Development of an approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms.

Purpose: In stable coronary artery disease (CAD), reduction in mortality and/or myocardial infarction with revascularization over medical therapy has not been reliably achieved. Coronary arteries are usually extracted to perform stenosis detection. As such, developing accurate segmentation of vascular structures and quantification of coronary arterial stenosis in invasive coronary angiograms (ICA) is necessary. Approach: A multi-input and multiscale (MIMS) U-Net with a two-stage recurrent training strategy was proposed for the automatic vessel segmentation. The proposed model generated a refined prediction map with the following two training stages: (i) stage I coarsely segmented the major coronary arteries from preprocessed single-channel ICAs and generated the probability map of arteries; and (ii) during the stage II, a three-channel image consisting of the original preprocessed image, a generated probability map, and an edge-enhanced image generated from the preprocessed image was fed to the proposed MIMS U-Net to produce the final segmentation result. After segmentation, an arterial stenosis detection algorithm was developed to extract vascular centerlines and calculate arterial diameters to evaluate stenotic level. Results: Experimental results demonstrated that the proposed method achieved an average Dice similarity coefficient of 0.8329, an average sensitivity of 0.8281, and an average specificity of 0.9979 in our dataset with 294 ICAs obtained from 73 patients. Moreover, our stenosis detection algorithm achieved a true positive rate of 0.6668 and a positive predictive value of 0.7043. Conclusions: Our proposed approach has great promise for clinical use and could help physicians improve diagnosis and therapeutic decisions for CAD.

Analyze Informant-Based Questionnaire for The Early Diagnosis of Senile Dementia Using Deep Learning.

OBJECTIVE: This paper proposes a multiclass deep learning method for the classification of dementia using an informant-based questionnaire. METHODS: A deep neural network classification model based on Keras framework is proposed in this paper. To evaluate the advantages of our proposed method, we compared the performance of our model with industry-standard machine learning approaches. We enrolled 6,701 individuals, which were randomly divided into training data sets (6030 participants) and test data sets (671 participants). We evaluated each diagnostic model in the test set using accuracy, precision, recall, and F1-Score. RESULTS: Compared with the seven conventional machine learning algorithms, the DNN showed higher stability and achieved the best accuracy with 0.88, which also showed good results for identifying normal (F1-score = 0.88), mild cognitive impairment (MCI) (F1-score = 0.87), very mild dementia (VMD) (F1-score = 0.77) and Severe dementia (F1-score = 0.94). CONCLUSION: The deep neural network (DNN) classification model can effectively help doctors accurately screen patients who have normal cognitive function, mild cognitive impairment (MCI), very mild dementia (VMD), mild dementia (Mild), moderate dementia (Moderate), and severe dementia (Severe).

Effects of aripiprazole on the QTc: a case report.

The use of neuroleptics in the elderly has been a topic of debate since 2005 when the US Food and Drug Administration issued a black-box warning of increased risk of mortality in elderly patients with dementia-related psychosis. Antipsychotic alternatives such as divalproex are sometimes favored on an "off-label" basis to manage agitation in the demented elderly, and antipsychotic use is often clinically necessary to treat psychosis in older adults, with or without dementia. Concurrently, risk for iatrogenic corrected QT (QTc) prolongation on electrocardiogram (ECG) remains a concern with the use of many antipsychotic agents because of its associated potential for fatal arrhythmias.

Pharmacological treatments of non-substance-withdrawal delirium: a systematic review of prospective trials.

