Classification Of Diabetes Research Articles

Diabetic retinopathy classification using VGG16 neural network

Diabetic retinopathy classification using VGG16 neural network

Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study.

Convolutional neural networks (CNN) are widely used in computer vision and medical image analysis as the state-of-the-art technique. In CNN, pooling layers are included mainly for downsampling the feature maps by aggregating features from local regions. Pooling can help CNN to learn invariant features and reduce computational complexity. Although the max and the average pooling are the widely used ones, various other pooling techniques are also proposed for different purposes, which include techniques to reduce overfitting, to capture higher-order information such as correlation between features, to capture spatial or structural information, etc. As not all of these pooling techniques are well-explored for medical image analysis, this paper provides a comprehensive review of various pooling techniques proposed in the literature of computer vision and medical image analysis. In addition, an extensive set of experiments are conducted to compare a selected set of pooling techniques on two different medical image classification problems, namely HEp-2 cells and diabetic retinopathy image classification. Experiments suggest that the most appropriate pooling mechanism for a particular classification task is related to the scale of the class-specific features with respect to the image size. As this is the first work focusing on pooling techniques for the application of medical image analysis, we believe that this review and the comparative study will provide a guideline to the choice of pooling mechanisms for various medical image analysis tasks. In addition, by carefully choosing the pooling operations with the standard ResNet architecture, we show new state-of-the-art results on both HEp-2 cells and diabetic retinopathy image datasets.

Diabetic retinopathy detection and classification using CNN tuned by genetic algorithm

Diabetic retinopathy detection and classification using CNN tuned by genetic algorithm

Klasifikasi Penyakit Diabetes Pada Imbalanced Class Dataset Menggunakan Algoritme Stacking

Diabetes is a disease that has the potential to cause death. Based on a report from the IDF (International Diabetes Federation), it was stated that in 2019 there were 463 million people in the world suffering from this disease. According to the Ministry of Health, Indonesia is a country that is included in the top 10 highest in the world by the number of people with diabetes. Machine learning models can be a solution for the early detection of diabetes based on history and available data. The majority of the research that has been done chiefly uses a single classifier. The single classifier model has a weakness when faced with class imbalance conditions in the dataset. Therefore, this study uses the Stacking Model for the classification and prediction process on the diabetes dataset. The goal is to improve the performance of a single classifier. In addition, the Stacking Model is expected to be one of the solutions for the classification of diabetes in the imbalanced class dataset. Based on two test experiments that have been carried out using two different datasets. The Stacking algorithm can produce an accuracy value of 89%, TPR value of 89%, TNR value of 85%, and G-Mean of 86.98% in the first dataset and can produce an accuracy value of 96%, TPR value of 96%, TNR value of 94%, and G-Mean of 94.99% in the second dataset. These results are better than single classifiers such as C4.5, K-NN, and SVM of the four indicators evaluated in both diabetes datasets. Thus, the proposed algorithm, namely Stacking (C4.5-SVM), can be a solution for classifying diabetes datasets with unbalanced class distribution conditions.

Characterisation of progression of macular oedema in the initial stages of diabetic retinopathy: a 3-year longitudinal study

Background/objectivesTo characterise the prevalence and three-year progression of centre-involving diabetic macular oedema (CI-DMO) in minimal to moderate non-proliferative diabetic retinopathy, using optical coherence tomography (OCT) and measurements of retinal fluid using tissue optical reflectivity ratios (OCT-Leakage).Methods/methodsSeventy-four eyes from 74 patients were followed in a 3-year prospective longitudinal observational cohort of type 2 diabetes (T2D) patients using spectral-domain optical coherence tomography (SD-OCT), OCT-Angiography (OCT-A) and OCT-Leakage (OCT-L). Eyes were examined four times with 1-year intervals. Sixteen eyes (17.8%) were excluded from the analysis due to quality control standards. Retinal oedema was measured by central retinal thickness and retinal fluid by using optical reflectivity ratios obtained with the OCT-L algorithm. Vessel density was measured by OCT-A. Thinning of the ganglion cell and inner plexiform layers (GCL + IPL) was examined to identify retinal neurodegenerative changes. Diabetic retinopathy ETDRS classification was performed using the seven-field ETDRS protocol.ResultsCI-DMO was identified in the first visit in 9% of eyes in ETDRS groups 10–20, 10% of eyes in ETDRS group 35 and 15% of eyes in ETDRS groups 43–47. The eyes with CI-DMO and subclinical CI-DMO showed a progressive increase in retinal extracellular fluid during the 3-year period of follow-up. The eyes with CI-DMO and increased retinal extracellular fluid accumulation were associated with vision loss.ConclusionsThe prevalence of subclinical CI-DMO and CI-DMO in the initial stages of NPDR occurs independently of severity grading of the retinopathy, showing progressive increase in retinal extracellular fluid and this increase is associated with vision loss (82% 9 out of 11 cases).

