A Novel Machine Learning Model Based on Exudate Localization to Detect Diabetic Macular Edema

Perdómo, Oscar; Otálora, Sebastian; Rodríguez, Francisco Javier Iglesias; Arévalo, John; González, Fabio A.

doi:10.17077/omia.1057

Cited by 46 publications

(23 citation statements)

References 10 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diabetic Macular Edema (DME) is one of the main complications related to Diabetes, and the largest leading cause of partial and total loss of vision [1]. DME affects central vision, leading to distortion of part of the visual field and blurred vision, even limiting the ability of people to do activities, such as reading, driving or walking [2]. One of the main problems regarding DME diagnosis is its occurrence at any stage of Diabetic Retinopathy (DR), so a precise diagnosis is critical for the correct treatment, avoiding health complications and associated costs [1,2].…”

Section: Introductionmentioning

confidence: 99%

“…DME affects central vision, leading to distortion of part of the visual field and blurred vision, even limiting the ability of people to do activities, such as reading, driving or walking [2]. One of the main problems regarding DME diagnosis is its occurrence at any stage of Diabetic Retinopathy (DR), so a precise diagnosis is critical for the correct treatment, avoiding health complications and associated costs [1,2]. DME diagnosis using eye fundus images is performed by experts looking for signs of retinopathy, retinal thickening and presence of exudates in the macula and the fovea [3,4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

OCT-NET: A convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes

Perdómo

Otálora

González

et al. 2018

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)

Self Cite

View full text Add to dashboard Cite

Diabetic macular edema (DME) is one of the most common eye complication caused by diabetes mellitus, resulting in partial or total loss of vision. Optical Coherence Tomography (OCT) volumes have been widely used to diagnose different eye diseases, thanks to their sensitivity to represent small amounts of fluid, thickness between layers and swelling. However, the lack of tools for automatic image analysis for supporting disease diagnosis is still a problem. Convolutional neural networks (CNNs) have shown outstanding performance when applied to several medical images analysis tasks. This paper presents a model, OCT-NET, based on a CNN for the automatic classification of OCT volumes. The model was evaluated on a dataset of OCT volumes for DME diagnosis using a leave-one-out cross-validation strategy obtaining an accuracy, sensitivity, and specificity of 93.75%.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

OCT-NET: A convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes

Perdómo

Otálora

González

et al. 2018

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Abràmoff et al [91] proposed a supervised end-to-end CNNbased method to recognize DME. Perdomo et al [92] proposed a method that combines EX localization and segmentation with DME detection. EX localization consists of two stages.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey

Asiri

Hussain

Adel

et al. 2019

Artificial Intelligence in Medicine

201

View full text Add to dashboard Cite

Diabetic retinopathy (DR) results in vision loss if not treated early. A computer-aided diagnosis (CAD) system based on retinal fundus images is an efficient and effective method for early DR diagnosis and assisting experts. A computer-aided diagnosis (CAD) system involves various stages like detection, segmentation and classification of lesions in fundus images. Many traditional machine-learning (ML) techniques based on hand-engineered features have been introduced. The recent emergence of deep learning (DL) and its decisive victory over traditional ML methods for various applications motivated the researchers to employ it for DR diagnosis, and many deeplearning-based methods have been introduced. In this paper, we review these methods, highlighting their pros and cons. In addition, we point out the challenges to be addressed in designing and learning about efficient, effective and robust deep-learning algorithms for various problems in DR diagnosis and draw attention to directions for future research.

show abstract

“…e technique was based on k-means segmentation of fundus photographs and preprocessing performed by machine learning approaches based on statistical and low-level features. Moreover, a novel approach was introduced by Perdomo et al [12] for the detection of diabetic macular edema on the basis of exudates' locations using machine learning techniques. Furthermore, Carson Lam et al [13] applied pretrained models, namely, AlexNet and GoogleNet, for the detection of diabetic retinopathy.…”

Section: Introductionmentioning

confidence: 99%

Exudate Detection for Diabetic Retinopathy Using Pretrained Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

In the field of ophthalmology, diabetic retinopathy (DR) is a major cause of blindness. DR is based on retinal lesions including exudate. Exudates have been found to be one of the signs and serious DR anomalies, so the proper detection of these lesions and the treatment should be done immediately to prevent loss of vision. In this paper, pretrained convolutional neural network- (CNN-) based framework has been proposed for the detection of exudate. Recently, deep CNNs were individually applied to solve the specific problems. But, pretrained CNN models with transfer learning can utilize the previous knowledge to solve the other related problems. In the proposed approach, initially data preprocessing is performed for standardization of exudate patches. Furthermore, region of interest (ROI) localization is used to localize the features of exudates, and then transfer learning is performed for feature extraction using pretrained CNN models (Inception-v3, Residual Network-50, and Visual Geometry Group Network-19). Moreover, the fused features from fully connected (FC) layers are fed into the softmax classifier for exudate classification. The performance of proposed framework has been analyzed using two well-known publicly available databases such as e-Ophtha and DIARETDB1. The experimental results demonstrate that the proposed pretrained CNN-based framework outperforms the existing techniques for the detection of exudates.

show abstract

A Novel Machine Learning Model Based on Exudate Localization to Detect Diabetic Macular Edema

Cited by 46 publications

References 10 publications

OCT-NET: A convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes

OCT-NET: A convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes

Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey

Exudate Detection for Diabetic Retinopathy Using Pretrained Convolutional Neural Networks

Contact Info

Product

Resources

About