2-D Compact Variational Mode Decomposition- Based Automatic Classification of Glaucoma Stages From Fundus Images

Parashar, Deepak; Agrawal, Dheeraj

doi:10.1109/tim.2021.3071223

Cited by 39 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parashar et al [6] and Khan et al [7] also applied nonstructural extractors to describe the images and classified them using traditional ML methods. Parashar et al [6] proposed a 2-D compact variational mode decomposition (2-DC-VMD).…”

Section: Related Workmentioning

confidence: 99%

A Comparative Analysis of Glaucoma Feature Extraction and Classification Techniques in Fundus Images

Assis

Cortez

2023

JCIS

View full text Add to dashboard Cite

Glaucoma is an asymptomatic chronic eye disease that, if not treated in the early stages, can lead to blindness. Therefore, detection in the early stages is essential to preserve the patient’s quality of life. Thus, it is crucial to have a noninvasive method capable of detecting this disease through images in the fundus examination. In the literature, datasets are available with fundus images; however, only a few have glaucoma images and labels. Learning from an imbalanced dataset challenges machine learning, which limits supervised learning algorithms. We compared approaches to extract and classify three public datasets with 2390 images: ACRIMA, REFUGE, and RIM-ONE DL. First, we evaluated extracted features non-structural from HOG, LBP, Zernike, and Gabor filters and features obtained from transfer learning. Then, we classified them with Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB). Finally, each classifier was evaluated individually and in a voting classifier (VOT). We extracted and classified features from transfer learning models in the same process. Also, they were classified using traditional machine learning. Due to class imbalance, we undersampled the majority class normal by applying the following methods: random choice, near miss, and cluster centroid. We also evaluated our model using a cross-dataset approach. Therefore, we efficiently identified glaucoma in different fundus images using network VGG19 and a voting classifier. In addition, balancing classes reduced false negatives and improved model quality. Our approach achieved an average F1-score equals to 94.69%, accuracy rate of 94.77%, precision of 96.10%, recall of 93.45%, and specificity of 96.08%.

show abstract

Section: Related Workmentioning

confidence: 99%

A Comparative Analysis of Glaucoma Feature Extraction and Classification Techniques in Fundus Images

Assis

Cortez

2023

JCIS

View full text Add to dashboard Cite

show abstract

“…If the FDN of an image is high, the texture roughness present in the image is high. FDN has shown good performance in glaucoma diagnosis in [16], [29]. Q r in Table II is used to scale up and scale down the texture image by factor r. Moment inversion features have been used in many works to diagnose glaucoma automatically, but such general moments show redundant information.…”

Section: F Texture Features From Lpb-sbimentioning

confidence: 99%

“…Contribution of this work are highlighted below: [12], [13] , flexible analytic wavelet transform (FAWT) [14], empirical mode decomposition (EMD) [17], variational mode decomposition (VMD) [15], [16], and empirical wavelet transform (EWT) [18], [19]. DWT has provided a significant contribution in the field of biomedical signal processing and image processing.…”

Section: Introductionmentioning

confidence: 99%

“…Use of FBSE domain for implementation of existing conventional signal decomposition method has shown improvement in decomposition performance [20], [22]- [26]. • Full, optical disc, and polar fundus image modalities based analysis: authors in [14]- [16] have used full fundus images to retain all the information present in the image while diagnosing glaucoma. Few authors have also first segmented the optic disc region from the full fundus image or directly taken the optic disc region and used it in the classification process [4]- [6], [21].…”

Section: Introductionmentioning

confidence: 99%

“…We have further used all three channels (RGB) in the feature extraction step to retain all the information present in the image. [16], [19], [29]. Due to the orthogonality of the Zernike moment, it can provide non-redundant features from moments, which is missing in non-orthogonal moment features [30].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Primary and Secondary Glaucoma Using 2D-FBSE-EWT From Different Fundus Image Modalities

Chaudhary¹,

Jain²,

Damani³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Automated screening of glaucoma stages from retinal fundus images using BPS and LBP based GLCM features

Patel

Kashyap

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Glaucoma is an eye disease in which the retinal nerve fibers are irreversibly damaged. Early identification of glaucoma is essential because it may slow the progression of the illness. The clinical treatments and medical imaging methods that are currently available are all manual and require expert supervision. An automated glaucoma diagnosis system that is fast, accurate, and helps to reduce the load on professionals is necessary for mass screening. In our proposed work, a novel approach based on bit‐plane slicing (BPS), local binary pattern (LBP), and gray‐level co‐occurrence matrix (GLCM) is used. First, fundus images are separated into channels like red, green, and blue, and these separated channels are split into plans using BPS. Then, LBP images are obtained from selected green channel images. Second, we extract features based on GLCM from LBP images. Finally, using a least‐squares support vector machine classifier, the higher ranked features are employed to classify glaucoma stages. According to the findings of the experiments, our model outperformed state‐of‐the‐art approaches for glaucoma classification. Using 10‐fold cross‐validation, this model achieved an improved classification accuracy of 95.04%, specificity of 96.37%, and sensitivity of 93.77%. We conducted many relative experiments with deep learning and traditional machine learning‐based models to test our proposed methodology. Compared to existing glaucoma classification approaches, the new method has been shown to be more efficient.

show abstract

2-D Compact Variational Mode Decomposition- Based Automatic Classification of Glaucoma Stages From Fundus Images

Cited by 39 publications

References 45 publications

A Comparative Analysis of Glaucoma Feature Extraction and Classification Techniques in Fundus Images

A Comparative Analysis of Glaucoma Feature Extraction and Classification Techniques in Fundus Images

Detection of Primary and Secondary Glaucoma Using 2D-FBSE-EWT From Different Fundus Image Modalities

Automated screening of glaucoma stages from retinal fundus images using BPS and LBP based GLCM features

Contact Info

Product

Resources

About