Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi
-
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi · Jun 2019
[Automatic classification method of arrhythmia based on discriminative deep belief networks].
Existing arrhythmia classification methods usually use manual selection of electrocardiogram (ECG) signal features, so that the feature selection is subjective, and the feature extraction is complex, leaving the classification accuracy usually affected. Based on this situation, a new method of arrhythmia automatic classification based on discriminative deep belief networks (DDBNs) is proposed. The morphological features of heart beat signals are automatically extracted from the constructed generative restricted Boltzmann machine (GRBM), then the discriminative restricted Boltzmann machine (DRBM) with feature learning and classification ability is introduced, and arrhythmia classification is performed according to the extracted morphological features and RR interval features. ⋯ For training sets and test sets with inconsistent data sources, a small number of training sets are extended by the active learning (AL) method, and the overall classification accuracy of the method is up to 99.31% ± 0.23%. The experimental results show the effectiveness of the method in arrhythmia automatic feature extraction and classification. It provides a new solution for the automatic extraction of ECG signal features and classification for deep learning.
-
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi · Dec 2016
[Application of (18)F-fluorodeoxyglucose Metabolic Imaging in Diagnosis and Treatment of Cervical Cancer].
The main purpose of this study is to evaluate the clinical value of 18F-fluorodeoxyglucose（18 F-FDG）metabolism imaging in accurate staging and prognosis prediction before treatment of cervical cancer.18F-FDG single photon emission computed tomography（SPECT/CT）was performed before treatment on 27 patients with cervical cancer and was analyzed retrospectively. All the images were analyzed by image fusion software. Meanwhile,primary tumor size and T/B,lymph nodes size and T/B were measured by software. ⋯ There were positive correlation between invasion of uterine body and lymph nodes metastasis（P<0.05）. In conclusion,18F-FDG imaging has an obvious value for the diagnosis of outside pelvic and distant lymph node metastasis,uterine body infiltrated,and accurate staging. Primary focal T/B value of cervical cancer associates with the clinical stage,which can reflect the risk of patients,and were useful to preliminarily predict the prognosis of cervical cancer.
-
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi · Oct 2016
[Analysis of the Characteristics of Infantile Small World Neural Network Node Properties Correlated with the Influencing Factors].
We applied resting-state functional magnetic resonance imaging(rfMRI)combined with graph theory to analyze 90 regions of the infantile small world neural network of the whole brain. We tried to get the following two points clear:1 whether the parameters of the node property of the infantile small world neural network are correlated with the level of infantile intelligence development;2 whether the parameters of the infantile small world neural network are correlated with the children’s baseline parameters,i.e.,the demographic parameters such as gender,age,parents’ education level,etc. Twelve cases of healthy infants were included in the investigation(9males and 3females with the average age of 33.42±8.42 months.)We then evaluated the level of infantile intelligence of all the cases and graded by Gesell Development Scale Test. ⋯ The node attributes of small world neural network are widely related to infantile intelligence level,moreover the distribution is characteristic in different encephalic regions. The distribution of dominant encephalic is in accordance the related functions. The existing correlations reflect the ever changing small world nervous network during infantile development.
-
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi · Aug 2016
[Design and Implementation of a Medical Nitric Oxide Flow Control Device].
Medical nitric oxide(NO)flow control system plays an important role in lowering pulmonary hypertension. The design requirements,overall scheme,delivery system and hardware circuits of a medical NO flow control system were introduced in this paper. Particularly,we proposed the design of NO delivery system and hardware circuits in detail. ⋯ The system can adjust and monitor the inhaled nitric oxide concentrations and send out sound and light alarms when the inhaled nitric oxide concentrations are out of the set range. To validate reliability and efficacy,we measured specifications such as linearity,stability and response time of the proposed NO flow control system by continuously administering nitric oxide into inspiratory circuit to deliver nitric oxide of variable concentrations to a test lung. The experiments showed that these specifications can meet the desired requirements.
-
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi · Oct 2015
[Research on the Method of Blood Pressure Monitoring Based on Multiple Parameters of Pulse Wave].
In order to improve the accuracy of blood pressure measurement in wearable devices, this paper presents a method for detecting blood pressure based on multiple parameters of pulse wave. Based on regression analysis between blood pressure and the characteristic parameters of pulse wave, such as the pulse wave transit time (PWTT), cardiac output, coefficient of pulse wave, the average slope of the ascending branch, heart rate, etc. we established a model to calculate blood pressure. For overcoming the application deficiencies caused by measuring ECG in wearable device, such as replacing electrodes and ECG lead sets which are not convenient, we calculated the PWTT with heart sound as reference (PWTT(PCG)). ⋯ The experiment results showed that it was feasible to calculate the PWTT from PWTT(PCG). The mean measurement error of the systolic and diastolic blood pressure calculated by the model based on multiple parameters of pulse wave is 1.62 mm Hg and 1.12 mm Hg, increased by 57% and 53% compared to those of the model based on simple parameter. This method has more measurement accuracy.