Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach

Deep learning techniques have recently made considerable advances in the field of artificial intelligence. These methodologies can assist psychologists in early diagnosis of mental disorders and preventing severe trauma. Major Depression Disorder (MDD) is a common and serious medical condition whose exact manifestations are not fully understood. So, early discovery of MDD patients helps to cure or limit the adverse effects. Electroencephalogram (EEG) is prominently used to study brain diseases such as MDD due to having high temporal resolution information, and being a noninvasive, inexpensive and portable method. This paper has proposed an EEG-based deep learning framework that automatically discriminates MDD patients from healthy controls. First, the relationships among EEG channels in the form of effective brain connectivity analysis are extracted by Generalized Partial Directed Coherence (GPDC) and Direct directed transfer function (dDTF) methods. A novel combination of sixteen connectivity methods (GPDC and dDTF in eight frequency bands) was used to construct an image for each individual. Finally, the constructed images of EEG signals are applied to the five different deep learning architectures. The first and second algorithms were based on one and two-dimensional convolutional neural network (1DCNN–2DCNN). The third method is based on long short-term memory (LSTM) model, while the fourth and fifth algorithms utilized a combination of CNN with LSTM model namely, 1DCNN-LSTM and 2DCNN-LSTM. The proposed deep learning architectures automatically learn patterns in the constructed image of the EEG signals. The efficiency of the proposed algorithms is evaluated on resting state EEG data obtained from 30 healthy subjects and 34 MDD patients. The experiments show that the 1DCNN-LSTM applied on constructed image of effective connectivity achieves best results with accuracy of 99.24% due to specific architecture which captures the presence of spatial and temporal relations in the brain connectivity. The proposed method as a diagnostic tool is able to help clinicians for diagnosing the MDD patients for early diagnosis and treatment.     

A novel fast kilovoltage switching dual-energy CT with deep learning: Accuracy of CT number on virtual monochromatic imaging and iodine quantification

PurposeA novel fast kilovoltage switching dual-energy CT with deep learning [Deep learning based-spectral CT (DL-Spectral CT)], which generates a complete sinogram for each kilovolt using deep learning views that complement the measured views at each energy, was commercialized in 2020. The purpose of this study was to evaluate the accuracy of CT numbers in virtual monochromatic images (VMIs) and iodine quantifications at various radiation doses using DL-Spectral CT.Materials and methodsTwo multi-energy phantoms (large and small) using several rods representing different materials (iodine, calcium, blood, and adipose) were scanned by DL-Spectral CT at varying radiation doses. Images were reconstructed using three reconstruction parameters (body, lung, bone). The absolute percentage errors (APEs) for CT numbers on VMIs at 50, 70, and 100 keV and iodine quantification were compared among different radiation dose protocols.ResultsThe APEs of the CT numbers on VMIs were <15% in both the large and small phantoms, except at the minimum dose in the large phantom. There were no significant differences among radiation dose protocols in computed tomography dose index volumes of 12.3 mGy or larger. The accuracy of iodine quantification provided by the body parameter was significantly better than those obtained with the lung and bone parameters. Increasing the radiation dose did not always improve the accuracy of iodine quantification, regardless of the reconstruction parameter and phantom size.ConclusionThe accuracy of iodine quantification and CT numbers on VMIs in DL-Spectral CT was not affected by the radiation dose, except for an extremely low radiation dose for body size.     

Deep Learning Using Havrda-Charvat Entropy for Classification of Pulmonary Optical Endomicroscopy

1) ObjectivePulmonary optical endomicroscopy (POE) is an imaging technology in real time. It allows to examine pulmonary alveoli at a microscopic level. Acquired in clinical settings, a POE image sequence can have as much as 25% of the sequence being uninformative frames (i.e. pure-noise and motion artifacts). For future data analysis, these uninformative frames must be first removed from the sequence. Therefore, the objective of our work is to develop an automatic detection method of uninformative images in endomicroscopy images.2) Material and methodsWe propose to take the detection problem as a classification one. Considering advantages of deep learning methods, a classifier based on CNN (Convolutional Neural Network) is designed with a new loss function based on Havrda-Charvat entropy which is a parametrical generalization of the Shannon entropy. We propose to use this formula to get a better hold on all sorts of data since it provides a model more stable than the Shannon entropy.3) ResultsOur method is tested on one POE dataset including 3895 distinct images and is showing better results than using Shannon entropy and behaves better with regard to the problem of overfitting. We obtain 70% of accuracy with Shannon entropy versus 77 to 79% with Havrda-Charvat.4) ConclusionWe can conclude that Havrda-Charvat entropy is better suited for restricted and or noisy datasets due to its generalized nature. It is also more suitable for classification in endomicroscopy datasets.     

