A deep learning-based smartphone app for real-time detection of five stages of diabetic retinopathy

Majumder, Sharmin; Elloumi, Yaroub; Akil, Mohamed; Kachouri, Rostom; Kehtarnavaz, Nasser

doi:10.1117/12.2557554

Cited by 37 publications

(24 citation statements)

References 15 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the system can be extended to provide a DR classification whatever the stage is, through detection all DR lesions. The classifier is able to be replace by a deep learning architecture, as the one proposed in [37]. Elsewhere, the timing performance can be improved by taking benefit from the parallelism offered by recent smartphone architectures.…”

Section: Execution Timementioning

confidence: 99%

See 1 more Smart Citation

Fast and accurate mobile-aided screening system of moderate diabetic retinopathy

Elloumi

Mbarek

Boukadida

et al. 2021

Thirteenth International Conference on Machine Vision

Self Cite

View full text Add to dashboard Cite

The Diabetic Retinopathy (DR) is a worldwide eye disease that causes visual damages and can leads to blindness. Therefore, the detection of the DR in the early stages is highly recommended. However, a delay is registered for ensuring early DR diagnosis which caused by the low-rate of the ophthalmologists, the deficiency of diagnosis equipment and the lack of mobility of elderly patients.In this paper, the main objective is to provide a mobile-aided screening system of moderate DR. Within this aim, we propose a classifier-based method which is based on detecting the Hard Exudate (HE) lesions that occur in moderate DR stage. A set of features are extracted to ensure an accurate and robust detection with respect to modest quality of fundus images. Moreover, the detection is provided in a low complexity processing to be suitable for mobile device. The aimed system corresponds to the implementation of the method on a smartphone associated to an optical lens for capturing fundus image. The system reached satisfactory screening performance where an accuracy of 98.36%, a sensitivity of 100% and specificity of 96.45% are registered using the DIARETDB1 fundus image databases. Moreover, the screening is performed in an average execution time of 2.68 seconds.

show abstract

Section: Execution Timementioning

confidence: 99%

“…The execution time was evaluated only when method was run in desktop. Our first work described in [37] was aimed to provide DR grading of classical fundus images when an overall accuracy of 87.4% was achieved. The method was implemented in smartphone where classification takes between 200 and 250 milli-seconds.…”

Section: Introductionmentioning

confidence: 99%

Fast and accurate mobile-aided screening system of moderate diabetic retinopathy

Elloumi

Mbarek

Boukadida

et al. 2021

Thirteenth International Conference on Machine Vision

Self Cite

View full text Add to dashboard Cite

show abstract

“…Classification of the severity stages of DR were presented in [41]- [43]. In [44], a deep neural network for four-degree classification of DR was covered.…”

Section: Introductionmentioning

confidence: 99%

“…In [46], several deep learning models (AleXNet, VggNet, GoogleNet, ResNet) were compared for DR classification using the Kaggle EyePACS dataset with VggNet achieving the best accuracy. A transfer learning-based smartphone app using a pretrained Xception model was previously developed for the classification of the five stages of DR in [43] by our research group. This app runs in real-time on smartphone platforms based on fundus images that are captured via commercially available lenses that snap onto smartphones in front of their cameras.…”

Section: Introductionmentioning

confidence: 99%

Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy

Majumder¹,

Kehtarnavaz

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Early diagnosis and treatment of diabetic retinopathy (DR) can reduce the risk of vision loss. There are five stages of DR consisting of no DR, mild DR, moderate DR, severe DR, and proliferate DR. This paper presents a multitask deep learning model to detect all the five stages of DR more accurately than existing methods. The developed multitask model consists of one classification model and one regression model, each with its own loss function. After training the regression model and the classification model separately, the features extracted by these two models are concatenated and inputted to a multilayer perceptron network to classify the five stages of DR. A modified Squeeze Excitation Densely Connected deep neural network is also developed as part of this multitasking approach. The developed multitask model is applied to the two large Kaggle datasets of APTOS and EyePACS. The results obtained indicate that the developed multitask model achieved a weighted Kappa score of 0.90 and 0.88 for the APTOS and EyePACS datasets, respectively. In addition, the micro and macro average area under the receiver operating characteristic (ROC) curve was found to be 0.96, and 0.93, respectively, which are higher than existing methods for detecting the five stages of DR.INDEX TERMS Diabetic Retinopathy (DR), eye fundus images, five stages of diabetic retinopathy, multitasking deep neural network, squeeze excitation densely connected network.

show abstract

“…[21][22][23] However, those images are characterized by a moderate quality, caused by the handheld aspect of the capture process. Within this context, several methods have been put forward and implemented into smartphones to detect ocular pathologies, such as DR grading 22,24 and glaucoma screening. 25,26 Our objective consists in proposing a novel method that detects NV from smartphone-captured fundus images.…”

Section: Introductionmentioning

confidence: 99%

Mobile‐aided screening system for proliferative diabetic retinopathy

Boukadida

Elloumi

Akil

et al. 2021

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

NeoVascularization (NV) occurs in the Proliferative Diabetic Retinopathy (PDR) stage, where the development progress of new vessels presents a high risk for severe vision loss and blindness. Therefore, early NV detection is primordial to preserve patient's vision. Several automated methods have been proposed to detect the NV on retinograph-captured fundus images. However, their employment is constrained by the reduced ophthalmologist-per-person ratio and the expensive equipment for image capturing. This paper presents a novel method for NV detection in smartphone-captured fundus images. The implementation of the method on a smartphone having an optical lens for fundus capturing leads to a Mobiles-Aided-Screening system of PDR (MAS-PDR). The challenge is to ensure accurate and robust detection even with moderate quality of fundus image, on reduced execution time.Within this objective, we identify the major criteria of neovascularized vessels which are tortuosity, width, bifurcation, and density. Our main contribution consists in proposing a sharp feature to reflect each criterion on reduced computational complexity processing. Therefore, the features are provided to a random forest classifier to deduce the PDR stage.A dataset raised from publicly databases is used on a 10-cross validation process where 98.69% accuracy, 97.73% sensitivity, and 99.12% specificity are achieved. To evaluate the robustness, the same experimentation is repeated after applying motion blur filters to the fundus image dataset, where 98.91% accuracy, 96.75% sensitivity, and 100% specificity are deduced. Moreover, NV screening is performed under 3 s when executed in smartphone devices demonstrating the appropriateness of our method to MAS-PDR.

show abstract

A deep learning-based smartphone app for real-time detection of five stages of diabetic retinopathy

Cited by 37 publications

References 15 publications

Fast and accurate mobile-aided screening system of moderate diabetic retinopathy

Fast and accurate mobile-aided screening system of moderate diabetic retinopathy

Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy

Mobile‐aided screening system for proliferative diabetic retinopathy

Contact Info

Product

Resources

About