scholarly journals Prediction of diabetic retinopathy using machine learning techniques

2021 ◽  
Author(s):  
T Jemima Jebaseeli ◽  
◽  
C. Anand Deva Durai ◽  
Salem Alelyani ◽  
Mohammed Saleh Alsaqer ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Early Stage ◽  
Image Data ◽  
Histogram Equalization ◽  
Machine Learning Techniques ◽  
Computer Assisted ◽  
Diabetic Patients ◽  
Resonance Theory ◽  
Adaptive Resonance

Diabetic Retinopathy (DR) is the complicatedness of diabetes that happens due to macular degeneration among Type II diabetic patients. The early symptom of this disease is predicted through annual eye checkups. Hence, one can save their vision at an early stage. Later on, it prompts retinal detachment. There is a requirement for awareness among diabetic patients about this disease to prevent their life from vision misfortune. Along these lines, there is a need for a computer-assisted method to analyze the disease. The proposed system used Adaptive Histogram Equalization (AHE) technique for image enhancement, Hop Field Neural Network for blood vessel segmentation, and Adaptive Resonance Theory (ART) for blood vessel classification. The proposed system analyzes the disease and classifies the disease level effectively with high accuracy. Also, the system notifies the users about the stages of the disease. The proposed system is evaluated with the clinical as well as open fundus image data sets like DRIVE, STARE, MESSIDOR, HRF, DRIONS, and REVIEW for diabetic retinopathy prediction. Also, physicians evaluated the system and concluded that the proposed system does not deviate from the quality of disease analysis and grading. The proposed techniques accomplished 99.99% accuracy. The system is evaluated by the ophthalmologists and witnesses that the proposed system has not veered off as far as quality.

Review of Various Tasks Performed in the Preprocessing Phase of a Diabetic Retinopathy Diagnosis System

2020 ◽  
Vol 16 (4) ◽  
pp. 397-426
Author(s):  
Muhammad Nadeem Ashraf ◽  
Muhammad Hussain ◽  
Zulfiqar Habib
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Vessels ◽  
Early Stage ◽  
Spherical Shape ◽  
Cost Effective ◽  
Lesion Detection ◽  
Diabetic Patients ◽  
Cad System ◽  
Non Invasive ◽  
Optic Discs

Diabetic Retinopathy (DR) is a major cause of blindness in diabetic patients. The increasing population of diabetic patients and difficulty to diagnose it at an early stage are limiting the screening capabilities of manual diagnosis by ophthalmologists. Color fundus images are widely used to detect DR lesions due to their comfortable, cost-effective and non-invasive acquisition procedure. Computer Aided Diagnosis (CAD) of DR based on these images can assist ophthalmologists and help in saving many sight years of diabetic patients. In a CAD system, preprocessing is a crucial phase, which significantly affects its performance. Commonly used preprocessing operations are the enhancement of poor contrast, balancing the illumination imbalance due to the spherical shape of a retina, noise reduction, image resizing to support multi-resolution, color normalization, extraction of a field of view (FOV), etc. Also, the presence of blood vessels and optic discs makes the lesion detection more challenging because these two artifacts exhibit specific attributes, which are similar to those of DR lesions. Preprocessing operations can be broadly divided into three categories: 1) fixing the native defects, 2) segmentation of blood vessels, and 3) localization and segmentation of optic discs. This paper presents a review of the state-of-the-art preprocessing techniques related to three categories of operations, highlighting their significant aspects and limitations. The survey is concluded with the most effective preprocessing methods, which have been shown to improve the accuracy and efficiency of the CAD systems.

scholarly journals Retinal Blood Vessel and Optic Disc Segmentation

2019 ◽  
Vol 8 (2) ◽  
pp. 833-838
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Optic Disc ◽  
Diabetic Patients ◽  
Retinal Vessels ◽  
Retinal Blood Vessel ◽  
Computerized Screening ◽  
Retinal Fundus

Diabetic Retinopathy (DR) is a main source of vision misfortune in diabetic patients. DR is a predominantly caused because of the harm caused in retinal veins of a diabetic patients. It is fundamental to recognize and fragment their tinal veins for DR identification and determination, which avoids prior vision misfortune in diabetic patients. The PC helped programmed discovery and division of veins through the end of optic location district in Retina. Optic Disc (OD) discovery is a principle step while creating computerized screening framework for diabetic retinopathy. This is a technique to naturally recognize the situation of the OD in advanced retinal fundus pictures. The strategy begins by normalizing glow and difference all through the picture utilizing brightening evening out and versatile histogram balance techniques individually. The OD recognition calculation depends on coordinating the normal directional example of the retinal veins. Henceforth, a straightforward coordinated channel is proposed to generally coordinate the headings of the vessels at the OD region. The retinal vessels are portioned utilizing a basic and standard 2-D Gaussian coordinated channel.

