Automatic 12-Leading Electrocardiogram Classification Network with Deformable Convolution.

Electrocardiogram (ECG) is an electrical signal that helps monitor the physiology of the heart. A complete ECG record includes 12 leads, each reflecting features from a different angle of the heart. In recent years, various deep learning algorithms, especially convolutional neural networks (CNN), have been applied to detect ECG features. However, the conventional CNN can only extract the local features and cannot extract the data correlation across the leads of ECG. Based on deformable convolution networks (DCN), this article proposes a new neural network structure (DCNet) to detect ECG features. The network architecture consists of four DCN blocks and a classification layer. For the ECG classification task, in a DCN block, the combination of normal convolution and deformable convolution with better effect was testified by the experiments. Based on the feature learning capability of DCN, the architecture can better extract the characteristics between leads. Using the public 12-leading ECG data in CPSC-2018, the diagnostic accuracy of this architecture is the highest, reaching 86.3%, which is superior to other common network architectures with good results in ECG signal classification.Clinical relevance-In this paper, we proposed an effective automatic ECG classification model that can reduce medical staff workload.

4-Nonylphenol effects on rat testis and sertoli cells determined by spectrochemical techniques coupled with chemometric analysis.

Herein, vibrational spectroscopy has been applied for qualitative identification of biomolecular alterations that occur in cells and tissues following chemical treatment. Towards this end, we combined attenuated total reflection Fourier-transform infrared (ATR-FTIR) and Raman spectroscopy to assess testicular toxicology after 4-nonylphenol (NP) exposure, an estrogenic endocrine disruptor affecting testicular function in rats and other species. Rats aged 21, 35 or 50 days received NP at intra-peritoneal doses of 0, 25, 50 or 100 mg/kg for 20 consecutive days. Primary Sertoli cells (SCs) were treated with NP at various concentrations (0, 2.5, 5, 10 or 20 µM) for 12 h. Post-exposure, testicular cells, interstitial tissue and SCs were interrogated respectively using spectrochemical techniques coupled with multivariate analysis. Distinct biomolecular segregation between the NP-exposed samples vs. control were observed based on infrared (IR) spectral regions of 3200-2800 cm-1 and 1800-900 cm-1, and the Raman spectral region of 1800-900 cm-1. For in vivo experiments, the main wavenumbers responsible for segregation varied significantly among the three age classes. The main IR and Raman band differences between NP-exposed and control groups were observed for Amide (proteins), lipids and DNA/RNA. An interesting finding was that the peptide aggregation level, Amide Ӏ-to-Amide II ratio, and phosphate-to-carbohydrate ratio were considerably reduced in ex vivo NP-exposed testicular cells or SCs in vitro. This study demonstrates that ATR-FTIR and Raman spectroscopy techniques can be applied towards analysing NP-induced testicular biomolecular alterations.

Simultaneous quantitation of carbohydrate antigen 125 and carcinoembryonic antigen in human serum via time-resolved fluoroimmunoassay.

In clinical diagnosis of cancer, immunology assay with single tumor marker often lead to a false and missed inspection. A quantitative method with a high degree of accuracy, sensitivity, and effectiveness is required for its diagnosis. We developed a dual-label time-resolved fluoroimmunoassay (TRFIA) to simultaneously detect carbohydrate antigen 125 (CA125) and carcinoembryonic antigen (CEA) in human serum to aid the diagnosis and prognosis of gastric cancer. The method was based on a microplate sandwich immunoassay using europium-labeled anti-CA125 antibodies and samarium-labeled anti-CEA antibodies as fluorescent reporters. The assay detection range was widely, and the limit of detection was sufficiently for detecting clinical sample. The intra- and inter-assay coefficients of variation were below 6%, and recoveries ranged from 90% to 110%. No significant statistical difference in sensitivity or specificity was observed between dual label-TRFIA and commercial chemiluminescent immunoassays in serum samples. These results demonstrate the successful development of an effective, reliable, and convenient novel TRFIA method for the simultaneous detection of CA125 and CEA, which can be used for clinical blood screening to monitor the occurrence and development of tumors to facilitate early treatment.

The fluorescence bioassay platforms on quantum dots nanoparticles.

In this paper, we present the optical properties and the platforms on fluorescent quantum dots for biological labeling, biomedical engineering and biosensor in molecular imaging. Quantum dots possess several properties that make them very attractive for fluorescent tagging: broad excitation spectrum, narrow emission spectrum, precise tunability of their emission peak, longer fluorescence lifetime than organic fluorophores and negligible photobleaching. We describe how to take such advantages of quantum dots to develop the technology and employ it to build assay platforms. Finally, ultrasensitivity, multicolor, and multiplexing of the technology of semiconductor quantum dots open up promising and interesting possibilities for bioassay platform.