Fine-Tuning Fuzzy KNN Classifier Based on Uncertainty Membership for the Medical Diagnosis of Diabetes

Diabetes, a metabolic disease in which the blood glucose level rises over time, is one of the most common chronic diseases at present. It is critical to accurately predict and classify diabetes to reduce the severity of the disease and treat it early. One of the difficulties that researchers face is that diabetes datasets are limited and contain outliers and missing data. Additionally, there is a trade-off between classification accuracy and operational law for detecting diabetes. In this paper, an algorithm for diabetes classification is proposed for pregnant women using the Pima Indians Diabetes Dataset (PIDD). First, a preprocessing step in the proposed algorithm includes outlier rejection, imputing missing values, the standardization process, and feature selection of the attributes, which enhance the dataset’s quality. Second, the classifier uses the fuzzy KNN method and modifies the membership function based on the uncertainty theory. Third, a grid search method is applied to achieve the best values for tuning the fuzzy KNN method based on uncertainty membership, as there are hyperparameters that affect the performance of the proposed classifier. In turn, the proposed tuned fuzzy KNN based on uncertainty classifiers (TFKNN) deals with the belief degree, handles membership functions and operation law, and avoids making the wrong categorization. The proposed algorithm performs better than other classifiers that have been trained and evaluated, including KNN, fuzzy KNN, naïve Bayes (NB), and decision tree (DT). The results of different classifiers in an ensemble could significantly improve classification precision. The TFKNN has time complexity O(kn2d), and space complexity O(n2d). The TFKNN model has high performance and outperformed the others in all tests in terms of accuracy, specificity, precision, and average AUC, with values of 90.63, 85.00, 93.18, and 94.13, respectively. Additionally, results of empirical analysis of TFKNN compared to fuzzy KNN, KNN, NB, and DT demonstrate the global superiority of TFKNN in precision, accuracy, and specificity.

Texture Attention Network for Diabetic Retinopathy Classification

Diabetic Retinopathy (DR) is a disease caused by a high level of glucose in retina vessels. This malicious disease put millions of people around the world at risk for vision loss each year. Being a life-threatening disease, early diagnosis can be an effective step in the treatment and prevention of vision loss. To automate the early diagnosis process, computer-aided diagnosis methods are not only useful in detecting the diabetic signatures but also provide information regarding the diabetic grade for the optometrist to determine an appropriate treatment. Several deep classification models are proposed in the literature to solve the diabetic retinopathy classification task, however, these methods usually lack incorporate an attention mechanism to better encode the semantic dependency and highlight the most important region for boosting the model performance. To overcome these limitations, we propose to incorporate a style and content recalibration mechanism inside the deep neural network to adaptively scale the informative regions for diabetic retinopathy classification. In our proposed method, the input image passes through the encoder module to encode both high-level and semantic features. Next, by utilizing a content and style separation mechanism, we decompose the representational space into a style (e.g., texture features) and content (e.g., semantic and contextual features) representation. The texture attention module takes the style representation and applies a high-pass filter to highlight the texture information while the spatial normalization module uses a convolutional operation to determine the more informative region inside the retinopathy image to detect diabetic signs. Once the attention modules are applied to the representational features, the fusion module combines both features to form a normalized representation for the decoding path. The decoder module in our model performs both diabetic grading and healthy, non-healthy classification tasks. Our experiment on APTOS Kaggle dataset (accuracy 0.85) demonstrates a significant improvement compared to the literature work. This fact reveals the applicability of our method in a real-world scenario.