Morphological Contour Based Blood Vessel Segmentation in Retinal Images Using Otsu Thresholding

2018 ◽  
Vol 9 (4) ◽  
pp. 48-63 ◽  
Author(s):  
S. Saranya Rubini ◽  
A. Kunthavai ◽  
M.B. Sachin ◽  
S. Deepak Venkatesh
Keyword(s):  
Blood Vessel ◽  
Blood Vessels ◽  
Early Stage ◽  
Histogram Equalization ◽  
Vessel Segmentation ◽  
Contour Detection ◽  
Experimental Result ◽  
Blood Vessel Segmentation ◽  
Otsu Thresholding ◽  
Sensitivity Specificity

Retinal image analysis plays an important part in identifying various eye related diseases such as diabetic retinopathy (DR), glaucoma and many others. Accurate segmentation of blood vessels plays an important part in identifying the retinal diseases at an early stage. In this article, an unsupervised approach based on contour detection has been proposed for effective segmentation of retinal blood vessels. The proposed morphological contour-based blood vessel segmentation (MCBVS) method performs preprocessing using contrast limited adaptive histogram equalization followed by alternate sequential filtering to generate a noise-free image. The resultant image undergoes Otsu thresholding for candidate extraction followed by contour detection to properly segment the blood vessels. The MCBVS method has been tested on the DRIVE dataset and the experimental result shows that the proposed method achieved a sensitivity, specificity and accuracy of 58.79%, 90.77% and 86.7%, respectively. The MCBVS method performs better than the existing methods Sobel, Prewitt and Modified U-Net in terms of accuracy.

scholarly journals Effective Fundus Image Decomposition for the Detection of Red Lesions and Hard Exudates to Aid in the Diagnosis of Diabetic Retinopathy

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6549
Author(s):  
Roberto Romero-Oraá ◽  
María García ◽  
Javier Oraá-Pérez ◽  
María I. López-Gálvez ◽  
Roberto Hornero
Keyword(s):  
Diabetic Retinopathy ◽  
Lesion Detection ◽  
Computer Assisted ◽  
Diabetic Patients ◽  
Fundus Image ◽  
Public Database ◽  
Diagnostic Systems ◽  
Hard Exudates ◽  
The Public ◽  
Proprietary Database

Diabetic retinopathy (DR) is characterized by the presence of red lesions (RLs), such as microaneurysms and hemorrhages, and bright lesions, such as exudates (EXs). Early DR diagnosis is paramount to prevent serious sight damage. Computer-assisted diagnostic systems are based on the detection of those lesions through the analysis of fundus images. In this paper, a novel method is proposed for the automatic detection of RLs and EXs. As the main contribution, the fundus image was decomposed into various layers, including the lesion candidates, the reflective features of the retina, and the choroidal vasculature visible in tigroid retinas. We used a proprietary database containing 564 images, randomly divided into a training set and a test set, and the public database DiaretDB1 to verify the robustness of the algorithm. Lesion detection results were computed per pixel and per image. Using the proprietary database, 88.34% per-image accuracy (ACCi), 91.07% per-pixel positive predictive value (PPVp), and 85.25% per-pixel sensitivity (SEp) were reached for the detection of RLs. Using the public database, 90.16% ACCi, 96.26% PPV_p, and 84.79% SEp were obtained. As for the detection of EXs, 95.41% ACCi, 96.01% PPV_p, and 89.42% SE_p were reached with the proprietary database. Using the public database, 91.80% ACCi, 98.59% PPVp, and 91.65% SEp were obtained. The proposed method could be useful to aid in the diagnosis of DR, reducing the workload of specialists and improving the attention to diabetic patients.

scholarly journals An Efficient Segmentation based Classification of Diabetic Retinopathy Identification using CLAHE with ResNet Model

2019 ◽  
Vol 8 (9) ◽  
pp. 2277-2283
Keyword(s):  
Diabetic Retinopathy ◽  
Histogram Equalization ◽  
Classification Model ◽  
Diabetic Patients ◽  
Detection Model ◽  
Adaptive Histogram Equalization ◽  
Active Population ◽  
Classifier Performance ◽  
Timely Treatment

