Cardiac arrhythmia is associated with abnormal electrical activities of the heart, which can be reflected by altered characteristics electrocardiogram (ECG). Due to simplicity and non-invasive nature, ECG has been widely used for detecting arrhythmias there an urgent need automatic detection. Up date, some algorithms have proposed classification cardiac based on features ECG; however, their stratification rate still poor due unreliable signal or limited generalization capability classifier,...

Atrial fibrillation (AF) is the most common cardiac arrhythmias causing morbidity and mortality. AF may appear as episodes of very short (i.e., proximal AF) or sustained duration persistent AF), either form which causes irregular ventricular excitations that affect global function heart. It an unmet challenge for early automatic detection AF, limiting efficient treatment strategies AF. In this study, we developed a new method based on continuous wavelet transform 2D convolutional neural...

Objective: Detecting changes in the QRS complexes ECG signals is regarded as a straightforward, noninvasive, inexpensive, and preliminary diagnosis approach for evaluating cardiac health of patients. Therefore, detecting must be accurate over short times. However, reliability automatic detection restricted by all kinds noise complex signal morphologies. The objective this paper to address complexes. Methods: In paper, we proposed new algorithm using dual channels based on U-Net bidirectional...

Cardiovascular diseases are associated with high morbidity and mortality. However, it is still a challenge to diagnose them accurately efficiently. Electrocardiogram (ECG), bioelectrical signal of the heart, provides crucial information about dynamical functions playing an important role in cardiac diagnosis. As QRS complex ECG ventricular depolarization, therefore, accurate detection vital for interpreting features. In this paper, we proposed real-time, accurate, effective algorithm...

Abstract Objective This study was undertaken to develop a deep learning framework that can classify and segment interictal epileptiform discharges (IEDs) in multichannel electroencephalographic (EEG) recordings with high accuracy, preserving both spatial information interchannel interactions. Methods We proposed novel framework, U‐IEDNet, for detecting IEDs EEG. The U‐IEDNet employs convolutional layers bidirectional gated recurrent units as temporal encoder extract features from...

Abstract Over the past few decades, number of patients with neurological diseases has increased significantly, posing huge challenges and opportunities for development brain imaging technology. As a hybrid method combining optical excitation acoustic detection techniques, photoacoustic tomography (PAT), experienced rapid development, due to high contrast spatial resolution at depth inside tissues. With lasers, ultrasonic detectors, data computations, PAT been widely applied diagnosis...

Medical imaging provides a powerful tool for medical diagnosis. In the process of computer-aided diagnosis and treatment liver cancer based on imaging, accurate segmentation region from abdominal CT images is an important step. However, due to defects tissue limitations procession, gray level in image heterogeneous, boundary between those adjacent tissues organs blurred, which makes extremely difficult task. this study, aiming at solving problem low accuracy original 3D U-Net network,...

Beat-by-beat arrhythmia detection in ambulatory electrocardiogram (ECG) monitoring is critical for the evaluation and prognosis of cardiac arrhythmias, however, it a highly professional demanding time-consuming task. Current methods automatic beat-by-beat suffer from poor generalization ability due to lack large-sample finely-annotated (labels are given each beat) ECG data model training. In this work, we propose weakly supervised deep learning framework (WSDL-AD), which permits training...

The shortage of annotated ECG data presents a significant impediment, hampering the overall generalization capabilities machine learning models tailored for automated classification. collective integration multisource datasets potential remedy this challenge. However, it is crucial to underscore that mere addition supplementary does not automatically guarantee performance enhancement, given unresolved challenges associated with data. In research, we address one such challenge, namely, issue...

Due to the increasing life pressure in modern society, more and people are suffering from sleep disorders.The most serious case of disorders called apnea is characterized by a complete breaking block, leading awakening subsequent disturbances.However, great obstacles still exist automatic identification arousals.In this study, novel method was developed detect non-apnea sources arousals during using several physiological signals.In dataset provided, duration arousal regions much less than...

The physiological signals such as the electrocardiogram (ECG) and arterial blood pressure (ABP) in ICU are often severely corrupted by noise, artifact missing data, producing large errors estimation of characteristics values, leading to false alarms ICU. In order solve this problem, we started with signal quality assessment vital intensive care patients using a derived index (SQI) reveal degree quality. And then use SQI-weighted residual error Kalman filters (KF) complete date fusion for...

Automatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, multi-label task owing to coexistence different kinds diseases, challenging due large number possible label combinations imbalance among categories. Furthermore, ECG cost-sensitive, fact that has usually been ignored in previous studies on development model. To address these problems, this work, we propose novel deep...

Introduction: Melanogenesis, the process responsible for melanin production, is a critical determinant of skin pigmentation. Dysregulation this can lead to hyperpigmentation disorders. Method: In study, we identified novel Reed Rhizome extract, (1'S, 2'S)-syringyl glycerol 3'-O-β-D-glucopyranoside (compound 5), and evaluated its anti-melanogenic potential in zebrafish models vitro assays. Compound 5 inhibited synthesis by 36.66% ± 14.00% tyrosinase vivo 48.26% 6.94%, surpassing inhibitory...

Heart sounds reflect information of the mechanical contraction heart in both physiological and pathological conditions.It is important to develop novel numerical algorithms characterize features sound as a helpful diagnostic tool cardiovascular diseases.This study aims an efficient algorithm for analyzing signals that can be used disease monitoring.In algorithms, wavelet analysis (coif5) with 5 decomposition levels was first applied noise eliminating by using soft fixed threshold.Then, were...

Heart failure (HF) is associated with an increased propensity for atrial fibrillation (AF), causing higher mortality than AF or HF alone. It hypothesized that HF-induced remodelling of cellular and tissue properties promotes the genesis action potential (AP) alternans conduction perpetuate AF. However, mechanism underlying susceptibility to in remains incompletely elucidated. In this study, we investigated effects how electrophysiological (with prolonged AP duration) structural (reduced...

Objective: To design and build up a computer-aided color matching system for porcelain tooth, which could offer dentists an objective suggestion selecting the of patient's tooth. Methods: The is mainly based on image analyzing processing techniques pattern recognition methods. This uses HSI space to compare calculate colors. consists five parts, are acquisition facility, part, tooth classification module, mixture module template library. technology find out image's feature then look it in...

Early diagnosis of Atrial Fibrillation (AF) could be benefited from automatic analysis a short single-lead ECG recording that can collected easily by portable device.Due to the limitations both quantity and quality signal, it is challenging distinguish AF broad taxonomy rhythms.This paper presents new method which classifies recordings single lead ECGs combined time time-frequency features.The features are represented some characteristics its RR intervals Poincare plot, while extracted...

Aims: Over the last decade, many attempts have been implemented for automatic detection of cardiac arrhythmias, however, their performances are still not ideal due to unreliable extracted features designed models or limited small public datasets.In this study, we investigate arrhythmias from 12lead electrocardiogram (ECG) recordings using an attention-based Res-BiGRU model.Methods: We train a deep neural networks (DNNs) identify eight types arrhythmias.The constructed model contains residual...