On the use of fiber lasers in non-invasive blood glucose monitoring

Diabetes is a chronic metabolic disorder, which may lead to a series of serious complications and endanger human life in severe cases. Regular monitoring of blood sugar levels can help patients prevent diabetes complications. In this review, firstly, the causes and classification of diabetes, the background knowledge of non-invasive blood glucose monitoring, the classification of blood glucose monitoring methods, the basic theory of optical methods, and the process of non-invasive blood glucose monitoring are described. Then, the basic structure of the fiber laser, and the significant characteristics of the output light pulse are introduced. Most importantly, five optical methods that the fiber laser can be applied to non-invasive blood glucose monitoring are described in detail. Finally, this review describes the process of electrical signal processing in the non-invasive blood glucose monitoring device, some important algorithms, and the means of device performance evaluation.

Exploration of Potential Biomarkers for Type 2 Diabetes by UPLC-QTOF-MS and WGCNA of Skin Surface Lipids.

BackgroundDiabetes has become popular and has become one of the most important global health care challenges. Patients with diabetes have a high incidence of skin diseases. Cell and animal models are often used to study the skin conditions of people with diabetes.MethodsIn this study, a volunteer questionnaire survey, skin lipomics analysis based on ultra-high performance liquid chromatography-quadrupole tandem time-of-flight mass spectrometry (UPLC-QTOF-MS), and weighted gene co-expression network analysis (WGCNA) were used to study the differences in skin conditions and skin lipids of participants with type 2 diabetes mellitus (Group D) versus healthy individuals (Group H) and the correlation between these groups. The questionnaire was used to investigate personal basic, diabetes, and facial skin status information of 77 female volunteers aged 55–65 years old from the Peking University Shougang Hospital. The facial skin lipids of all volunteers were analysed by UPLC-QTOF-MS technique; the differential lipids between groups D and H were analysed by partial least-squared discriminant and univariate analysis.ResultsIn total, 23 kinds of differential lipids were identified, all of which belonged to sphingolipids. The use of WGCNA combined clinical information with lipid analysis to study the relationship between glycosylated haemoglobin, skin pigmentation/non-pigmentation, and skin lipids. Two types of lipids were identified to distinguish between hub lipids of high and low glycosylated haemoglobin; 12 types of lipids were identified that could distinguish between the hub lipids of pigmented and non-pigmented participants (PLS-DA).ConclusionThe experimental results not only provide a reference for the diagnosis and classification of diabetes via analysing the skin lipids of patients, but also provides a theoretical basis for further study on the effects of diabetes on the skin of patients.

Pipeline Parallelism in Distributed Deep Learning for Diabetic Retinopathy Classification

Deep learning (DL) has been used widely and successfully in a variety of industries. It is challenging for researchers to carry out their experiments to find the optimal learning model because training the deep learning model is a time-consuming operation. Distributed deep learning offers a technique for rapid training of DL models (DDL). It is difficult to create and implement DDL, nevertheless, so it is important to report on the performance analysis of different DDL algorithms for the benefit of the research community. The authors of this proposed study use two GPUs to design, construct, and analyse a pipeline parallelism in DDL and then present an analysis of its performance. As a case study for DDL implementation, the authors employ diabetic retinopathy classification. 0.834 is obtained as the validation F1 score. The performance of DDL is reported and examined by the authors, and it is demonstrated to improve training effectiveness in terms of both time and speed.

