Online Prediction of Onsets of Seizure-like Events in Hippocampal Neural Networks Using Wavelet Artificial Neural Networks

It has been previously shown that wavelet artificial neural networks (WANNs) are able to classify the different states of epileptiform activity and predict the onsets of seizure-like events (SLEs) by offline processing (Ann. Biomed. Eng. 33(6):798–810, 2005) of the electrical data from the in-vitro hippocampal slice model of recurrent spontaneous SLEs. The WANN design entailed the assumption that time-varying frequency information from the biological recordings can be used to estimate the times at which onsets of SLEs would most likely occur in the future. Progressions of different frequency components were captured by the artificial neural network (ANN) using selective frequency inputs from the initial wavelet transform of the biological data. The training of the WANN had been established using 184 SLE episodes in 34 slices from 21 rats offline. Nine of these rats also exhibited periods of interictal bursts (IBs). These IBs were included as part of the training to help distinguish the difference in dynamics of bursting activities between the preictal- and interictal type. In this paper, we present the results of an online processing using WANN on 23 in-vitro rat hippocampal slices from 9 rats having 93 spontaneous SLE episodes generated under low magnesium conditions. Over the test cases, three of the nine rats exhibited over 30 min of IB activities. We demonstrated that the WANN was able to classify the different states, namely, interictal, preictal, ictal, and IB activities with an accuracy of 86.6, 72.6, 84.5, and 69.1%, respectively. Prediction of state transitions into ictal events was achieved using regression of initial “normalized time-to-onset” estimates. The SLE onsets can be estimated up to 36.4 s ahead of their actual occurrences, with a mean error of 14.3 ± 27.0 s. The prediction errors decreased progressively as the actual time-to-onset decreased and more initial “normalized time-to-onset” estimates were used for the regression procedure.     

Classification of Leukemia Blood Samples Using Neural Networks

Pattern recognition applied to blood samples for diagnosing leukemia remains an extremely difficult task which frequently leads to misclassification errors due in large part to the inherent problem of data overlap. A novel artificial neural network (ANN) algorithm is proposed for optimizing the classification of multidimensional data, focusing on acute leukemia samples. The programming tool established around the ANN architecture focuses on the classification of normal vs. abnormal blood samples, namely acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML). There were 220 blood samples considered with 60 abnormal samples and 160 normal samples. The algorithm produced very high sensitivity results that improved up to 96.67% in ALL classification with increased data set size. With this type of accuracy, this programming tool provides information to medical doctors in the form of diagnostic references for the specific disease states that are considered for this study. The results obtained prove that a neural network classifier can perform remarkably well for this type of flow-cytometry data. Even more significant is the fact that experimental evaluations in the testing phase reveal that as the ALL data considered is gradually increased from small to large data sets, the more accurate are the classification results.     

神经干细胞球生长动力学模型

神经干细胞的体外大规模培养对于细胞移植治疗中枢神经系统受损及各种神经退行性疾病有重大意义。体外呈球状生长的神经干细胞球在长大到一定尺寸之后，有可能在其内部由于养分缺乏而形成坏死细胞，这对于干细胞的有效扩增是极为不利的。因此，模拟神经球的动态生长过程并分析出现坏死细胞的临界神经球尺度对于神经干细胞的大规模扩增有重要意义。本研究采用元胞自动机技术建立了模拟神经球生长的动态模型，并结合神经球内养分的扩散传递模型，求解神经干细胞球内出现坏死细胞的临界神经球尺寸以及坏死细胞的扩大规律。计算结果表明，坏死细胞的出现与体外培养条件有一定关系；坏死细胞的出现主要取决于神经球的尺寸，其外部再好的培养条件也不可能抑制坏死的出现。此外，计算结果还表明，神经球内由于氧缺乏而形成的坏死细胞的出现要早于由于葡萄糖缺乏时的情况，并且坏死细胞一旦出现，其增长速度就非常快，有可能很快使整个神经球成为坏死细胞球。本研究所建立的CA模型及神经球内的传质模型可以很好的模拟神经球的生长过程。     

High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks

The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73–100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.     

