scholarly journals Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification

2021 ◽  
Vol 11 (2) ◽  
pp. 514
Author(s):  
Jui-Jen Chen ◽  
Ting-Yi Su ◽  
Wei-Shiang Chen ◽  
Yen-Hsiang Chang ◽  
Henry Horng-Shing Lu
Keyword(s):  
Neural Network ◽  
Myocardial Perfusion ◽  
Convolutional Neural Network ◽  
Heart Diseases ◽  
Chang Gung Memorial Hospital ◽  
Prototype System ◽  
Coronary Heart Diseases ◽  
Spect Myocardial Perfusion ◽  
Area Of Interest ◽  
Czt Spect

This study analyzes CZT SPECT myocardial perfusion images that are collected at Chang Gung Memorial Hospital, Kaohsiung Medical Center in Kaohsiung. This study focuses on the classification of myocardial perfusion images for coronary heart diseases by convolutional neural network techniques. In these gray scale images, heart blood flow distribution contains the most important features. Therefore, data-driven preprocessing is developed to extract the area of interest. After removing the surrounding noise, the three-dimensional convolutional neural network model is utilized to classify whether the patient has coronary heart diseases or not. The prediction accuracy, sensitivity, and specificity are 87.64%, 81.58%, and 92.16%. The prototype system will greatly reduce the time required for physician image interpretation and write reports. It can assist clinical experts in diagnosing coronary heart diseases accurately in practice.

Evolutionary Algorithm-based Convolutional Neural Network for Predicting Heart Diseases

2021 ◽  
pp. 107651
Author(s):  
Ali A. Samir ◽  
Abdullah R. Rashwan ◽  
Karam M. Sallam ◽  
Ripon K. Chakrabortty ◽  
Michael J. Ryan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Evolutionary Algorithm ◽  
Heart Diseases

scholarly journals A Convolutional Neural Network Combining Discriminative Dictionary Learning and Sequence Tracking for Left Ventricular Detection

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3693
Author(s):  
Xuchu Wang ◽  
Fusheng Wang ◽  
Yanmin Niu
Keyword(s):  
Neural Network ◽  
Left Ventricle ◽  
Convolutional Neural Network ◽  
Dictionary Learning ◽  
Heart Diseases ◽  
Volume Measurement ◽  
Blood Pool ◽  
Left Ventricular ◽  
Data Set ◽  
Discriminative Dictionary Learning

Cardiac MRI left ventricular (LV) detection is frequently employed to assist cardiac registration or segmentation in computer-aided diagnosis of heart diseases. Focusing on the challenging problems in LV detection, such as the large span and varying size of LV areas in MRI, as well as the heterogeneous myocardial and blood pool parts in LV areas, a convolutional neural network (CNN) detection method combining discriminative dictionary learning and sequence tracking is proposed in this paper. To efficiently represent the different sub-objects in LV area, the method deploys discriminant dictionary to classify the superpixel oversegmented regions, then the target LV region is constructed by label merging and multi-scale adaptive anchors are generated in the target region for handling the varying sizes. Combining with non-differential anchors in regional proposal network, the left ventricle object is localized by the CNN based regression and classification strategy. In order to solve the problem of slow classification speed of discriminative dictionary, a fast generation module of left ventricular scale adaptive anchors based on sequence tracking is also proposed on the same individual. The method and its variants were tested on the heart atlas data set. Experimental results verified the effectiveness of the proposed method and according to some evaluation indicators, it obtained 92.95% in AP50 metric and it was the most competitive result compared to typical related methods. The combination of discriminative dictionary learning and scale adaptive anchor improves adaptability of the proposed algorithm to the varying left ventricular areas. This study would be beneficial in some cardiac image processing such as region-of-interest cropping and left ventricle volume measurement.

scholarly journals Design and Implementation of Opportunity Signal Perception Unit Based on Time-Frequency Representation and Convolutional Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7871
Author(s):  
Zhongliang Deng ◽  
Hang Qi ◽  
Yanxu Liu ◽  
Enwen Hu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Utilization Efficiency ◽  
Prototype System ◽  
Positioning System ◽  
Signal Recognition ◽  
Positioning Systems ◽  
Time Frequency ◽  
Signal Perception

The traditional signal of opportunity (SOP) positioning system is equipped with dedicated receivers for each type of signal to ensure continuous signal perception. However, it causes a low equipment resources utilization and energy waste. With increasing SOP types, problems become more serious. This paper proposes a new signal perception unit for SOP positioning systems. By extracting the perception function from the positioning system and operating independently, the system can flexibly schedule resources and reduce waste based on the perception results. Through time-frequency joint representation, time-frequency image can be obtained which provides more information for signal recognition, and is difficult for traditional single time/frequency-domain analysis. We also designed a convolutional neural network (CNN) for signal recognition and a negative learning method to correct the overfitting to noisy data. Finally, a prototype system was built using USRP and LabVIEW for a 2.4 GHz frequency band test. The results show that the system can effectively identify Wi-Fi, Bluetooth, and ZigBee signals at the same time, and verified the effectiveness of the proposed signal perception architecture. It can be further promoted to realize SOP perception in almost full frequency domain, and improve the integration and resource utilization efficiency of the SOP positioning system.