Diabetic retinopathy (DR) is a widespread problem for diabetic patient and it has been a main reason for blindness in the active population. Several difficulties faced by diabetic patients because of DR can be eliminated by properly maintaining the blood glucose and by timely treatment. As the DR comes with different stages and varying difficulties, it is hard to DR and also it is time consuming. In this paper, we develop an automated segmentation based classification model for DR. Initially, the Contrast limited adaptive histogram equalization (CLAHE) is used for segmenting the images. Later, residual network (ResNet) is employed for classifying the images into different grades of DR. For experimental analysis, the dataset is derived from Kaggle website which is open source platform that attempts to build DR detection model. The highest classifier performance is attained by the presented model with the maximum accuracy of 83.78, sensitivity of 67.20 and specificity of 89.36 over compared models

scholarly journals Multifocal Electroretinogram Can Detect the Abnormal Retinal Change in Early Stage of type2 DM Patients without Apparent Diabetic Retinopathy

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Jiang Huang ◽  
Yi Li ◽  
Yao Chen ◽  
Yuhong You ◽  
Tongtong Niu ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Early Stage ◽  
Multifocal Electroretinogram ◽  
Implicit Time ◽  
Diabetic Patients ◽  
Healthy Controls ◽  
Type 2 Diabetic Patients ◽  
Type 2 Dm ◽  
Retinal Change

Purpose. To study retinal function defects in type 2 diabetic patients without clinically apparent retinopathy using a multifocal electroretinogram (mf-ERG). Methods. Seventy-six eyes of thirty-eight type 2 diabetes mellitus(DM) patients without clinically apparent retinopathy and sixty-four normal eyes of thirty-two healthy control (HC) participants were examined using mf-ERG. Results. Patients with type 2 DM without apparent diabetic retinopathy demonstrated an obvious implicit time delay of P1 in ring 1, ring 3, and ring 5 compared with healthy controls ( t = 5.184 , p ≤ 0.001 ; t = 8.077 , p ≤ 0.001 ; t = 2.000 , p = 0.047 , respectively). The implicit time (IT) in ring 4 of N1wave was significantly delayed in the DM group ( t = 2.327 , p = 0.021 ). Compared with the HC group, the implicit time of the P1 and N1 waves in the temporal retina zone was significantly prolonged ( t = 3.66 , p ≤ 0.001 ; t = 2.187 , p = 0.03 , respectively). And the amplitude of P1 in the temporal retina decreased in the DM group, which had a significantly statistical difference with the healthy controls ( t = − 6.963 , p ≤ 0.001 ). However, there were no differences in either the amplitude of the response or the implicit time of the nasal retina zone between DM and HC. The AUC of multiparameters of mf-ERG was higher in the diagnosis of DR patients. Conclusions. Patients with type 2 DM without clinically apparent retinopathy had a delayed implicit time of P1 wave in temporal regions of the postpole of the retina compared with HC subjects. It demonstrates that mf-ERG can detect the abnormal retinal change in the early stage of type2 DM patients without apparent diabetic retinopathy. Multiparameters of mf-ERG can improve the diagnostic efficacy of DR, and it may be a potential clinical biomarker for early diagnosis of DR.

scholarly journals Application of Machine Learning for Prediction of Lung Cancer using Omics Data

2020 ◽  
Vol 9 (6) ◽  
pp. 230-236
Keyword(s):  
Machine Learning ◽  
Lung Cancer ◽  
Data Mining ◽  
Survival Analysis ◽  
Early Stage ◽  
Image Data ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Omics Data

Cancer is one of the deadly diseases across many countries. However, cancer can be cured, if detected at an early stage. Researchers are working on healthcare for early detection and prevention of cancer. Medical data has reached its utmost potential by providing researchers with huge data sets collected from all over the globe. In the present scenario, Machine Learning has been widely used in the area of cancer diagnosis and prognosis. Survival analysis may help in the prediction of the early onset of disease, relapse, re-occurrence of diseases and biomarker identification. Applications of machine learning and data mining methods in medical field are currently the most widespread in cancer detection and survival analysis. In this survey, different ways to detect and predict lung cancer using latest Machine learning algorithms combined with data mining has been analyzed. Comparative study of various machine learning techniques and technologies has been done over different types of data such as clinical data, omics data, image data etc.

eDiaPredict: An Ensemble-based Framework for Diabetes Prediction

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-26
Author(s):  
Ashima Singh ◽  
Arwinder Dhillon ◽  
Neeraj Kumar ◽  
M. Shamim Hossain ◽  
Ghulam Muhammad ◽  
...  
Keyword(s):  
Machine Learning ◽  
Early Stage ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Critical Conditions ◽  
Support Vector ◽  
Diabetic Patients ◽  
Medical Systems ◽  
Diabetes Status

