Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Elloumi, Yaroub

doi:10.1002/ima.22722

Cited by 15 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, this method is the first attempt to differentiate fundus images into normal, dry AMD, and wet AMD classes. Furthermore, this suggested contribution is able to be implemented into a mobile End-To-End system for retinal pathology screening [28], [29].…”

Section: Discussionmentioning

confidence: 99%

Automated Diagnosis of Retinal Neovascularization Pathologies from Color Retinal Fundus Images

Boukadida¹,

Elloumi²,

Kachouri³

et al. 2022

Advances in Computer Graphics

Self Cite

View full text Add to dashboard Cite

The retinal Neo-Vascularization (NV) is the abnormal growth of new blood vessels in the retina, which leads to a severe reduction on visual acuity and blindness. It is a main biomarker to screening several diseases, where the Proliferative Diabetic Retinopathy (PDR) and Wet Age-related Macular Degeneration (WAMD) are the most common ones. The NV severity requires a fast screening to avoid severe degradation. However, it is labor intensive and timeconsuming for the ophthalmologists. In this paper, we suggest an automated screening method that automatically detects NV from fundus photography and classify it as PDR, WAMD and Healthy. For this purpose, the image is preprocessed and then provided a transfer learned model of the VGG16 neural network. The method was evaluated using a dataset containing 395 fundus photographs of retinal images where an accuracy of 98.30%, a sensitivity of 98.66%, a specificity of 98.33% were achieved. In addition, the areas under curve in terms of classes were between 98% and 100%.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Diagnosis of Retinal Neovascularization Pathologies from Color Retinal Fundus Images

Boukadida¹,

Elloumi²,

Kachouri³

et al. 2022

Advances in Computer Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

“…What's more, these deep learning methods use only one model to highlight lung lobe representation, which may lead to inaccurate segmentation in some CT scans. As a result, an ensemble learning approach is presented to combine multiple inducers to make a final decision on lung lobe segmentation 13,33,34 …”

Section: Related Workmentioning

confidence: 99%

“…As a result, an ensemble learning approach is presented to combine multiple inducers to make a final decision on lung lobe segmentation. 13,33,34 This article is organized as follows. Materials and methods are described in Section 3.…”

Section: Related Workmentioning

confidence: 99%

Lung lobe segmentation in computed tomography images based on multi‐feature fusion and ensemble learning framework

Peng

Zhang

2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Lung lobe segmentation in computed tomography (CT) images can be regarded as essential supporting information for the diagnosis and treatment of lung diseases, yet it is a challenging uncertainty for the complex segmentation task due to the diverse structures like indistinguishable pulmonary arteries and veins, unpredictable pathological deformation and blurring pulmonary fissures. To circumvent these challenges, we present a productive deep learning network based on multi‐feature fusion and ensemble learning approach to highlight pulmonary fissure representation and suppress other structures for lung lobe segmentation in CT images. Considering that pulmonary fissures are the physical boundaries of lung lobes, a multi‐feature fusion approach is presented to integrate original images, enhanced fissure magnitude images, and enhanced fissure orientation images to highlight shape representation for semantic segmentation. In addition, a deep‐supervised ensemble learning network is employed to combine multiple inducers for lung lobe segmentation improvement. The performance of the proposed deep learning model is validated in experiments with an available dataset, it acquired a high IoU value and a low Hausdorff distance compared with manual references. Experimental results demonstrate that the proposed computational model based on multi‐feature fusion and deep‐supervised ensemble learning framework has an improved predictive performance than many state‐of‐the‐art deep neural networks in lung lobe segmentation.

show abstract

“…The applied upsampling layers are parameterized by a kernel size "nxn=2 × 2" and a stride "s=2", allows reproducing the spatial size and information of the image. Thus, the output feature map size can be calculated as (4), where "M" corresponds to the input image size and the padding is set to zero.…”

Section: Proposed Networkmentioning

confidence: 99%

“…Therefore, an automatic and an accurate vessel segmentation is required. With the development of deep learning and especially Convolutional Neural Networks (CNNs), various architecture are proposed and have been applied in various medical domains [1,4,5]. Certain of these architectures have been propounded for the segmentation tasks such as [6].…”

Section: Introductionmentioning

confidence: 99%

Extended U-net for Retinal Vessel Segmentation

Boudegga

Elloumi

Kachouri

et al. 2022

Advances in Computational Collective Intelligence

View full text Add to dashboard Cite

The retinal vascular tree is an important biomarker for the diagnosis of ocular dis-ease, where an efficient segmentation is highly required. Recently, various standard Convolutional Neural Networks CNN dedicated for segmentation are applied for retinal vessel segmentation. In fact, retinal blood vessels are presented in different retinal image resolutions with a complicated morphology. Thus, it is difficult for the standard configuration of CNN to guarantee an optimal feature extraction and efficient segmentation whatever the image resolution is. In this paper, new retinal vessel segmentation approach based on deep learning architecture is propounded. The idea consists of enlarging the kernel size of convolution layer in order to cover the vessel pixels as well as more neighbors for extracting features. Within this objective, our main contribution consists of identifying the kernel size in correlation with retinal image resolution through an experimental approach. Then, a novel U-net extension is proposed by using convolution layer with the identified kernel size. The suggested method is evaluated on two public databases DRIVE and HRF having different resolutions, where higher segmentation performances are achieved respectively with 5*5 and 7*7 convolution kernel sizes. The average accuracy and sensitivity values for DRIVE and HRF databases are respectively in the order of to 0.9785, 0.8474 and 0.964 and 0.803 which outperform the segmentation performance for the standard U-net.

show abstract

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Cited by 15 publications

References 53 publications

Automated Diagnosis of Retinal Neovascularization Pathologies from Color Retinal Fundus Images

Automated Diagnosis of Retinal Neovascularization Pathologies from Color Retinal Fundus Images

Lung lobe segmentation in computed tomography images based on multi‐feature fusion and ensemble learning framework

Extended U-net for Retinal Vessel Segmentation

Contact Info

Product

Resources

About