No abstract

<p class="abstract"><strong>Background:</strong> Hip prosthesis is a successful surgical technique the treatment of hip joint fracture. Thompson hip prosthesis is commonly used treatment of femoral head fracture. It is designed for non-union of fracture neck of femur when there is no neck available.</p><p class="abstract"><strong>Methods:</strong> In this retrospective study, examined the results of patients with Thompson hip prosthesis (cemented and uncemented). This examination has been done from August 2014 to February 2016. 50 Patients were enrolled in this study with mean age of 70 years in which the ratio of number of females more than the number of males. AO classification was used to categorize the hip fracture type. Patient physical fitness was obtained through visual analog scale. Thompson hip prosthesis has been used to treatment of femoral head fracture, manufactured at Auxein Medical Pvt. Ltd., Sonipat, Haryana, India.<strong></strong></p><p class="abstract"><strong>Results:</strong> Patients were follow-up on six week and three-month after discharge from hospital. 90% patients have excellent or pain-free results. There is no implant related complication has been found such as Loosening, prosthesis related size. The overall performance of hip prosthesis was very good.</p><p class="abstract"><strong>Conclusions:</strong> Present guideline strongly favor of hip prosthesis. After clinical study, we can conclude that the Thompson hip prosthesis is the best technique to treatment of femoral head fracture. Thompson is also a quick, simple, palliative solution to early mobility.</p>

In this work, we present a learning based method focusing on the convolutional neural network (CNN) architecture to detect these forgeries. We consider the detection of both copy-move forgeries and inpainting based forgeries. For these, we synthesize our own large dataset. In addition to classification, the focus is also on interpretability of the forgery detection. As the CNN classification yields the image-level label, it is important to understand if forged region has indeed contributed to the classification. For this purpose, we demonstrate using the Grad-CAM heatmap, that in various correctly classified examples, that the forged region is indeed the region contributing to the classification. Interestingly, this is also applicable for small forged regions, as is depicted in our results. Such an analysis can also help in establishing the reliability of the classification.