Medical systems incorporate modern computational intelligence in healthcare. Machine learning techniques are applied to predict the onset and reoccurrence of the disease, identify biomarkers for survivability analysis depending upon certain health conditions of the patient. Early prediction of diseases like diabetes is essential as the number of diabetic patients of all age groups is increasing rapidly. To identify underlying reasons for the onset of diabetes in its early stage has become a challenging task for medical practitioners. Continuously increasing diabetic patient data has necessitated for the applications of efficient machine learning algorithms, which learns from the trends of the underlying data and recognizes the critical conditions in patients. In this article, an ensemble-based framework named e DiaPredict is proposed. It uses ensemble modeling, which includes an ensemble of different machine learning algorithms comprising XGBoost, Random Forest, Support Vector Machine, Neural Network, and Decision tree to predict diabetes status among patients. The performance of eDiaPredict has been evaluated using various performance parameters like accuracy, sensitivity, specificity, Gini Index, precision, area under curve, area under convex hull, minimum error rate, and minimum weighted coefficient. The effectiveness of the proposed approach is shown by its application on the PIMA Indian diabetes dataset wherein an accuracy of 95% is achieved.

Study of diabetic retinopathy among diabetic patients

2020 ◽  
Vol 11 (3) ◽  
pp. 3240-3250
Author(s):  
Vinit Umesh Rewanwar ◽  
Joshi B.S.
Keyword(s):  
Diabetic Retinopathy ◽  
Fluorescein Angiography ◽  
Diabetes Complications ◽  
Early Stage ◽  
Age Groups ◽  
Diabetic Patients ◽  
Fundus Fluorescein Angiography ◽  
Diagnostic Potential ◽  
Eye Examination

People with diabetes complications under many tests. For diabetic retinopathy, we do many tests like, ophthalmoscopy which is done in clinical examination & Fundus Fluorescein Angiography (FFA), etc. This study has been conducted to evaluate the use of Fundus fluorescein angiography in DM patients and its comparison with clinical evaluation for early detection and assessment of the stage of diabetic retinopathy. The current study looked for ophthalmology and the diagnostic potential of FFA in the diagnosis of ophthalmic retinopathy findings because both facilities may not be available everywhere. So look for and provide better options for diagnosis of diabetic retinopathy. Diabetic maculopathy is also a clear finding on direct eye examination. We found that there was a significant correlation between the age groups of the patients: Diabetes, and the development of diabetic retinopathy. No significant association with the sex of patients was observed in the event of retinopathy. In diabetic patients younger than five years of age or those who are in the early stage of diabetic retinopathy, we found that the initial pathological changes that could not be seen on ophthalmoscopy were evident on FFA. The procedure is useful in diagnosis, treatment, follow-up of patients, maintain a permanent record of the retinopathy staging, study the course of the disease, and response to the procedure.

scholarly journals The Relationship between Estimated Glomerular Filtration Rate and Diabetic Retinopathy

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Jingyang Wu ◽  
Jin Geng ◽  
Limin Liu ◽  
Weiping Teng ◽  
Lei Liu ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Diabetic Retinopathy ◽  
Glomerular Filtration Rate ◽  
Glomerular Filtration ◽  
Filtration Rate ◽  
Early Stage ◽  
Density Lipoprotein ◽  
Diabetic Patients ◽  
Aged People ◽  
The Relationship

Diabetic retinopathy (DR) is the leading cause of visual impairment and blindness in working-aged people. Several studies have suggested that glomerular filtration rate (GFR) was correlated with DR. This is a hospital-based study and the aim of it was to examine the relationship between the GFR and DR in patients with type 2 diabetes mellitus (T2DM). We used CKD-EPI equation to estimate GFR and SPSS 19.0 and EmpowerStats software to assess their relationship. Among the 1613 participants (aged 54.75 ± 12.19 years), 550 (34.1%) patients suffered from DR. The multivariate analysis revealed that the risk factors for DR include age (P<0.001, OR = 0.940), duration of diabetes (P<0.001, OR = 1.163), hemoglobin A1c (P=0.007, OR = 1.224), systolic blood pressure (P<0.001, OR = 1.032), diastolic blood pressure (P=0.007, OR = 0.953), high density lipoprotein cholesterol (P=0.024, OR = 3.884), and eGFR (P=0.010, OR = 0.973). Through stratified analysis and saturation effect analysis, our data suggests that eGFR of 99.4 mL/min or lower might imply the early stage of DR in diabetic patients. Thus, the evaluation of eGFR has clinical significance for the early diagnosis of DR.

Sign in / Sign up

Export Citation Format

Share Document