Differential convolutional neural network.

Convolutional neural networks with strong representation ability of deep structures have ever increasing popularity in many research areas. The main difference of Convolutional Neural Networks with respect to existing similar artificial neural networks is the inclusion of the convolutional part. This inclusion directly increases the performance of artificial neural networks. This fact has led to the development of many different convolutional models and techniques. In this work, a novel convolution technique named as Differential Convolution and updated error back-propagation algorithm is proposed. The proposed technique aims to transfer feature maps containing directional activation differences to the next layer. This implementation takes the idea of how convolved features change on the feature map into consideration. In a sense, this process adapts the mathematical differentiation operation into the convolutional process. Proposed improved back propagation algorithm also considers neighborhood activation errors. This property increases the classification performance without changing the number of filters. Four different experiment sets were performed to observe the performance and the adaptability of the differential convolution technique. In the first experiment set utilization of the differential convolution on a traditional convolutional neural network structure made a performance boost up to 55.29% for the test accuracy. In the second experiment set differential convolution adaptation raised the top1 and top5 test accuracies of AlexNet by 5.3% and 4.75% on ImageNet dataset. In the third experiment set differential convolution utilized model outperformed all compared convolutional structures. In the fourth experiment set, the Differential VGGNet model obtained by adapting proposed differential convolution technique performed 93.58% and 75.06% accuracy values for CIFAR10 and CIFAR100 datasets, respectively. The accuracy values of the Differential NIN model containing differential convolution operation were 92.44% and 72.65% for the same datasets. In these experiment sets, it was observed that the differential convolution technique outperformed both traditional convolution and other compared convolution techniques. In addition, easy adaptation of the proposed technique to different convolutional structures and its efficiency demonstrate that popular deep learning models may be improved with differential convolution.

Effects of different bladder management methods on the quality of life in patients with traumatic spinal cord injury.

STUDY DESIGN: Multi-center, cross-sectional study. OBJECTIVES: To investigate the effects of different bladder management methods on the quality of life (QoL) in patients with spinal cord injury (SCI). SETTING: Turkey. METHODS: Consecutive SCI patients (n=195, 74.4% males), for whom at least 6 months had elapsed since the injury, were included and evaluated in five groups: normal spontaneous micturition (NSM), micturition with assisted maneuvers (MAM), aseptic intermittent catheterization by patient (IC-P), aseptic IC by an attendant/caregiver (IC-A) and indwelling catheterization. The King's Health Questionnaire was used to evaluate the patients' QoL. RESULTS: The bladder management groups were similar regarding age, time elapsed since injury, education level, marital and occupational status. There was no difference among the groups in general health perception, personal relationships and sleep/energy domain scores. While the NSM group had generally the lowest scores, that is, better QoL, the IC-A group had the highest scores, that is, poorer QoL, in most of the domains. When the patients were grouped according to the frequency of urinary incontinence or American Spinal Injury Association Impairment Scale grades, no difference was found in the domain scores of the groups except the symptom severity domain scores. No significant difference was found between paraplegic and tetraplegic patients in the King's Health Questionnaire domains. CONCLUSION: The QoL was notably affected in SCI patients in IC-A group and negative effects on emotional status, physical and social activity limitations were observed, as well.

The numbers of Foxp3 + Treg cells are positively correlated with higher grade of infiltration at the salivary glands in primary Sjogren's syndrome.

This study was designed to investigate whether Foxp3( +) regulatory T (Treg) cells play a role in the histopathologic changes of primary Sjögren's Syndrome (pSS) and to evaluate other factors possibly associated with Foxp3(+) Treg cells in pSS patients. The number of FoxP3-expressing T cells in peripheral blood (PB) of 39 patients with pSS, 40 patients with rheumatoid arthritis (RA), and 28 healthy controls was measured by flow-cytometer analysis. FoxP3-expressing CD4(+)CD25(+) Treg cells were analyzed in minor salivary gland (SG) tissues of 39 pSS patients. Histopathologic changes were examined by light microscopy according to Chisholm's classification. Immunohistochemistry and immunofluorescence were performed to assess the Foxp3(+) Treg in SG biopsy specim-ens. The numbers of CD4(+) T cells and FoxP3-expressing CD4(+) T cells in PB were similar in all groups. Expression of CD25 on CD4(+) T cells in PB of patients with pSS and RA was significantly higher than in healthy controls, especially for RA patients. Immunohistochemistry and immunofluorescence showed that FoxP3(+) Treg were enriched in the SGs of pSS patients, with a positive correlation between the increase in FoxP3(+) Treg in SG and the Chisholm score in pSS (p < 0.001, r = +0.605). The increase of FoxP3( +) Treg cells in the SGs of pSS patients, which is correlated with gland infiltration, suggests that natural regulatory T cells play an important role in the pathogenesis of pSS. Further studies are required to explore the mechanisms that mediate the relationship between Treg and the pathogenesis of pSS.