By peripheral nerve injury, we mean theloss of neurosensory and neuromotor functionsinduced by various causative factors,manifesting paralysis of the limbs andmuscular atrophy. It falls into the category ofinjury of t...By peripheral nerve injury, we mean theloss of neurosensory and neuromotor functionsinduced by various causative factors,manifesting paralysis of the limbs andmuscular atrophy. It falls into the category ofinjury of the muscle and tendon, and flacciditysyndrome in TCM. The following is asummary of documents in the recent 20展开更多
Objective： To report a case ser/es of six neglected cervical spine dislocations without neurological deficit, which were managed operatively. Methods： The study was conducted fromAugust 2010 to December 2011 and ca...Objective： To report a case ser/es of six neglected cervical spine dislocations without neurological deficit, which were managed operatively. Methods： The study was conducted fromAugust 2010 to December 2011 and cases were selected from the out- patient department of Postgraduate Institute of Medical Education and Research, India. The patients were in the age group of 30 to 50 years. All patients were operated via both anterior and posterior approaches. Results： During the immediate postoperative period, five （83.33%） patients had normal neurological status. One （16.67%） patient who had C5-C6 subluxation developed neu- rological deficit with sensory loss below C6 level and motor power of 2/5 in the lower limb and 3/5 in the upper limb below C6 level. Conclusion： There is no role of skull traction in ne- glected distractive flexion injuries to cervical spine delayed for more than 3 weeks. Posterior followed by anterior ap- proach saves much time. If both approaches are to be done in the same sitting, there is no need for instrumentation posteriorly. But if staged procedure is planed, posterior sta- bilization is recommended, as there is a risk of deterioration in neurological status.展开更多
In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific...In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.展开更多
文摘By peripheral nerve injury, we mean theloss of neurosensory and neuromotor functionsinduced by various causative factors,manifesting paralysis of the limbs andmuscular atrophy. It falls into the category ofinjury of the muscle and tendon, and flacciditysyndrome in TCM. The following is asummary of documents in the recent 20
文摘Objective： To report a case ser/es of six neglected cervical spine dislocations without neurological deficit, which were managed operatively. Methods： The study was conducted fromAugust 2010 to December 2011 and cases were selected from the out- patient department of Postgraduate Institute of Medical Education and Research, India. The patients were in the age group of 30 to 50 years. All patients were operated via both anterior and posterior approaches. Results： During the immediate postoperative period, five （83.33%） patients had normal neurological status. One （16.67%） patient who had C5-C6 subluxation developed neu- rological deficit with sensory loss below C6 level and motor power of 2/5 in the lower limb and 3/5 in the upper limb below C6 level. Conclusion： There is no role of skull traction in ne- glected distractive flexion injuries to cervical spine delayed for more than 3 weeks. Posterior followed by anterior ap- proach saves much time. If both approaches are to be done in the same sitting, there is no need for instrumentation posteriorly. But if staged procedure is planed, posterior sta- bilization is recommended, as there is a risk of deterioration in neurological status.
基金Project supported by the National Natural Science Foundation of China(No.61379074)the Zhejiang Provincial Natural Science Foundation of China(Nos.LZ12F02003 and LY15F020035)
文摘In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.