An Approach Based on Mutually Informed Neural Networks to Optimize the Generalization Capabilities of Decision Support Systems Developed for Heart Failure Prediction

Available clinical methods for heart failure (HF) diagnosis are expensive and require a high-level of experts intervention. Recently, various machine learning models have been developed for the prediction of HF where most of them have an issue of over-fitting. Over-fitting occurs when machine learning based predictive models show better performance on the training data yet demonstrate a poor performance on the testing data and the other way around. Developing a machine learning model which is able to produce generalization capabilities (such that the model exhibits better performance on both the training and the testing data sets) could overall minimize the prediction errors. Hence, such prediction models could potentially be helpful to cardiologists for the effective diagnose of HF. This paper proposes a two-stage decision support system to overcome the over-fitting issue and to optimize the generalization factor. The first stage uses a mutual information based statistical model while the second stage uses a neural network. We applied our approach to the HF subset of publicly available Cleveland heart disease database. Our experimental results show that the proposed decision support system has optimized the generalization capabilities and has reduced the mean percent error (MPE) to 8.8% which is significantly less than the recently published studies. In addition, our model exhibits a 93.33% accuracy rate which is higher than twenty eight recently developed HF risk prediction models that achieved accuracy in the range of 57.85% to 92.31%. We can hope that our decision support system will be helpful to cardiologists if deployed in clinical setup.     

Pulmonary embolism and 3-month outcomes in 4036 patients with venous thromboembolism and chronic obstructive pulmonary disease: data from the RIETE registry

Background

Patients with chronic obstructive pulmonary disease (COPD) have a modified clinical presentation of venous thromboembolism (VTE) but also a worse prognosis than non-COPD patients with VTE. As it may induce therapeutic modifications, we evaluated the influence of the initial VTE presentation on the 3-month outcomes in COPD patients.

Methods

COPD patients included in the on-going world-wide RIETE Registry were studied. The rate of pulmonary embolism (PE), major bleeding and death during the first 3 months in COPD patients were compared according to their initial clinical presentation (acute PE or deep vein thrombosis (DVT)).

Results

Of the 4036 COPD patients included, 2452 (61%; 95% CI: 59.2-62.3) initially presented with PE. PE as the first VTE recurrence occurred in 116 patients, major bleeding in 101 patients and mortality in 443 patients (Fatal PE: first cause of death). Multivariate analysis confirmed that presenting with PE was associated with higher risk of VTE recurrence as PE (OR, 2.04; 95% CI: 1.11-3.72) and higher risk of fatal PE (OR, 7.77; 95% CI: 2.92-15.7).

Conclusions

COPD patients presenting with PE have an increased risk for PE recurrences and fatal PE compared with those presenting with DVT alone. More efficient therapy is needed in this subtype of patients.     

Vagal nerve stimulation protects cardiac injury by attenuating mitochondrial dysfunction in a murine burn injury model

Mitochondria play a central role in the integration and execution of a wide variety of apoptotic signals. In the present study, we examined the deleterious effects of burn injury on heart tissue. We explored the effects of vagal nerve stimulation (VNS) on cardiac injury in a murine burn injury model, with a focus on the protective effect of VNS on mitochondrial dysfunction in heart tissue. Mice were subjected to a 30% total body surface area, full‐thickness steam burn followed by right cervical VNS for 10 min. and compared to burn alone. A separate group of mice were treated with the M₃‐muscarinic acetylcholine receptor (M₃‐AchR) antagonist 4‐DAMP or phosphatidylinositol 3 Kinase (PI3K) inhibitor LY294002 prior to burn and VNS. Heart tissue samples were collected at 6 and 24 hrs after injury to measure changes in apoptotic signalling pathways. Burn injury caused significant cardiac pathological changes, cardiomyocyte apoptosis, mitochondrial swelling and decrease in myocardial ATP content at 6 and 24 hrs after injury. These changes were significantly attenuated by VNS. VNS inhibited release of pro‐apoptotic protein cytochrome C and apoptosis‐inducing factor from mitochondria to cytosol by increasing the expression of Bcl‐2, and the phosphorylation level of Bad (pBad¹³⁶) and Akt (pAkt³⁰⁸). These protective changes were blocked by 4‐DAMP or LY294002. We demonstrated that VNS protected against burn injury–induced cardiac injury by attenuating mitochondria dysfunction, likely through the M₃‐AchR and the PI3K/Akt signalling pathways.     