OBJECTIVE: Most reviews of pharmacological strategies for delirium treatment evaluate the effectiveness of these interventions for delirium prevention, reduction in duration and severity of ongoing delirium, and other outcomes that extend beyond the recommendations of expert treatment guidelines. However, little if any attention is given to substantiating the potential benefits of such treatment or addressing the methodological weaknesses that, in part, limit the pharmacological recommendations made by expert treatment guidelines. Therefore, the authors conducted a systematic review to provide the most up-to-date and inclusive review of published prospective trials of potential pharmacological interventions for the prevention and treatment of delirium, and they discuss potential benefits of pharmacological prevention of delirium and/or reduction of ongoing delirium episode duration and severity. METHOD: The analysis followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, including prospective randomized and nonrandomized double-blind, single-blind, and open-label clinical trials of any pharmacological agent for the prevention or treatment of delirium and reviewing them systematically for effectiveness on several predefined outcomes. RESULTS: The pharmacological strategies reviewed showed greater success in preventing delirium than in treating it. Significant delirium prevention effects are associated with haloperidol, second-generation antipsychotics, iliac fascia block, gabapentin, melatonin, lower levels of intraoperative propofol sedation, and a single dose of ketamine during anesthetic induction and with dexmedetomidine compared with other sedation strategies for mechanically ventilated patients. CONCLUSIONS: These promising results warrant further study with consideration of the methodological weaknesses and inconsistencies of studies to date.

Electroconvulsive therapy (ECT) for catatonia in a patient with schizophrenia and synthetic cannabinoid abuse: a case report.

We present the case of a young man with a long-standing history of schizophrenia who presented with severe and life-threatening catatonia in the setting of synthetic cannabis use who was successfully treated with electroconvulsive therapy. To our knowledge, this is the first reported case of severe and persistent catatonia in the setting of synthetic cannabis use and the first documented successful treatment.

A preliminary investigation of the efficacy of riparian fencing schemes for reducing contributions from eroding channel banks to the siltation of salmonid spawning gravels across the south west UK.

The low productivity of salmonids in many river systems across the UK is testament to their intolerance of water quality perturbations including those associated with excessive sedimentation. Catchment and fishery managers concerned with combating such issues require reliable information on the key sources of the sediment problem to target management and on the efficacy of the mitigation options being implemented. In recognition of the latter requirement, a pre- and post-remediation sediment sourcing survey was used to examine the potential for using sediment tracing to assemble preliminary information on the efficacy of riparian fencing schemes for reducing sediment contributions from eroding channel banks to salmonid spawning gravels in the Rivers Camel, Fal, Lynher, Plym, Tamar and Tavy in the south west of the UK. Respective estimates of the overall mean proportion (+/-95% confidence limits) of the interstitial sediment input to salmonid spawning gravels originating from eroding channel banks during the pre- (1999-2000) and post-remediation (2008-2009) study periods were computed at 97+/-1% vs. 69+/-1%, 94+/-1% vs. 91+/-1%, 12+/-1% vs. 10+/-1%, 92+/-1% vs. 34+/-1%, 31+/-1% vs. 16+/-1% and 90+/-1% vs. 66+/-1%. Whilst the study demonstrates the potential utility of the fingerprinting approach for helping to assemble important information on the efficacy of bank fencing as a sediment source control measure at catchment scale, a number of limitations of the work and some suggestions for improving experimental design are discussed. Equivalent data are urgently required for many sediment mitigation options to help inform the development of water quality policy packages designed to protect aquatic ecosystems.

Effect of surface material on electrostatic charging of houseflies (Musca domestica L).

Houseflies (Musca domestica L) accumulated electrostatic charges when walking over clean, uncharged dielectric surfaces. The charges elicited on a walking housefly by a range of materials were quantified, allowing a triboelectric series to be determined relative to M domestica. This ranged from surfaces that charged individuals positively, e.g. Correx (corrugated polypropylene) [.1 (+/- 4.2)pC], to those that applied a negative charge, e.g. clear cast acrylic [-14.9 (+/- 2.9)pC]. Maximum positive and negative charges accumulated by individual M domestica were +73 and -27 pC. Replicate measurements on the same fly and surface showed little variation. Variation between individuals was not related to sex and was not consistent between surfaces. Different materials charged M domestica significantly differently and individual flies had significantly different charging properties. Variation in temperature between 21.3 degrees C and 24.7 degrees C and humidity between 24% and 41% RH significantly affected charge accumulated by M domestica on some surfaces, although further experimentation is needed to confirm this. The implications of this work are discussed in relation to insect trap design and pollination biology.