Evolutionary Intelligence and Deep Learning Enabled Diabetic Retinopathy Classification Model

Diabetic Retinopathy (DR) has become a widespread illness among diabetics across the globe. Retinal fundus images are generally used by physicians to detect and classify the stages of DR. Since manual examination of DR images is a time-consuming process with the risks of biased results, automated tools using Artificial Intelligence (AI) to diagnose the disease have become essential. In this view, the current study develops an Optimal Deep Learning-enabled Fusion-based Diabetic Retinopathy Detection and Classification (ODL-FDRDC) technique. The intention of the proposed ODL-FDRDC technique is to identify DR and categorize its different grades using retinal fundus images. In addition, ODL-FDRDC technique involves region growing segmentation technique to determine the infected regions. Moreover, the fusion of two DL models namely, CapsNet and MobileNet is used for feature extraction. Further, the hyperparameter tuning of these models is also performed via Coyote Optimization Algorithm (COA). Gated Recurrent Unit (GRU) is also utilized to identify DR. The experimental results of the analysis, accomplished by ODL-FDRDC technique against benchmark DR dataset, established the supremacy of the technique over existing methodologies under different measures.

Classification of Diabetes Types using Machine Learning

Machine learning algorithms have aided health workers (including doctors) in the processing, analysis, and diagnosis of medical problems, as well as the detection of disease patterns and other patient data. Diabetes mellitus (DM), commonly referred to as diabetes, is a gathering of a syndrome issue that is portrayed by high glucose levels in the blood over a drawn-out period. It is a long-term illness that is a great threat to humanity and causes death. Most of the existing machine learning algorithms used for the classification and prediction of diabetes suffer from embodying redundant or inessential medical procedures that cause complications and wastage of time and resources. The absence of a correct diagnosis scheme, deficiency of economic means, and a general lack of awareness represent the main reasons for these negative effects. Hence, preventing the sickness altogether through early detection may doubtless cut back a considerable burden on the economy and aid the patient in diabetes management. This study developed diabetes classification using machine learning techniques that will minimize the aforementioned drawbacks in the prediction of diabetes systems. Decision tree classifiers, logistic regression, random forest, and support vector machines are all examples of predictive algorithms that were tested in this paper. 1009 records of data set were obtained from the Diabetes dataset of Abelvikas, Data World. We used a confusion matrix to visualize the performance evaluation of the classifiers. The experimental result shows that the four machine learning algorithms perform well. However, Random Forest outperforms the other three, with a prediction accuracy of 100% and has a better prediction level when compared with others and existing work.

Deep Learning Techniques for Diabetic Retinopathy Classification: A Survey

Diabetic Retinopathy (DR) is a degenerative disease that impacts the eyes and is a consequence of Diabetes mellitus, where high blood glucose levels induce lesions on the eye retina. Diabetic Retinopathy is regarded as the leading cause of blindness for diabetic patients, especially the working-age population in developing nations. Treatment involves sustaining the patient’s current grade of vision since the disease is irreversible. Early detection of Diabetic Retinopathy is crucial in order to sustain the patient’s vision effectively. The main issue involved with DR detection is that the manual diagnosis process is very time, money, and effort consuming and involves an ophthalmologist’s examination of eye retinal fundus images. The latter also proves to be more difficult, particularly in the early stages of the disease when disease features are less prominent in the images. Machine learning-based medical image analysis has proven competency in assessing retinal fundus images, and the utilization of deep learning algorithms has aided the early diagnosis of Diabetic Retinopathy (DR). This paper reviews and analyzes state-of-the-art deep learning methods in supervised, self-supervised, and Vision Transformer setups, proposing retinal fundus image classification and detection. For instance, referable, non-referable, and proliferative classifications of Diabetic Retinopathy are reviewed and summarized. Moreover, the paper discusses the available retinal fundus datasets for Diabetic Retinopathy that are used for tasks such as detection, classification, and segmentation. The paper also assesses research gaps in the area of DR detection/classification and addresses various challenges that need further study and investigation.

