scholarly journals Advances in Classifying the Stages of Diabetic Retinopathy Using Convolutional Neural Networks in Low Memory Edge Devices

2021 ◽  
Author(s):  
Aditya Jyoti Paul
Keyword(s):  
Neural Network ◽  
Risk Factors ◽  
Neural Networks ◽  
Diabetic Retinopathy ◽  
Recent Literature ◽  
Vision Impairment ◽  
Huge Number ◽  
Hard Exudates ◽  
Two Stages ◽  
Macular Ischemia

Diabetic Retinopathy (DR) is a severe complication that may lead to retinal vascular damage and is one of the leading causes of vision impairment and blindness. DR broadly is classified into two stages - non-proliferative (NPDR), where there are almost no symptoms, except a few microaneurysms, and proliferative (PDR) involving a huge number of microaneurysms and hemorrhages, soft and hard exudates, neo-vascularization, macular ischemia or a combination of these, making it easier to detect. More specifically, DR is usually classified into five levels, labeled 0-4, from 0 indicating no DR to 4 which is most severe. This paper firstly presents a discussion on the risk factors of the disease, then surveys the recent literature on the topic followed by examining certain techniques which were found to be highly effective in improving the prognosis accuracy. Finally, a convolutional neural network model is proposed to detect all the stages of DR on a low-memory edge microcontroller. The model has a size of just 5.9 MB, accuracy and F1 score both of 94% and an inference speed of about 20 frames per second.

scholarly journals Deep Neural Network for Predicting Diabetic Retinopathy from Risk Factors

Mathematics ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1620 ◽  
Author(s):  
Ganjar Alfian ◽  
Muhammad Syafrudin ◽  
Norma Latif Fitriyani ◽  
Muhammad Anshari ◽  
Pavel Stasa ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Risk Factors ◽  
Diabetic Retinopathy ◽  
Prediction Model ◽  
Deep Neural Network ◽  
Early Stage ◽  
Individual Risk ◽  
Proposed Model ◽  
Individual Risk Factors

Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.

scholarly journals Fast and Accurate Algorithm for ECG Authentication Using Residual Depthwise Separable Convolutional Neural Networks

2020 ◽  
Vol 10 (9) ◽  
pp. 3304 ◽  
Author(s):  
Eko Ihsanto ◽  
Kalamullah Ramli ◽  
Dodi Sudiana ◽  
Teddy Surya Gunawan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Feature Extraction ◽  
Processing Speed ◽  
State Of The Art ◽  
Ecg Signal ◽  
Biometric Authentication ◽  
Beat Detection ◽  
Two Stages ◽  
Electrocardiogram Ecg

The electrocardiogram (ECG) is relatively easy to acquire and has been used for reliable biometric authentication. Despite growing interest in ECG authentication, there are still two main problems that need to be tackled, i.e., the accuracy and processing speed. Therefore, this paper proposed a fast and accurate ECG authentication utilizing only two stages, i.e., ECG beat detection and classification. By minimizing time-consuming ECG signal pre-processing and feature extraction, our proposed two-stage algorithm can authenticate the ECG signal around 660 μs. Hamilton’s method was used for ECG beat detection, while the Residual Depthwise Separable Convolutional Neural Network (RDSCNN) algorithm was used for classification. It was found that between six and eight ECG beats were required for authentication of different databases. Results showed that our proposed algorithm achieved 100% accuracy when evaluated with 48 patients in the MIT-BIH database and 90 people in the ECG ID database. These results showed that our proposed algorithm outperformed other state-of-the-art methods.

Application of Neural Networks for Automatically Detecting Verbal Accents

Vestnik MEI ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 98-107
Author(s):  
Oleg V. Barte`nev ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Russian Language ◽  
Numerical Code ◽  
Data Array ◽  
The Neural Network ◽  
Word Forms ◽  
Word Classification ◽  
Word Classes ◽  
Two Stages

The problem of automatically detecting verbal accents is solved. Word classes with one and two non-transitive accents, with transitive accents, and without accents are identified. An accent is determined in words in which it is not transitive. Words are grouped by the number of syllables. Each group is divided into word classes with the same numbers of accented syllables. Thus, the accents determination problem solved by means of neural networks boils down to word classification. The data array (training and test sets) is formed from A.A. Zaliznyak's Russian language grammatical dictionary, which contains word forms with placed accents. A word model comprises a list of syllables. In the data array, syllables are replaced by their numerical codes, for which syllable dictionaries are compiled. The numerical code of a syllable is its number in the syllable dictionary. The accents are searched in two stages. First, it is found out whether the word has non-transitive accents, and if yes, the word is transferred to the neural network that determines the accents. All neural networks designed in this study contain an Embedding layer which translates scalar representations of word syllables into vector ones. At its input, the neural network receives a vector with the numerical codes of word syllables, and at the output it yields the word class number, which in the case of one non-transitive accent coincides with the number of the accented syllable, and in the case of two non-transitive accents indicates the numbers of two accented syllables. The probabilities of correctly determining one and two non-transitive accents are estimated at 0.9474 and 0.9759, respectively.

