Diabetes is a serious health condition that can cause several issues in human body organs such as the heart and kidney as well as a serious eye disease called diabetic retinopathy(DR).Early detection and treatment are...Diabetes is a serious health condition that can cause several issues in human body organs such as the heart and kidney as well as a serious eye disease called diabetic retinopathy(DR).Early detection and treatment are crucial to prevent complete blindness or partial vision loss.Traditional detection methods,which involve ophthalmologists examining retinal fundus images,are subjective,expensive,and time-consuming.Therefore,this study employs artificial intelligence(AI)technology to perform faster and more accurate binary classifications and determine the presence of DR.In this regard,we employed three promising machine learning models namely,support vector machine(SVM),k-nearest neighbors(KNN),and Histogram Gradient Boosting(HGB),after carefully selecting features using transfer learning on the fundus images of the Asia Pacific Tele-Ophthalmology Society(APTOS)(a standard dataset),which includes 3662 images and originally categorized DR into five levels,now simplified to a binary format:No DR and DR(Classes 1-4).The results demonstrate that the SVM model outperformed the other approaches in the literature with the same dataset,achieving an excellent accuracy of 96.9%,compared to 95.6%for both the KNN and HGB models.This approach is evaluated by medical health professionals and offers a valuable pathway for the early detection of DR and can be successfully employed as a clinical decision support system.展开更多
Diabetic retinopathy(DR)is a complication of diabetes that can lead to reduced vision or even blindness if left untreated.Therefore,early and accurate detection of this disease is crucial for diabetic patients to prev...Diabetic retinopathy(DR)is a complication of diabetes that can lead to reduced vision or even blindness if left untreated.Therefore,early and accurate detection of this disease is crucial for diabetic patients to prevent vision loss.This study aims to develop a deep-learning approach for the early and precise diagnosis of DR,asmanual detection can be time-consuming,costly,and prone to human error.The classification task is divided into two groups for binary classification:patients with DR(diagnoses 1–4)and those without DR(diagnosis 0).For multi-class classification,the categories are no DR,mild DR,moderate DR,severe DR,and proliferative diabetic retinopathy(PDR).To achieve this,the proposed model utilizes two pre-trained convolutional neural networks(CNNs),specifically ResNet50 and DenseNet-121.Both models were trained and evaluated on fundus images sourced from the widely recognized APTOS dataset,a publicly available resource.,and achieved impressive training and testing accuracies.For binary classification,DenseNet-121 achieved an accuracy of 98.1%,while ResNet50 attained an accuracy of 97.4%.Inmulti-class classification forDR,DenseNet-121 achieved an accuracy of 82.0%,and ResNet50 reached an accuracy of 80.8%.The results are promising and comparable to state-of-the-art techniques in the literature for both binary and multi-label classification of DR.展开更多
文摘Diabetes is a serious health condition that can cause several issues in human body organs such as the heart and kidney as well as a serious eye disease called diabetic retinopathy(DR).Early detection and treatment are crucial to prevent complete blindness or partial vision loss.Traditional detection methods,which involve ophthalmologists examining retinal fundus images,are subjective,expensive,and time-consuming.Therefore,this study employs artificial intelligence(AI)technology to perform faster and more accurate binary classifications and determine the presence of DR.In this regard,we employed three promising machine learning models namely,support vector machine(SVM),k-nearest neighbors(KNN),and Histogram Gradient Boosting(HGB),after carefully selecting features using transfer learning on the fundus images of the Asia Pacific Tele-Ophthalmology Society(APTOS)(a standard dataset),which includes 3662 images and originally categorized DR into five levels,now simplified to a binary format:No DR and DR(Classes 1-4).The results demonstrate that the SVM model outperformed the other approaches in the literature with the same dataset,achieving an excellent accuracy of 96.9%,compared to 95.6%for both the KNN and HGB models.This approach is evaluated by medical health professionals and offers a valuable pathway for the early detection of DR and can be successfully employed as a clinical decision support system.
文摘Diabetic retinopathy(DR)is a complication of diabetes that can lead to reduced vision or even blindness if left untreated.Therefore,early and accurate detection of this disease is crucial for diabetic patients to prevent vision loss.This study aims to develop a deep-learning approach for the early and precise diagnosis of DR,asmanual detection can be time-consuming,costly,and prone to human error.The classification task is divided into two groups for binary classification:patients with DR(diagnoses 1–4)and those without DR(diagnosis 0).For multi-class classification,the categories are no DR,mild DR,moderate DR,severe DR,and proliferative diabetic retinopathy(PDR).To achieve this,the proposed model utilizes two pre-trained convolutional neural networks(CNNs),specifically ResNet50 and DenseNet-121.Both models were trained and evaluated on fundus images sourced from the widely recognized APTOS dataset,a publicly available resource.,and achieved impressive training and testing accuracies.For binary classification,DenseNet-121 achieved an accuracy of 98.1%,while ResNet50 attained an accuracy of 97.4%.Inmulti-class classification forDR,DenseNet-121 achieved an accuracy of 82.0%,and ResNet50 reached an accuracy of 80.8%.The results are promising and comparable to state-of-the-art techniques in the literature for both binary and multi-label classification of DR.