深部热水硫酸盐还原菌微滴数字PCR检测技术的建立与应用

【背景】地下深部存在一个生物圈,深部沉积岩、玄武岩、花岗岩和变质岩等岩性环境的微生物群落已被调查,而地下深部碳酸盐岩岩溶-裂隙热储层微生物群落特征仍然不清。硫酸盐还原菌(sulfate-reducing bacteria,SRB)是地下深部频繁检出的微生物。【目的】建立快速准确定量深部热水硫酸盐还原菌的微滴数字PCR (droplet digital PCR,ddPCR)技术。【方法】以SRB的功能基因dsrB为检测目标,优化SRB ddPCR技术的退火温度,考察其线性范围、敏感性、重复性和特异性,并将该技术用于实际样品的检测。【结果】SRB ddPCR技术的最佳退火温度为54 °C,检测的线性范围为1.1×100?1.1×105 copies/μL-DNA,相关系数R2为0.996,检出限为1 copy/μL-DNA,重复性的相对标准差优于9%,对3种非SRB人工构建的质粒均没有扩增,显示该技术具有很好的线性关系、敏感性、重复性和特异性。利用该技术对冀中地热区深部热水、浅层水和土壤样品进行了检测,平均含量分别为(4.0±8.4)×103 copies/mL、(1.6±3.5)×102 copies/mL和(1.5±1.2)×103 copies/g-dw。与浅层水和土壤相比,深部热水富含SRB菌。【结论】为了提高地下深部生物圈认识和合理开发利用深部热水,建立了一种快速、灵敏、准确的SRB ddPCR检测技术,同时为其他指示菌检测技术的建立提供了参考。     

Influence of segmental and extra-segmental conditioning stimuli on cortical potentials evoked by painful electrical stimulation

This study evaluated the effects of two different types of segmental/extra-segmental conditioning stimuli (tonic muscle pain and non-painful vibration) on the subjective experience (perceived pain intensity) and on the cortical evoked potentials to standardized test stimuli (cutaneous electrical stimuli). Twelve subjects participated in two separate sessions to investigate the effects of tonic muscle pain or cutaneous vibration on experimental test stimuli. The experimental protocol contained a baseline registration (test stimuli only), a registration with the test stimuli in combination with the conditioning stimuli, followed by a registration with the test stimuli only. In addition, the effects of the conditioning stimuli were examined at two anatomically separated locations (segmental and extra-segmental). Compared with the test stimulus alone, the perceived pain intensity and peak-to-peak amplitudes of the evoked potentials were unchanged in the presence of non-painful conditioning stimuli at either location. In contrast, a significant decrease of the perceived pain intensity and peak-to-peak amplitudes was found in the presence of painful conditioning stimuli at the extra-segmental sites. Moreover, the topographic maps of the 32-channel recordings suggested that the distribution of the scalp evoked potentials was almost symmetrical around the vertex Cz in the baseline registration. The evoked potentials were generally decreased during hypertonic saline infusion at the extra-segmental sites, but the distribution of the topographic maps did not appear to change. Vibration has previously been shown to inhibit pain, but in the present study the perceived intensity of phasic painful electrical stimuli was unchanged. The reduced perceived pain intensity and the smaller peak-to-peak amplitude of the evoked potential in the presence of extra-segmental conditioning pain are in accordance with the concept of diffuse noxious inhibitory control.     

关节置换术后抗凝药物预防深静脉血栓及相关并发症的临床研究进展

抗凝药物有助于预防全髋关节置换术和全膝关节置换术后深静脉血栓形成,临床上最常使用的传统抗凝药物如低分子肝素、华法林等可以起到很好的预防效果。目前有一类新的口服抗凝药物已经用于临床,为关节置换术后患者带来了一种更方便、安全和有效预防血栓的治疗选择。本篇综述主要针对传统抗凝药物低分子肝素及维生素K拮抗剂,直接凝血酶抑制剂达比加群,以及选择性Xa因子抑制剂利伐沙班和阿哌沙班,对迄今为止传统抗凝药物在全髋关节置换术和全膝关节置换术患者中的临床使用经验、优缺点、以及新型口服抗凝药物最新临床用药进展进行综述,为关节置换术后患者预防深静脉血栓提供用药参考。