Detection of microscopic glaucoma through fundus images using deep transfer learning approach

Glaucoma disease in humans can lead to blindness if it progresses to the point where it affects the oculus' optic nerve head. It is not easily detected since there are no symptoms, but it can be detected using tonometry, ophthalmoscopy, and perimeter. However, advances in artificial intelligence approaches have permitted machine learning techniques to diagnose at an early stage. Numerous methods have been proposed using Machine Learning to diagnose glaucoma with different data sets and techniques but these are complex methods. Although, medical imaging instruments are used as glaucoma screening methods, fundus imaging specifically is the most used screening technique for glaucoma detection. This study presents a novel DenseNet and DarkNet combination to classify normal and glaucoma affected fundus image. These frameworks have been trained and tested on three data sets of high-resolution fundus (HRF), RIM 1, and ACRIMA. A total of 658 images have been used for healthy eyes and 612 images for glaucoma-affected eyes classification. It has also been observed that the fusion of DenseNet and DarkNet outperforms the two CNN networks and achieved 99.7% accuracy, 98.9% sensitivity, 100% specificity for the HRF database. In contrast, for the RIM1 database, 89.3% accuracy, 93.3% sensitivity, 88.46% specificity has been attained. Moreover, for the ACRIMA database, 99% accuracy, 100% sensitivity, 99% specificity has been achieved. Therefore, the proposed method is robust and efficient with less computational time and complexity compared to the literature available.     

The effect of fiber insertion on fracture strength and fracture modes in endocrown and overlay restorations

Aim of this study was to determine the fracture strength and modes of endocrown and overlay restorations with/without fiber reinforcement on endodontically treated teeth. Sixty-five molar teeth were used: Group IN (intact teeth), Group E (endocrown), Group ER (endocrown + ribbond), Group O (overlay), Group OR (overlay + ribbond; n = 13). Ribbond (Seattle, WA) was inserted at the base of pulp chamber in Group ER and OR. All restorations were designed and produced by using computer-aided design and computer-aided manufacturing (Sirona Dental Systems, Bensheim, Germany) and Cerasmart (GC Corp. Kasugai, Aichi, Japan). All teeth were subjected to thermomechanical aging and fractured in a universal test device. Fractured surfaces were analyzed with a stereomicroscope (SMZ1000, Nikon, Japan). Data were analyzed with Welch's analysis of variance and Games–Howell test (p < .001). Group E showed significantly lower fracture strength values than other groups(p < .05). No statistically significant differences were found among the other groups(p > .05). Most of the unfavorable fractures were seen in Groups E and O. Overlay restorations showed higher fracture strength values than endocrown restorations. Although fiber insertion did not improve the fracture strength of the indirect restorations, it reduced the frequency of irreparable fracture mode. Overlay restorations and fiber application are more advantageous in preserving the durability of the endodontically treated teeth.     

Machine learning for post-traumatic stress disorder identification utilizing resting-state functional magnetic resonance imaging

Early detection of post-traumatic stress disorder (PTSD) is essential for proper treatment of the patients to recover from this disorder. The aligned purpose of this study was to investigate the performance deviations in regions of interest (ROI) of PTSD than the healthy brain regions, to assess interregional functional connectivity and applications of machine learning techniques to identify PTSD and healthy control using resting-state functional magnetic resonance imaging (rs-fMRI). The rs-fMRI data of 10 ROI was extracted from 14 approved PTSD subjects and 14 healthy controls. The rs-fMRI data of the selected ROI were used in ANOVA to measure performance level and Pearson's correlation to investigate the interregional functional connectivity in PTSD brains. In machine learning approaches, the logistic regression, K-nearest neighbor (KNN), support vector machine (SVM) with linear, radial basis function, and polynomial kernels were used to classify the PTSD and control subjects. The performance level in brain regions of PTSD deviated as compared to the regions in the healthy brain. In addition, significant positive or negative functional connectivity was observed among ROI in PTSD brains. The rs-fMRI data have been distributed in training, validation, and testing group for maturity, implementation of machine learning techniques. The KNN and SVM with radial basis function kernel were outperformed for classification among other methods with high accuracies (96.6%, 94.8%, 98.5%) and (93.7%, 95.2%, 99.2%) to train, validate, and test datasets, respectively. The study's findings may provide a guideline to observe performance and functional connectivity of the brain regions in PTSD and to discriminate PTSD subject using only the suggested algorithms.     

A new mathematical approach to improve residual stress measurement in ring-core method

Journal of Mechanical Science and Technology - III-conditioning at the inverse equation of integral method in ring-core residual stress measurement leads to high stress sensitivity to strain...     

Concurrent impact of chipping and pitting damages in a locomotive power transmission system

Journal of Mechanical Science and Technology - The reliability of power transmission systems in locomotives directly impacts trains’ availability and running safety. The failure of gears,...     

热暴露对激光沉积Ti60A高温钛合金组织性能影响

对比研究了激光沉积Ti60A高温钛合金经600℃,100 h的恒温热暴露和循环热暴露后显微组织、拉伸性能及断口形貌。结果表明,恒温热暴露后α相体积分数略有增大。循环热暴露后β相体积分数显著减小,α相体积分数增加约12%。这2种热暴露后合金中Ti3Al共格有序相和100~150 nm的六方S2型椭球状硅化物(TiZr0.3)6Si3的析出基本一致,拉伸性能均明显下降,尤其是循环热暴露后的塑性几乎丧失,这与合金组织在循环热应力作用下的显著变化密切相关。     

镍-铝复合涂层的电沉积机理

在改进的Watts溶液中电沉积镍-铝复合涂层。采用Z电位分析、伏安法和电化学阻抗谱（EIS）,研究涂层的电化学行为。结果发现,铝颗粒的Z电位是-4 mV,与氧化铝的非常接近。添加导电铝颗粒到电解液中,导致极化曲线向负电位方向移动,且EIS曲线的环路尺寸增大。结果表明,镍-铝复合层的共沉积行为服从Guglielmi模型。加入的导电铝颗粒起惰性粒子的作用,证实在铝颗粒表面存在薄的氧化铝层。     

Enhancement of Flexural Design of Horizontally Curved Prestressed Bridges

In this paper, flexural behavior of horizontally curved prestressed (posttensioned) box bridges is studied by using three-dimensional and refined finite-element modeling and analysis. Bridge length, section geometry, and material properties are the same in all the models, while angle of curvature varies from 0 to 90°. The results of analysis show that in curved bridges, stress distribution is significantly different in comparison to straight bridges. Also, the level of stresses at some locations of section width is considerably high. It is proposed to vary the distribution of the prestressing tendons across section width in order to optimize the bridge capacity. Results show that by proper redistribution of prestressing in section width, significant reduction in resultant stress is possible.     

Effects of Raw Material Molar Ratio and Addition of Mg on Titanium Aluminide–Alumina Composite Formation Mechanism

Powder Metallurgy and Metal Ceramics - In this study, the effects of molar ratio of the raw materials (TiO2 and Al) and the addition of Mg on the titanium aluminide–alumina composite...