scholarly journals INTERPRETATION OF NEURAL NETWORK TECHNOLOGIES FOR PREDICTION AND MANAGEMENT OF RISK FACTORS

Aviation ◽  
2010 ◽  
Vol 14 (1) ◽  
pp. 19-23 ◽  
Author(s):  
Volodimir Kharchenko ◽  
Oleh Alexeiev
Keyword(s):  
Neural Network ◽  
Risk Factors ◽  
Neural Networks ◽  
Management System ◽  
Safety Management ◽  
Flight Safety ◽  
Integrated Methods ◽  
Network Technologies ◽  
Informative Indices ◽  
Neural Network Technologies

The analysis carried out, as well as the systematisation and generalisation of flight safety problems, has allowed us to propose a model for a flight safety management system and to define directions for priority research. To solve flight safety problems, it is suggested to use the integrated methods of flight safety management on the basis of basic and partial criteria totality, where it is possible to take into account simultaneously the probabilistic indices of the system and informative indices, which are connected by means of using neural networks. Santrauka Atliktas tyrimas, taip pat skrydžio saugumo problemu susisteminimas bei apibendrinimas leido numatyti skrydžiu saugumo valdymo sistemos tobulinimo kelius, nustatyti prioritetines ju tyrimo kryptis. Siekiant užtikrinti skrydžiu sauguma, siūloma taikyti integruotus skrydžiu saugumo valdymo metodus, kurie remiasi baziniu bei daliniu kriteriju visuma; čia galima kartu ivertinti sistemos tikimybinius bei informacinius duomenis, kuriu jungiamaja grandimi yra neuroniniai tinklai.

scholarly journals Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 205
Author(s):  
Hassan Tariq ◽  
Muhammad Rashid ◽  
Asfa Javed ◽  
Eeman Zafar ◽  
Saud S. Alotaibi ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Deep Convolutional Neural Networks ◽  
Appropriate Treatment ◽  
Long Time ◽  
Computer Based ◽  
Degree Classification ◽  
Eye Exams

Diabetic retinopathy (DR) is a human eye disease that affects people who are suffering from diabetes. It causes damage to their eyes, including vision loss. It is treatable; however, it takes a long time to diagnose and may require many eye exams. Early detection of DR may prevent or delay the vision loss. Therefore, a robust, automatic and computer-based diagnosis of DR is essential. Currently, deep neural networks are being utilized in numerous medical areas to diagnose various diseases. Consequently, deep transfer learning is utilized in this article. We employ five convolutional-neural-network-based designs (AlexNet, GoogleNet, Inception V4, Inception ResNet V2 and ResNeXt-50). A collection of DR pictures is created. Subsequently, the created collections are labeled with an appropriate treatment approach. This automates the diagnosis and assists patients through subsequent therapies. Furthermore, in order to identify the severity of DR retina pictures, we use our own dataset to train deep convolutional neural networks (CNNs). Experimental results reveal that the pre-trained model Se-ResNeXt-50 obtains the best classification accuracy of 97.53% for our dataset out of all pre-trained models. Moreover, we perform five different experiments on each CNN architecture. As a result, a minimum accuracy of 84.01% is achieved for a five-degree classification.

scholarly journals Diabetic retinopathy classification using deep convolutional neural network

2021 ◽  
Vol 24 (1) ◽  
pp. 208
Author(s):  
Akshita L. ◽  
Harshul Singhal ◽  
Ishita Dwivedi ◽  
Poonam Ghuli
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Traditional Method ◽  
High Accuracy ◽  
Vision Impairment ◽  
Fundus Images ◽  
Computationally Efficient ◽  
Deep Convolutional Neural Networks ◽  
Deep Convolution Neural Network ◽  
Different Levels

<span>Diabetic retinopathy (DR) is a diabetic impairment that affects the eyes and if not treated could lead to permanent vision impairment. Traditionally, Ophthalmologists perform diagnosis of DR by checking for existence and any seriousness of some subtle features in the fundus images. This process is not very efficient as it takes a lot of time and resources. DR testing of all the patients, a lot of which are undiagnosed or untreated, is a big task due to the inefficiency of the traditional method. This paper was written with the aim to propose a classification system based on an efficient deep convolution neural network (DCNN) model which is computationally efficient. Amongst other supervised algorithms involved, proposed solution is to find a way to efficiently classify the fundus images into 5 different levels of severity. Application of segmentation after the pre-processing and then use of deep convolutional neural networks on the dataset results in a high accuracy of 91.52%. The result achieved is high given the limitations of the dataset and computational powers.</span>

scholarly journals Prototyping neural networks to evaluate the risk of adverse cardiovascular outcomes in the population