Grading of Diabetic Retinopathy in Suspected Individuals

Diabetic retinopathy is a fast-spreading eye disease and this may lead to blindness in working-age adults. Between 32 to 40 % of about 347 million people suffer from diabetic retinopathy. It is a silent vision problem and thus, requires regular annual check-ups which will help in controlling the disease at initial stage and effective treatment will provide favorable results. The research utilizes a deep learning approach for diabetic retinopathy classification, which also will aid in addressing real-world issues. The work has already been done to solve this issue with the use of different classification techniques but somehow the efficiency of the training algorithm is dependent on the quality of feature extraction, which necessitates domain expertise. The current work solves the issue by applying a deep learning algorithm that recognizes the pattern and classifies retinal fundus images as normal or infected. In this study on the different categories of diabetic retinopathy 3662 retinal images were analyzed. The categories that are present in the data are No- diabetic retinopathy , mild, moderate, severe, and proliferative diabetic retinopathy . The publicly available retinopathy detection database and a trained model will be used in the experiments to retrieve the features of the ocular images and provide an appropriate output. The goal of this study is to apply and comprehend how the performance of a pretrained model distinguishes between proliferative and nonproliferative diabetic retinopathy.

Uncertainty-Aware Deep Learning Methods for Robust Diabetic Retinopathy Classification

Automatic classification of diabetic retinopathy from retinal images has been increasingly studied using deep neural networks with impressive results. However, there is clinical need for estimating uncertainty in the classifications, a shortcoming of modern neural networks. Recently, approximate Bayesian neural networks (BNNs) have been proposed for this task, but previous studies have only considered the binary referable/non-referable diabetic retinopathy classification applied to benchmark datasets. We present novel results for 9 BNNs by systematically investigating a clinical dataset and 5-class classification scheme, together with benchmark datasets and binary classification scheme. Moreover, we derive a connection between entropy-based uncertainty measure and classifier risk, from which we develop a novel uncertainty measure.We observe that the previously proposed entropy-based uncertainty measure improves performance on the clinical dataset for the binary classification scheme, but not to such an extent as on the benchmark datasets. It improves performance in the clinical 5-class classification scheme for the benchmark datasets, but not for the clinical dataset. Our novel uncertainty measure generalizes to the clinical dataset and to one benchmark dataset. Our findings suggest that BNNs can be utilized for uncertainty estimation in classifying diabetic retinopathy on clinical data, though proper uncertainty measures are needed to optimize the desired performance measure. In addition, methods developed for benchmark datasets might not generalize to clinical datasets.

A Secure IoT-Cloud Based Healthcare System for Disease Classification Using Neural Network

The integration of the Internet of Things (IoT) and cloud computing is the most popular growing technology in the IT world. IoT integrated cloud computing technology can be used in smart cities, health care, smart homes, environmental monitoring, etc. In recent days, IoT integrated cloud can be used in the health care system for remote patient care, emergency care, disease prediction, pharmacy management, etc. but, still, security of patient data and disease prediction accuracy is a major concern. Numerous machine learning approaches were used for effective early disease prediction. However, machine learning takes more time and less performance while classification. In this research work, the Attribute based Searchable Honey Encryption with Functional Neural Network (ABSHE-FNN) framework is proposed to analyze the disease and provide stronger security in IoT-cloud healthcare data. In this work, the Cardiovascular Disease and Pima Indians diabetes dataset are used for heart and diabetic disease classification. Initially, means-mode normalization removes the noise and normalizes the IoT data, which helps to enhance the quality of data. Rectified Linear Unit (RLU) was applied to adjust the feature weight to reduce the training cost and error classification. This proposed ABSHE-FNN technique provides better security and achieves 92.79% disease classification accuracy compared to existing techniques.

A Multilevel Deep Feature Selection Framework for Diabetic Retinopathy Image Classification