基于细胞神经网络的有核细胞边缘检测方法研究

骨髓切片中的有核细胞数是测量骨髓增生程度的一个重要标志。由于骨髓成分的复杂性,计算机自动识别的效果不甚理想。提出了基于改进的细胞神经网络的有核细胞边缘检测的新方法。首先提出了改进的细胞神经网络的形式,推导了它的稳定性的条件。针对具体应用,设计了合适的网络参数。实验结果证明,新方法能够在复杂背景条件下,准确地提取出有核细胞的边缘。由于细胞神经网络硬件的易实现性,所以具有非常好的应用前景。     

Classification of Endocardial Electrograms Using Adapted Wavelet Packets and Neural Networks

The discrimination of ventricular tachycardias with 1:1 retrograde conduction from sinus tachycardia still remains a challenge for rate based algorithms commonly used in dual-chamber implantable cardioverter defibrillators. Morphology based analysis techniques for a classification of antegrade and retrograde atrial activation patterns can be used to cope with this problem. Here time-domain template matching techniques are known approaches. However, a time-domain representation of endocardial electrograms is not optimal for classification tasks as the dimensionality of the underlying signal space is high and features being irrelevant for a signal characterization are involved in the analysis. Therefore, the aim of this study is to develop an enhanced morphological analysis tool for a classification of antegrade and retrograde atrial activation by using a transform domain representation of endocardial electrograms. For this, we applied an adapted wavelet-packet decomposition to extract discriminating features in endocardial electrograms representing antegrade and retrograde activation patterns. Further, a feed-forward neural network was utilized to produce a classification based on the extracted information. In using our hybrid method, no false classification of the physiological and pathological cardiac state was made. It is concluded that the proposed classification scheme represents a highly efficient approach for a classification of antegrade and retrograde atrial activation.     

Hemodynamic Computation Using Multiphase Flow Dynamics in a Right Coronary Artery

Hemodynamic data on the roles of physiologically critical blood particulates are needed to better understand cardiovascular diseases. The blood flow patterns and particulate buildup were numerically simulated using the multiphase non-Newtonian theory of dense suspension hemodynamics in a realistic right coronary artery (RCA) having various cross sections. The local hemodynamic factors, such as wall shear stress (WSS), red blood cell (RBC) buildup, viscosity, and velocity, varied with the spatially nonuniform vessel structures and temporal cardiac cycles. The model generally predicted higher RBC buildup on the inside radius of curvature. A low WSS region was found in the high RBC buildup region, in particular, on the area of maximum curvature of a realistic human RCA. The complex recirculation patterns, the oscillatory flow with flow reversal, and vessel geometry resulted in RBC buildup due to the prolonged particulate residence time, specifically, at the end of the diastole cycle. The increase of the initial plasma viscosity caused the lower WSS. These predictions have significant implications for understanding the local hemodynamic phenomena that may contribute to the earliest stage of atherosclerosis, as clinically observed on the inside curvatures and torsion of coronary arteries.     

Organization of Neural Networks in the Neocortex

Implanted semimicroelectrodes were used in conscious cats to record spike discharges from groups of close-lying neurons, i.e., multineuron activity, in the deep layers of the frontal and motor areas of the cortex at different levels of food motivation. Spike activity was extracted from 4–7 neurons and interneuronal interactions were studied by cross-correlation analysis between neighboring neurons in each zone (local networks) and between neurons in two zones (distributed networks) with analysis epochs of 0–100 msec. The results showed that neurons in local networks can be divided into two subgroups: neurons with high-amplitude spikes and a predominance of output (divergent) connections and neurons with low-amplitude spikes and a predominance of input (convergent) connections. Local networks are based on powerful monosynaptic connections (with delays of up to 2 msec) between large and small neurons. Most connections in distributed networks were between small neurons in local networks of the frontal cortex and large neurons in local networks in the motor cortex. Food deprivation for 24 h mainly affected late (with delays of 2–100 msec) cross-correlation interneuronal relationships in both local and distributed networks.     

Computer-Aided Diagnosis of Vertebral Compression Fractures Using Convolutional Neural Networks and Radiomics

Journal of Digital Imaging - Vertebral Compression Fracture (VCF) occurs when the vertebral body partially collapses under the action of compressive forces. Non-traumatic VCFs can be secondary to...     