scholarly journals Intellectual heartbeats classification model for diagnosis of heart disease from ECG signal using hybrid convolutional neural network with GOA

2021 ◽  
Vol 3 (2) ◽  
Author(s):  
Ankita Tyagi ◽  
Ritika Mehra
Keyword(s):  
Neural Network ◽  
Heart Disease ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Heart Diseases ◽  
Classification Model ◽  
Ecg Signal ◽  
Grasshopper Optimization Algorithm ◽  
Grasshopper Optimization ◽  
Selection Of

AbstractAutomatic heart disease detection from human heartbeats is a challenging and intellectual assignment in signal processing because periodically monitoring of the heart beat arrhythmia for patient is an essential task to reduce the death rate due to cardiovascular disease (CVD). In this paper, the focus of research is to design hybrid Convolutional Neural Network (CNN) architecture by making use of Grasshopper Optimization Algorithm (GOA) to classify different types of heart diseases from the ECG signal or human heartbeats. Convolutional Neural Network (CNN) as an artificial intelligence approach is widely used in computer vision-based medical data analysis. However, the traditional CNN cannot be used for classification of heart diseases from the ECG signal because lots of noise or irrelevant data is mixed with signal. So this study utilizes the pre-processing and selection of feature for proper heart diseases classification, where Discrete Wavelet Transform (DWT) is used for the noise reduction as well as segmentation of ECG signal and Grasshopper Optimization Algorithm (GOA) is used for selection of R-peaks features from the extracted feature sets in terms of R-peaks and R-R intervals that help to attain better classification accuracy. For training as well as testing of projected Heartbeats Classification Model (HCM), the Standard MIT-BIH arrhythmia database is utilized with hybrid Convolutional Neural Network (CNN) architecture. The assortment of proper R-peaks and R-R intervals is a major factor and because of the deficiency of apposite pre-processing phases like noise removal, signal decomposition, smoothing and filtering, the uniqueness of extracted feature is less. The experimental outcomes show that the planned HCM is effective for detecting irregular human heartbeats via R-peaks and R-R intervals. When the proposed Heartbeats Classification Model (HCM) was verified on the database, model achieved higher efficiency than other state-of-the-art techniques for 16 heartbeat disease categories and the average classification accuracy is 99.58% with fast and robust responses where the correctly classified heartbeats are 86,005 and misclassified beats is only 108 with 0.42% error rate.

scholarly journals Eliminating artefacts in polarimetric images using deep learning

2019 ◽  
Vol 491 (4) ◽  
pp. 5151-5157
Author(s):  
D Paranjpye ◽  
A Mahabal ◽  
A N Ramaprakash ◽  
G V Panopoulou ◽  
K Cleary ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Wide Field ◽  
True Positive ◽  
True Negative ◽  
Polarization Measurements ◽  
Area Of Interest ◽  
Near Future

ABSTRACT Polarization measurements done using Imaging Polarimeters such as the Robotic Polarimeter are very sensitive to the presence of artefacts in images. Artefacts can range from internal reflections in a telescope to satellite trails that could contaminate an area of interest in the image. With the advent of wide-field polarimetry surveys, it is imperative to develop methods that automatically flag artefacts in images. In this paper, we implement a Convolutional Neural Network to identify the most dominant artefacts in the images. We find that our model can successfully classify sources with 98 per cent true positive and 97 per cent true negative rates. Such models, combined with transfer learning, will give us a running start in artefact elimination for near-future surveys like WALOP.

scholarly journals Implementasi Convolutional Neural Network Untuk Deteksi Nyeri Bayi Melalui Citra Wajah Dengan YOLO

2021 ◽  
Vol 5 (4) ◽  
pp. 624-630
Author(s):  
Tomy Abuzairi ◽  
Nurdina Widanti ◽  
Arie Kusumaningrum ◽  
Yeni Rustina
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Facial Expressions ◽  
Pain Assessment ◽  
Psychological Trauma ◽  
Prototype System ◽  
Average Value ◽  
The Future ◽  
Attention To Pain ◽  
Pain Responses

Pain in a baby is difficult to detect is because the method for detecting pain is self-reporting even though babies themselves still cannot describe the pain verbally, then by observing changes in behavior in the form of facial expressions. Statistically, it is also recorded that about 80% of the world's population pays less attention to pain assessment, especially for children, even though this pain gives children a bad experience so that it can interfere with pain responses in the future or psychological trauma. Based on these problems, a prototype system was made using the NVIDIA Jetson Nano Developer kit to help detect pain, especially in infants 0-12 months by using the Convolutional Neural Network (CNN) model with the PyTorch framework and the You Only Look Once (YOLO) algorithm with three detection classification is sad, neutral and sick. From the results of the study, it was found that the YOLO algorithm was able to detect the three classifications with a sad mAP value of 77.8%, neutral 76.7%, in pain 68.9%. With a precision value of 71.4%, recall 62.5% and f1-score 66.6%. The average value of Confidence is 53.57%.

Sign in / Sign up

Export Citation Format

Share Document