Diabetes or Diabetes Mellitus (DM) is the upset that happens due to high glucose level within the body. With the passage of time, this polygenic disease creates eye deficiency referred to as Diabetic Retinopathy (DR) which can cause a major loss of vision. The symptoms typically originate within the retinal space square in the form of enlarged veins, liquid dribble, exudates, haemorrhages and small scale aneurysms. In current therapeutic science, pictures are the key device for an exact finding of patients’ illness. Meanwhile, an assessment of new medicinal symbolisms stays complex. Recently, Computer Vision (CV) with deep neural networks can train models with high accuracy. The thought behind this paper is to propose a computerized learning model to distinguish the key precursors of Dimensionality Reduction (DR). The proposed deep learning framework utilizes the strength of selected models (VGG and Inception V3) by fusing the extracated features. To select the most discriminant features from a pool of features, an entropy concept is employed before the classification step. The deep learning models are fit for measuring the highlights as veins, liquid dribble, exudates, haemorrhages and miniaturized scale aneurysms into various classes. The model will ascertain the loads, which give the seriousness level of the patient’s eye. The model will be useful to distinguish the correct class of seriousness of diabetic retinopathy pictures.

Multi-Stream Deep Neural Network for Diabetic Retinopathy Severity Classification Under a Boosting Framework

Diabetic Retinopathy (DR) is an eye disorder in patients with diabetes. Detection of DR presence and its complications using fundus images at an early stage helps prevent its progression to the advanced levels. In the recent years, several well-designed Convolutional Neural Networks (CNN) have been proposed to detect the presence of DR with the help of publicly available datasets. However, these existing CNN-based classifiers focus on utilizing different architectural settings to improve the performance of detection task only i.e. presence or absence of DR. The further classification of the severity and type of the disease, however, remains a non-trivial task. To this end, we propose a multi-stream ensemble deep network to classify diabetic retinopathy severity. The proposed approach takes advantages of the deep networks and principal component analysis (PCA) to learn inter-class and intra-class variations from the raw image features. Ensemble machine learning classifiers are then applied to achieve high classification accuracy and robust performance on the obtained deep features. Specifically, a multi-stream network is made using pre-trained deep learning architectures i.e. ResNet-50 and DenseNet-121 to serve as the main feature extractors. Further application of PCA reduces the dimensionality of features and effectively separates the variation space of inter-class and intra-class images. Finally, an ensemble machine learning classifier using AdaBoost and random forest algorithms is built to further improve classification accuracy. The proposed approach has been compared with multiple conventional CNN-based approaches on Messidor-2 (two categories) and EyePACS (two, five categories) datasets. The experiment results show that our proposed approach achieves superior performance (upto 95.58% accuracy) and can be considered a promising method for automatic diabetic retinopathy detection.

Local Binary CNN for Diabetic Retinopathy Classification on Fundus Images

Local Binary CNN for Diabetic Retinopathy Classification on Fundus Images

Applicability of portable retinal cameras and telemedicine as facilitating tools in screening diabetic retinopathy in the COVID-19 pandemic scenario.

Diabetes mellitus is a leading cause of impaired vision. The objective of this study was to evaluate the feasibility of use of portable retinograph and remote analysis of images along with a virtual questionnaire for screening for diabetic retinopathy in basic health units in the city of Ribeirão Preto/SP during the Covid-19 pandemic. Standard Covid-19 protocol was followed during the screening. Blood pressure and capillary blood glucose were measured. Demographic and social data were collected through a standardized online questionnaire via smartphone. After pupillary dilation, fundal images were obtained with portable retinographs by trained ophthalmology residents. Two standardized 45° images were acquired: one posterior segment and another nasal to the optic nerve. Diabetic retinopathy was classified according to the Early Treatment Diabetic Retinopathy Study. A total of 350 patients (64% female; 45% aged 55-70 years; 55% Caucasian) were evaluated. For 40.5% of patients, the campaign was the first opportunity for retinal evaluation; 47.56% had diabetes mellitus for >10 years. On repeat analysis of images stored in a cloud-based repository by retinal specialist, a 7.8% difference was observed in the Early Treatment Diabetic Retinopathy Study diabetic retinopathy classification, compared to the screening findings. Mild diabetic retinopathy was observed in 12.23%, moderate diabetic retinopathy in 6.31%, and proliferative diabetic retinopathy in 2.58% patients. Macular edema was present in 4.58% patients. Diabetic retinopathy was not detected in 72.78% patients. Use of portable retinographs together with telemedicine can provide efficient alternative to traditional methods for screening and diagnosis of diabetic retinopathy.