Classification of Diabetic Retinopathy Disease Using Convolutional Neural Network

Minarno, Agus Eko; Mandiri, Mochammad Hazmi Cokro; Azhar, Yufis; Bimantoro, Fitri; Nugroho, Hanung Adi; İbrahim, Zarina Bibi

doi:10.30630/joiv.6.1.857

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, our validation accuracy gives better results with a score of 95.33% compared to Bodapati et al [8,19] with 80.96% validation accuracy and Patel and Chaware [13] with 81.00% accuracy. Our work also gives better training accuracy results when compared to Minarno et al [23] work. Although their research gives better test and F1-Score results, Minarno et al [23] research uses a different proportion of training and validation compared to our work, and they use the EfficientNet-B7 model which has more parameters compared to the base EfficientNet-B0 model, thus needing more computational power, resulting with a model that is bigger in sizes.…”

Section: Testing Resultsmentioning

confidence: 49%

Severity Classification of Diabetic Retinopathy Using Ensemble Stacking Method

Handoyo¹,

Kusuma²

2022

RIA

View full text Add to dashboard Cite

Diabetic retinopathy (DR), is a complication resulting from the disease that can lead to blindness if not detected early. Recently, many classification systems for diabetic retinopathy have been developed. However, several problems were found, namely, the classification results in certain classes still have less than optimal accuracy values, the lack of in-depth analysis for the results, and the overall accuracy that can still be improved. In this work, we experiment by evaluating and combining new deep learning models such as EfficientNet, EfficientNetV2, LCNet, MobileNetV3, TinyNet, and FBNetV3 using ensemble stacking techniques with four different meta-learners: decision trees, logistic regression, ANN, and SVM to provide better accuracy in classifying the severity of diabetic retinopathy. Our work offers satisfactory classification results on the APTOS 2019 dataset with training, validation, testing, and F1 score accuracy of 96.56%, 95.33%, 84.17%, and 70.16%, respectively.

show abstract

Section: Testing Resultsmentioning

confidence: 49%

Severity Classification of Diabetic Retinopathy Using Ensemble Stacking Method

Handoyo¹,

Kusuma²

2022

RIA

View full text Add to dashboard Cite

show abstract

“…Diabetic disease needs a unique study to improve the availability of investigation or reduce the variance and spread of this vital disease. Studies are becoming more sensitive to such an issue due to its causes and symptoms, as discussed and explained in [40] and [41].…”

Section: F Features Selection Techniquesmentioning

confidence: 99%

Feature Minimization for Diabetic Disorders High Performances Prediction System-based on Random Forest Tree

Mohammed,

Ahmed,

Mohammed

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Human organ failure due to high blood sugar is considered a chronic disease. Early prediction might reduce or prevent complications due to such disorders, especially with recent machine-learning improvement techniques and the availability of electronic data from different sources. The number of diabetic patients roughly increased and may reach more than 600 million by twenty years. Transforming data into valuable and helpful information is an effort for researchers to improve the performance of ML techniques. This paper applies several types of sampling to predict 1000 samples with attributes and three diabetes class types (Random Forest tree, Hoeffding tree, LWL, NB updatable, and support vector Machine). This paper focused on most parameters that affected overall prediction accuracy. ML performances have been measured depending on the accuracy and mean absolute error for several cross-validation values before Feature reduction and after feature minimization by applying feature selection methods. It shows that Gender, Age, Blood Sugar Level (HbA1c), Triglycerides (TG), and Body Mass Index (BMI) are the most impact attributes applied. It is also shown that the Random Forest tree was the best method (97.7 and 98.6 %) with and without feature minimization, respectively, but it has a higher performance by omitting some unbalanced features from the diabetic dataset. Weight minimization has also been applied to techniques like SVM to obtain a better-searching plane and a robust model. In addition, this study specifies which parameters have weight minimization with the required analysis. Also, the feature selection method was applied to gain memory and reduce time.

show abstract

“…Minarno et al [22] emphasise the seriousness of malaria as a worldwide public health concern and the significance of early identification and fast treatment to avoid serious results, including death. The purpose of this study was to categorise malaria cell images using the Inception-V3 architecture.…”

Section: Related Workmentioning

confidence: 99%

Deep learning-based computer assisted detection techniques for malaria parasite using blood smear images

2023

IJATEE

View full text Add to dashboard Cite

Malaria remains a significant global health concern, impacting various regions worldwide. Achieving effective treatment and reducing mortality rates hinges on early and accurate diagnosis. In the year 2021, the World Health Organization (WHO) reported a staggering 619,000 deaths attributed to malaria. Additionally, approximately 214 million individuals were afflicted by this disease during that period. Hence, this study introduces two distinct deep-learning algorithms tailored for malaria disease classification. The first method employs a binary classifier convolutional neural network (CNN) model, attaining an accuracy (ACC) of 90.20%. The second method introduces a customized CNN model that exhibits even greater ACC, reaching an impressive 96.02%. These advanced deep learning (DL) techniques hold the potential to enhance the precision (PRE) and efficiency of malaria diagnosis, ultimately facilitating early disease detection. The study provides comprehensive insights into the proposed models. Model 1 involves malaria disease classification employing a CNN-based binary classifier, while Model 2 adopts a customized CNN architecture. The methodology section elucidates the details of these models, their design, and the execution of experiments undertaken to evaluate their performance. Notably, the proposed method is juxtaposed with the state-of-the-art approach, demonstrating superior results in accurately discerning infected and uninfected malaria blood cell images.

show abstract

Classification of Diabetic Retinopathy Disease Using Convolutional Neural Network

Cited by 9 publications

References 17 publications

Severity Classification of Diabetic Retinopathy Using Ensemble Stacking Method

Severity Classification of Diabetic Retinopathy Using Ensemble Stacking Method

Feature Minimization for Diabetic Disorders High Performances Prediction System-based on Random Forest Tree

Deep learning-based computer assisted detection techniques for malaria parasite using blood smear images

Contact Info

Product

Resources

About