Learning ensemble classifiers for diabetic retinopathy assessment

Saleh, Emran; Błaszczyński, Jerzy; Moreno, Antonio; Valls, Aïda; Romero-Aroca, Pedro; Riva-Fernández, Sofia de la; Słowiński, Roman

doi:10.1016/j.artmed.2017.09.006

Cited by 70 publications

(44 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Considering a dataset containing training samples, the sections can be expressed as: (6) where is the th input sample and is the corresponding output. Now, if we consider a decision tree with index within the ensemble and a function that associates input to its corresponding region in the partition, the approximate output can be calculated using [12]: (7) where is a function defined by: (8) where is the indicator function and defined as:…”

Section: H Classification Of Retinal Images Using Et Classifiermentioning

confidence: 99%

“…Later that year, [7] outlined a method incorporating CNN and Random Forest (RF) for retinal blood vessel segmentation. In 2017, [8] proposed a method for DR assessment using a fuzzy RF and dominance-based rough set balanced rule ensemble. The proposed method differs from these procedures in terms of the source of the retinal images, the employed image processing techniques, and type of features extracted from the images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Early Blindness Detection Based on Retinal Images Using Ensemble Learning

Sikder

Chowdhury

Arif

et al. 2019

2019 22nd International Conference on Computer and Information Technology (ICCIT)

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is the primary cause of vision loss among grown-up people around the world. In four out of five cases having diabetes for a prolonged period leads to DR. If detected early, more than 90% of the new DR occurrences can be prevented from turning into blindness through proper treatment. Despite having multiple treatment procedures available that are well-capable to deal with DR, the negligence and failure of early detection cost most of the DR patients their precious eyesight. The recent developments in the field of Digital Image Processing (DIP) and Machine Learning (ML) have paved the way to use machines in this regard. The contemporary technologies allow us to develop devices capable of automatically detecting the condition of a person's eyes based on their retinal images. However, in practice, several factors hinder the quality of the captured images and impede the detection outcome. In this study, a novel early blind detection method has been proposed based on the color information extracted from retinal images using an ensemble learning algorithm. The method has been tested on a set of retinal images collected from people living in the rural areas of South Asia, which resulted in a 91% classification accuracy.

show abstract

Section: H Classification Of Retinal Images Using Et Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Early Blindness Detection Based on Retinal Images Using Ensemble Learning

Sikder

Chowdhury

Arif

et al. 2019

2019 22nd International Conference on Computer and Information Technology (ICCIT)

View full text Add to dashboard Cite

show abstract

“…[3] is the most hurtful ophthalmic circumstance enticed by DM in the event that it couldn't be recognized before and fittingly treated [1]. By means of DR [2] [3] is a significant elucidation of vision defeat between individuals suffering from diabetes [4], they must be observed These days, Computer Aided Diagnostic framework (CAD) [8] [9] is accustomed so as with analyze DR by separating optic plate by assessing previously mentioned issues in the prevailing frameworks. Also, with respect to the CAD frameworks [10] to help clinicians in their procedure of basic direction has expanded, along these lines encouraging speedier and increasingly exact demonstrative choices with less discrepancy.…”

Section: Fig 1 Basic Details Of Retinal Image and Structure Ofmentioning

confidence: 99%

“…In 2018, Saleh et al [2], proposed ensemble based classifiers with two classes of ensemble classifiers. These classifiers utilize a micro level arrangement of attributes that imply significant hazard imperatives to discover the hazard possibility of patients of creating DR. From the experimentation results, explicitness and sensitivity were found to achieve better improvement of 80%.…”

Section: Fig 1 Basic Details Of Retinal Image and Structure Ofmentioning

confidence: 99%

Tri Concomitant Local Feature Learning for Diabetic Retinopathy Classification

Randive,

Senapati

2019

IJEAT

View full text Add to dashboard Cite

In this paper, we have proposed a new technique entitled as Transformed Directional Tri Concomitant Triplet Patterns with Artificial Neural Network is proposed for Diabetic Retinopathy Classification. TdtCTp consist of three stages to obtain detail directional information about pixel progression. In first stage, structural rule based approach is proposed to extract directional information in various direction. Further, in second stage, microscopic information and correlation between each sub-structural element are extracted by using concomitant conditions. Finally, minute directional intensity variation information and correlation between the sub-structural elements are extracted by integrating first two stages. After feature extraction, the extracted feature is used as input to the artificial neural network. To the best of our knowledge, this is the first learning based approach for diabetic retinopathy classification. Effectiveness of the proposed method is evaluated in terms of average precision and compared with existing state-of-the-art methods. The experimental analysis shows that the proposed method is achieved significant performance compared to other methods.

show abstract

“…Junior et al [44] proposed a data stream ensemble classifier named Iterative Boosting Streaming ensemble (IBS), able to cope with classification tasks in streaming data environments. Saleh et al [45] proposed ensemble classifier for diabetic retinopathy (DR) detection. They used fuzzy random forests (FRF) and dominance-based rough set on SRJUH dataset.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Medical Decision–Support Framework Based on a Heterogeneous Ensemble Classifier for Diabetes Prediction

et al. 2019

View full text Add to dashboard Cite

Early diagnosis of diabetes mellitus (DM) is critical to prevent its serious complications. An ensemble of classifiers is an effective way to enhance classification performance, which can be used to diagnose complex diseases, such as DM. This paper proposes an ensemble framework to diagnose DM by optimally employing multiple classifiers based on bagging and random subspace techniques. The proposed framework combines seven of the most suitable and heterogeneous data mining techniques, each with a separate set of suitable features. These techniques are k-nearest neighbors, naïve Bayes, decision tree, support vector machine, fuzzy decision tree, artificial neural network, and logistic regression. The framework is designed accurately by selecting, for every sub-dataset, the most suitable feature set and the most accurate classifier. It was evaluated using a real dataset collected from electronic health records of Mansura University Hospitals (Mansura, Egypt). The resulting framework achieved 90% of accuracy, 90.2% of recall = 90.2%, and 94.9% of precision. We evaluated and compared the proposed framework with many other classification algorithms. An analysis of the results indicated that the proposed ensemble framework significantly outperforms all other classifiers. It is a successful step towards constructing a personalized decision support system, which could help physicians in daily clinical practice.

show abstract

Learning ensemble classifiers for diabetic retinopathy assessment

Cited by 70 publications

References 42 publications

Early Blindness Detection Based on Retinal Images Using Ensemble Learning

Early Blindness Detection Based on Retinal Images Using Ensemble Learning

Tri Concomitant Local Feature Learning for Diabetic Retinopathy Classification

A Comprehensive Medical Decision–Support Framework Based on a Heterogeneous Ensemble Classifier for Diabetes Prediction

Contact Info

Product

Resources

About