Quantitative Measurement of Blood Flow Dynamics in Embryonic Vasculature Using Spectral Doppler Velocimetry

The biophysical effects of blood flow are known to influence the structure and function of adult cardiovascular systems. Similar effects on the maturation of the cardiovascular system have been difficult to directly and non‐invasively measure due to the small size of the embryo. Optical coherence tomography (OCT) has been shown to provide high spatial and temporal structural imaging of the early embryonic chicken heart. We have developed an extension of Doppler OCT, called spectral Doppler velocimetry (SDV), that will enable direct, non‐invasive quantification of blood flow and shear rate from the early embryonic cardiovascular system. Using this technique, we calculated volumetric flow rate and shear rate from chicken embryo vitelline vessels. We present blood flow dynamics and spatial velocity profiles from three different vessels in the embryo as well as measurements from the outflow tract of the embryonic heart tube. This technology can potentially provide spatial mapping of blood flowand shear rate in embryonic cardiovascular structures, producing quantitative measurements that can be correlated with gene expression and normal and abnormal morphology. Anat Rec, 2009. © 2008 Wiley‐Liss, Inc.     

基于联合决策卷积神经网络的光学相干断层扫描图像自动分类

光学相干断层扫描(OCT)技术能实现视网膜的高分辨率三维层析成像,对视网膜疾病类型的诊断和发展阶段的分析具有至关重要的作用。临床基于 OCT 图像的视网膜疾病诊断主要依靠眼科医生对图像中病变结构的分析,这一人工分析过程不仅耗时而且易产生主观的误判。研究视网膜疾病的自动分析和诊断技术将极大减轻眼科医生的工作量,是实现高效诊疗的有效途径。针对视网膜OCT图像自动分类,构建一种联合决策的卷积神经网络分类模型。该模型利用卷积神经网络从原始输入OCT图像中自动地学习不同层级的特征,同时在网络多个卷积层上设计多个决策层,这些决策层能够根据网络中不同尺度的特征图分别对OCT图像分类,最后模型融合所有决策层的分类结果做出最终决策。在Duke数据集(3 231张OCT图像)上的实验结果表明,基于多层级特征联合决策的卷积神经网络分类模型对正常视网膜、视网膜年龄相关性黄斑变性和视网膜黄斑水肿的平均识别准确率达到94.5%,灵敏性达到90.5%,特异性达到95.8%。在HUCM数据集(4 322张OCT图像)上的实验结果表明,基于多层级特征联合决策的卷积神经网络分类模型的平均识别准确率达到89.6%,灵敏性达到88.8%,特异性达到90.8%。充分利用卷积神经网络中丰富的多层级特征,能够有效地对视网膜OCT图像实现准确的分类,为临床上视网膜疾病的辅助诊断提供技术支撑。     

Rapid Assessment of Acute Ischemic Stroke by Computed Tomography Using Deep Convolutional Neural Networks

Journal of Digital Imaging - Acute stroke is one of the leading causes of disability and death worldwide. Regarding clinical diagnoses, a rapid and accurate procedure is necessary for patients...     

Use of Neural Networks for Identification of Artifacts in Electroencephalographic Signals Decomposed Using Wavelet Packet Transform

An algorithm for automatic interference (artifact) detection is suggested. This algorithm detects interference (artifact) as a component of EEG signals. The algorithm is based on approximation of electrophysiological signal using neural network model decomposition using the wavelet packet transform.     

Effects of Ascorbic Acid on Calcium Signaling in Tumor Cells

Effects of ascorbic acid on calcium homeostasis of human laryngeal carcinoma cells were studied. Intracellular concentration of free calcium and intracellular pH were measured by fluorescent analysis. Ascorbic acid in concentrations of 3–10 mM caused pH drop and sharply increased concentrations of free Ca ions in HEp-2 cells. Intracellular concentration of free Ca ions resulted from Ca ion release from the thapsigargin-sensitive Ca depots.     

Endoplasmic Reticulum Stress and the Related Signaling Networks in Severe Asthma

The endoplasmic reticulum (ER) is a specialized organelle that plays a central role in biosynthesis, correct protein folding, and posttranslational modifications of secretory and membrane proteins. Loss of homeostasis in ER functions triggers the ER stress response, resulting in activation of unfolded protein response (UPR), a hallmark of many inflammatory diseases. These pathways have been reported as critical players in the pathogenesis of various pulmonary disorders, including pulmonary fibrosis, lung injury, and chronic airway disorders. More interestingly, ER stress and the related signaling networks are emerging as important modulators of inflammatory and immune responses in the development of allergen-induced bronchial asthma, especially severe asthma.