) fair with no poor results.INTERPRETATION /CONCLUSION From the present study it is concluded that the technique of open reduction and internal fixation with Kirschner wires and tension band wiring for simple transverse and oblique fractures and olecranon plate fixation for comminuted fractures are effective means and gold standard technique of treating fractures of olecranon and is based on sound biomechanical principle.

Biomedical image segmentation is one of the main and fast growing field in medical image processing domain. Deep neural networks is one of the popular field used for image segmentation. Convolutional neural networks(CNNs) in deep neural networks have shown good performance for biomedical image segmentation. However, a strong notion exists that large number of annotated images are required for training of CNNs. Therefore, in this paper we have come up with a modified U-Net architecture for limited number of annotated data with an intersection over union score of 92.54%. The architecture uses rectified-adam optimizer(advanced version of adam) for minimizing the loss function which helps us to come close to global optima. We have also compared the performance of various optimizers on the proposed network.