Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images

Kausu, T.R.; Gopi, Varun P.; Wahid, Khan A.; Doma, Wangchuk; Niwas, S. Issac

doi:10.1016/j.bbe.2018.02.003

Cited by 81 publications

(24 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the proposed work, the wavelet features are extracted by applying ADTCWT on fundus images. In anisotropic decomposition, the sub-bands are decomposed into vertically or horizontally only [6]. The DTCWT sub-bands are directional.…”

Section: A Feature Extraction Techniquesmentioning

confidence: 99%

“…While using the SVM classifier, the system produced an accuracy of 86% with High-Resolution Fundus (HRF) images and 84% with DIARETDB0 datasets. The glaucoma detection and its classification from retinal images by combining clinical and multi-resolution features are described in [6]. The glaucoma identification is performed by extracting features using the ADTCWT method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Binary and Multiclass Classification of Diabetic Retinopathy Using Haralick and Multiresolution Features

et al. 2020

Self Cite

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is considered as the complication of Diabetes Mellitus that damages the blood vessels in the retina. This is characterized as a serious vision-threatening problem in most of the diabetic subjects. Effective automatic classification of diabetic retinopathy is a challenging task in the medical field. The feature extraction plays an eminent role in the effective classification of disease. The proposed work focuses on the extraction of Haralick and Anisotropic Dual-Tree Complex Wavelet Transform (ADTCWT) features that can perform reliable DR classification from retinal fundus images. The Haralick features are based on second-order statistics and ADTCWT reliably extracts the directional features in images. The proposed work concentrates on both binary classification as well as multiclass classification of DR. The system is evaluated across various classifiers such as Support Vector Machine (SVM), Random Forest, Random Tree, J48 classifiers by giving input image features extracted from the MESSIDOR, KAGGLE and DIARETDB0 databases. The performances of the classifiers are analyzed by comparing specificity, precision, recall, False Positive Rate (FPR) and accuracy values for each classifier. The evaluation results show that by applying the proposed feature extraction method, Random Forest outperforms all the other classifiers with an average accuracy of 99.7% and 99.82% for binary and multiclass classification respectively. INDEX TERMS DR binary classification, DR multiclass classification, retinal fundus images, HARALICK, ADTCWT, 10-fold cross validation. S. GAYATHRI received the B.Tech. degree in electronics and communication engineering from the Vivekandha College of Engineering, under Anna university, Chennai, in 2012, and the M.Tech. degree in advanced communication and information systems from the Rajiv Gandhi Institute of Technology, under Mahatma Gandhi University, Kottayam, in 2014. She is currently pursuing the Ph.D. degree in biomedical image processing with the National Institute of Technology at Tiruchirappalli, Tiruchirappalli, India. Her research interests include bio medical signal and image processing, machine learning, and deep learning.

show abstract

Section: A Feature Extraction Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated Binary and Multiclass Classification of Diabetic Retinopathy Using Haralick and Multiresolution Features

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…CNNs representing Deep Learning (DL) architectures have encouraging results for image recognition applications, including medical imaging [12,13]. In addition, DL models have also demonstrated impressive results for difficult applications such as handwritten character recognition [34], object detection [35], natural language processing [36], and speech recognition [37].…”

Section: ) Glaucoma Diagnosis Using Deep Learning Modelsmentioning

confidence: 99%

Multi-modal classifier fusion with feature cooperation for glaucoma diagnosis

Benzebouchi

Azizi

Ashour

et al. 2019

Journal of Experimental & Theoretical Artificial Intelligen

View full text Add to dashboard Cite

Background: Glaucoma is a major public health problem that can lead to an optic nerve lesion, requiring systematic screening in the population over 45 years of age. The diagnosis and classification of this disease have had a marked and excellent development in recent years, particularly in the machine learning domain. Multimodal data have been shown to be a significant aid to the machine learning domain, especially by its contribution to improving data driven decisionmaking. Method: Solving classification problems by combinations of classifiers has made it possible to increase the robustness as well as the classification reliability by using the complementarity that may exist between the classifiers. Complementarity is considered a key property of multimodality. A Convolutional Neural Network (CNN) works very well in pattern recognition and has been shown to exhibit superior performance, especially for image classification which can learn by themselves useful features from raw data. This article proposes a multimodal classification approach based on deep Convolutional Neural Network and Support Vector Machine (SVM) classifiers using multimodal data and multimodal feature for glaucoma diagnosis from retinal fundus images from RIM-ONE dataset. We make use of handcrafted feature descriptors such as the Gray Level Co-Occurrence Matrix, Central Moments and Hu Moments to cooperate with features automatically generated by the CNN in order to properly detect the optic nerve and consequently obtain a better classification rate, allowing a more reliable diagnosis of glaucoma. Results: The experimental results confirm that the combination of classifiers using the BWWV technique is better than learning classifiers separately. The proposed method provides a computerized diagnosis system for glaucoma disease with impressive results comparing them to the main related studies that allow us to continue in this research path.

show abstract

“…A new glaucoma Fuzzy Expert Systems for early glaucoma diagnosis was presented in [17] by considering both instrumental parameters and risk factors resulting in valuable identification suspected to have glaucoma. Yet another combination of clinical and multi resolution features using fundus images was presented in [18]. Computer-aided detection (CAD) was presented in [19] to make reliable and fast glaucoma diagnosis based on optic nerve features.…”

Section: Related Workmentioning

confidence: 99%

Automatic Detection of Glaucoma based on Refined Complete Local Binary Pattern and Random Forest Classification Method

2019

IJITEE

View full text Add to dashboard Cite

Glaucoma is considered to be one of the main root causes of blindness. As it shows no symptoms, if not properly identified at the correct time would result in the loss of vision. This paper proposes a method for the Automatic Detection of Glaucoma based on Refined Complete Local Binary Pattern and Random Forest Classification Method(RCLBP-RFC), which identifies the presence or the absence of glaucoma in a patient at an early stage. The first step is use to convert a color image into gray scale image and the second step we use Neighborhood Fuzzy K Means Clustering to segment Optic Disc(OD) and Optic Cup(OC). In the third step Statistical Optimized and Restoration model is use to extract the enhanced images using the restoration technique. In the Fourth step we exploit Refined Complete Local Binary Patterns Extraction to extract the most relevant features and finally, Random Forest Classification methods are involved to classify the features as normal, abnormal or early detected glaucoma. The experiments show that our RCLBP-RFC method achieves state-of-the-art OD and OC segmentation result on DRIONS dataset. Experimental results indicates that the proposed method identifies the presence or absence of glaucoma more precisely than other existing methods in terms of computational time and complexity, and accuracy

show abstract

Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images

Cited by 81 publications

References 12 publications

Automated Binary and Multiclass Classification of Diabetic Retinopathy Using Haralick and Multiresolution Features

Automated Binary and Multiclass Classification of Diabetic Retinopathy Using Haralick and Multiresolution Features

Multi-modal classifier fusion with feature cooperation for glaucoma diagnosis

Automatic Detection of Glaucoma based on Refined Complete Local Binary Pattern and Random Forest Classification Method

Contact Info

Product

Resources

About