Dual-feature Fusion Attention Network for Small Object Segmentation.

Accurate segmentation of medical images is an important step during radiotherapy planning and clinical diagnosis. However, manually marking organ or lesion boundaries is tedious, time-consuming, and prone to error due to subjective variability of radiologist. Automatic segmentation remains a challenging task owing to the variation (in shape and size) across subjects. Moreover, existing convolutional neural networks based methods perform poorly in small medical objects segmentation due to class imbalance and boundary ambiguity. In this paper, we propose a dual feature fusion attention network (DFF-Net) to improve the segmentation accuracy of small objects. It mainly includes two core modules: the dual-branch feature fusion module (DFFM) and the reverse attention context module (RACM). We first extract multi-resolution features by multi-scale feature extractor, then construct DFFM to aggregate the global and local contextual information to achieve information complementarity among features, which provides sufficient guidance for accurate small objects segmentation. Moreover, to alleviate the degradation of segmentation accuracy caused by blurred medical image boundaries, we propose RACM to enhance the edge texture of features. Experimental results on datasets NPC, ACDC, and Polyp demonstrate that our proposed method has fewer parameters, faster inference, and lower model complexity, and achieves better accuracy than more state-of-the-art methods.

Deep Neural Networks for Automatic Flower Species Localization and Recognition.

Deep neural networks are efficient methods of recognizing image patterns and have been largely implemented in computer vision applications. Object detection has many applications in computer vision, including face and vehicle detection, video surveillance, and plant leaf detection. An automatic flower identification system over categories is still challenging due to similarities among classes and intraclass variation, so the deep learning model requires more precisely labeled and high-quality data. In this proposed work, an optimized and generalized deep convolutional neural network using Faster-Recurrent Convolutional Neural Network (Faster-RCNN) and Single Short Detector (SSD) is used for detecting, localizing, and classifying flower objects. We prepared 2000 images for various pretrained models, including ResNet 50, ResNet 101, and Inception V2, as well as Mobile Net V2. In this study, 70% of the images were used for training, 25% for validation, and 5% for testing. The experiment demonstrates that the proposed Faster-RCNN model using the transfer learning approach gives an optimum mAP score of 83.3% with 300 and 91.3% with 100 proposals on ten flower classes. In addition, the proposed model could identify, locate, and classify flowers and provide essential details that include flower name, class classification, and multilabeling techniques.

In the line of duty: a study of ambulance drivers during the 2010 conflict in Kashmir.

PURPOSE: The purpose of this study was to identify the problems faced by ambulance drivers working in a conflict zone. METHODS: This study was conducted on ambulance drivers working for the four major hospitals in Kashmir, India. The drivers were interviewed and asked a series of 30 work-related questions. The individual interviews were conducted over a three-month period in the valley of Kashmir that was affected by continuous violence, strict curfew, and strikes. RESULTS: A total of 35 ambulance drivers were interviewed. Drivers worked an average of 60 h/wk, and they drove an average of 160 km/d. Twenty-nine (83%) of the drivers experienced >1 threat of physical harm; 18 (54%) experienced physical assaults; and 31 (89%) reported evidence of psychological morbidity associated with their jobs. CONCLUSIONS: The atmosphere of conflict on the streets of Kashmir impacted the ambulance drivers adversely, both physically as well as mentally. The stress faced by these professionals in conflict zones during their duty hours should be recognized, and corrective measures must be put in place.

The Gibson and Piggott osteotomy for adult hallux valgus.

BACKGROUND: The Gibson and Piggott procedure for hallux valgus is based on sound surgical principles addressing the basic pathologies of this disorder. However, this procedure has not been studied extensively in the literature in comparison to the Mitchell and Chevron osteotomies. MATERIAL AND METHODS: We report a prospective study conducted on 50 adult feet with hallux valgus. The Gibson and Piggot osteotomy was done on all the feet. RESULTS: We obtained 76% excellent and 18% good results with this procedure. CONCLUSION: The results bear out the fact that this procedure is a useful procedure for the management of this disorder.

Tuberculosis of the elbow joint in children: a review of ten patients who were managed nonoperatively.

BACKGROUND: There is scarce information regarding osteoarticular tuberculosis of the elbow in children, even in countries where tuberculosis is endemic. We report our experience with ten patients who were managed nonoperatively. METHODS: We retrospectively assessed ten children with elbow tuberculosis with regard to their presentation, diagnosis, management, response to standard antitubercular drugs, and outcome at the completion of antitubercular therapy. All patients were managed nonoperatively with splinting for as long as six weeks, followed by mobilization along with multidrug antitubercular medication for twelve months. RESULTS: Swelling of the elbow that did not respond to initial treatment was the most common cause for referral to our clinic. The proximal ulnar metaphysis was most commonly involved. The average duration of follow-up was twenty-six months. The average time for healing of draining sinuses was twelve weeks (range, four to fourteen weeks). Lytic lesions, including coke-like sequestrum, healed radiographically at an average of 7.4 months (range, six to nine months). Range of motion improved with treatment, but some motion restriction always persisted, depending on the extent of joint destruction. CONCLUSIONS: In the Indian subcontinent, the presentation of elbow tuberculosis is usually exudative with abscess formation, and the disease is fairly advanced at the time of diagnosis. An "ice cream scoop" appearance of the proximal part of the ulna in children should raise suspicion for tuberculosis. Elbow tuberculosis in children can be treated adequately with use of nonoperative means, regardless of the extent of osseous destruction, with a good outcome.