2021 ◽  
Vol 6 (4) ◽  
pp. 67-81
Author(s):  
L. A. Bogdanov ◽  
E. A. Komossky ◽  
V. V. Voronkova ◽  
D. E. Tolstosheev ◽  
G. V. Martsenyuk ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Risk Factors ◽  
Neural Networks ◽  
User Interface ◽  
Arterial Hypertension ◽  
Graphical User Interface ◽  
Cross Validation ◽  
Cardiovascular Outcomes ◽  
Artery Disease

Aim. To develop a neural network basis for the design of artificial intelligence software to predict adverse cardiovascular outcomes in the population.Materials and Methods. Neural networks were designed using the database of 1,525 participants of PURE (Prospective Urban Rural Epidemiology Study), an international, multi-center, prospective study investigating disease risk factors in the urban and rural areas. As this study is still ongoing, we analysed only baseline data, therefore switching prognosis and diagnosis task. Because of its leading prevalence among other cardiovascular diseases, arterial hypertension was selected as an adverse outcome. Neural networks were designed employing STATISTICA Automated Neural Networks (SANN) software, manually selected, cross-validated, and transferred to the original graphical user interface software.Results. Input risk factors were gender, age, place of residence, concomitant diseases (i.e., coronary artery disease, chronic heart failure, diabetes mellitus, chronic obstructive pulmonary disease, and asthma), active or passive smoking, regular use of medications, family history of arterial hypertension, coronary artery disease or stroke, heart rate, body mass index, fasting blood glucose and cholesterol, high- and low-density lipoprotein cholesterol, and serum creatinine levels. Our neural networks showed a moderate efficacy in the virtual diagnostics of arterial hypertension (84.5%, or 1,289 successfully predicted outcomes out of 1,525, area under the ROC curve = 0.88), with almost equal sensitivity (83.6%) and specificity (85.3%), and were successfully integrated into graphical user interface that is necessary for the development of the commercial prognostication software. Cross-validation of this neural network on bootstrapped samples of virtual patients demonstrated sensitivity of 82.7 – 84.7%, specificity of 84.5 – 87.3%, and area under the ROC curve of 0.88 – 0.89.Conclusion. The artificial intelligence prognostication software to predict adverse cardiovascular outcomes in the population can be developed by a combination of automated neural network generation and analysis followed by manual selection, cross-validation, and integration into graphical user interface.

scholarly journals Proportion of severity of retinal hard exudates and its association with systemic risk factors

2020 ◽  
Vol 8 (1) ◽  
pp. 51
Author(s):  
Devi Silpa ◽  
Anuja Sathar ◽  
Beena Thankappan
Keyword(s):  
Risk Factors ◽  
Diabetic Retinopathy ◽  
Serum Lipid ◽  
Univariate Analysis ◽  
Systemic Hypertension ◽  
P Value ◽  
Cross Sectional ◽  
Female Ratio ◽  
Hard Exudates ◽  
Hba1c Levels

Background: Diabetic macular edema (DME) characterized by deposition of hard exudates in central retina is now the leading cause of visual loss in persons with diabetes mellitus. Several studies have shown association between severity of retinal hard exudates and various components of serum lipid. The aim of this study is to estimate the proportion of severity of retinal hard exudates with risk factors like dyslipidemia, duration of diabetes, hypertension, HbA1c levels and microalbuminuria.  Methods: A hospital based cross sectional study was done involving 242 diabetic retinopathy patients. After dilated fundus examination, severity of retinal hard exudates was graded by photographs with Topcon fundus camera using modified airlie house classification. These grades were divided into three groups. Group 1 (absent or minimal hard exudates) included patients with grade 0, 1 or 2 hard exudates; group 2 (hard exudates present), included patients with grade 3 or 4 hard exudates and group 3 (prominent hard exudates), patients with grade 5 hard exudates. Values of serum lipid profile, HbA1C and urine microalbumin were analysed in association with severity of retinal hard exudates.Results: Out of the 242 diabetic retinopathy patients, the male female ratio was 1:1 and the mean age was 59.8±7.4 years. There were 12% patients in group one, 52.5% in group two and 35.5% in group three. On univariate analysis, severity of hard exudates was significantly associated with serum cholesterol (p value<0.01), LDL (p value<0.01) triglycerides (p value<0.01), HbA1c (p value<0.01), systemic hypertension (p value<0.01) and urine microalbumin (p value=0.01).  Conclusions: Severity of retinal hard exudates in diabetic retinopathy patients is significantly associated with risk factors like systemic hypertension, dyslipidemia, raised HbA1C levels and urine microalbumin.

Sign in / Sign up

Export Citation Format

Share Document