Deep learning system applicability for rapid glaucoma prediction from fundus images across various data sets

Singh, Law Kumar; Pooja, .; Garg, Hitendra; Khanna, Munish

doi:10.1007/s12530-022-09426-4

Cited by 38 publications

(9 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Singh et al [18] proposed using DL techniques to diagnose glaucoma, which is the second leading cause of permanent blindness. Teir study showed that Inception-ResNet-v2 and Xception models outperformed other models in detecting glaucoma from fundus pictures.…”

Section: Literature Reviewmentioning

confidence: 99%

“…layers to preserve their pretrained features, adding custom fully connected layers for task-specifc learning, and creating a new output layer for your specifc classifcation problem; (6) t ← 1; (7) while t < T do (8) for batch size b � 1 : 32 do (9) Train the model on the augmented training images dataset for each batch b based on the ftness function fit(); (10) Compile the model with fve types of optimizers, which are AdaGrad, Adam, NAdam, AdaMax, and RMSprop; (11) end for (12) Evaluate the training accuracy value and the validation loss value for each epoch t; (13) if the validation loss value does not enhance for certain epochs then go to 7 (14) end if (15) end while (16) Evaluate the trained model on the testing images dataset based on the predict() function to obtain predictions for the testing images;(17) Calculate the accuracy score using the predicted labels and the true labels;(18) Choose one of the two classes;(19) Compare the results of each optimizer and fnd the best to these proposed models;…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning System for Detecting Cardiomegaly Disease Based on CXR Image

Sorour,

Wafa,

Abohany

et al. 2024

International Journal of Intelligent Systems

View full text Add to dashboard Cite

The potential of technology to revolutionize healthcare is exemplified by the synergy between artificial intelligence (AI) and early detection of cardiomegaly, demonstrating the power of proactive intervention in cardiovascular health. This paper presents an innovative approach that leverages advanced AI algorithms, specifically deep learning (DL) technology, for the early detection of cardiomegaly. The methodology consists of five key steps, including data collection, image preprocessing, data augmentation, feature extraction, and classification. Utilizing chest X-ray (CXR) images from the National Institutes of Health (NIH), the study applies rigorous image preprocessing operations, including color transformation and normalization. To enhance model generalization, data augmentation is employed, paving the way for two distinct DL models, a convolutional neural network (CNN) developed from scratch and a pretrained residual network with 50 layers (ResNet50), and adapted to the problem domain. Both models are systematically evaluated with five optimizers, revealing the AdaMax optimizer’s superiority for the CNN model and AdaGrad’s efficacy for the modified ResNet50. The proposed CNN with AdaMax achieves an impressive 99.91% accuracy, outperforming recent techniques in precision, recall, and F1−score. This research underscores the transformative potential of AI in cardiovascular health diagnostics, emphasizing the significance of timely intervention.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

mentioning

confidence: 99%

A Deep Learning System for Detecting Cardiomegaly Disease Based on CXR Image

Sorour,

Wafa,

Abohany

et al. 2024

International Journal of Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Disorders in any of these parts can have severe consequences, ranging from visual impairment to blindness. Among the numerous eye disorders, four prevalent ones often result in vision loss or blindness: Age-related Macular Degeneration (AMD) [ 1 ], Glaucoma [ 2 ], Cataracts [ 3 ], and Diabetic Retinopathy (DR) [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification

Bilal,

Imran,

Baig

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The integration of artificial intelligence (AI) in diagnosing diabetic retinopathy, a major contributor to global vision impairment, is becoming increasingly pronounced. Notably, the detection of vision-threatening diabetic retinopathy (VTDR) has been significantly fortified through automated techniques. Traditionally, the reliance on manual analysis of retinal images, albeit slow and error-prone, constituted the conventional approach. Addressing this, our study introduces a novel methodology that amplifies the robustness and precision of the detection process. This is complemented by the groundbreaking Hierarchical Block Attention (HBA) and HBA-U-Net architecture, which notably propel attention mechanisms in image segmentation. This innovative model refines image processing without imposing excessive computational demands by honing in on individual pixel intricacies, spatial relationships, and channel-specific attention. Building upon this innovation, our proposed method employs a multi-stage strategy encompassing data pre-processing, feature extraction via a hybrid CNN-SVD model, and classification employing an amalgamation of Improved Support Vector Machine-Radial Basis Function (ISVM-RBF), DT, and KNN techniques. Rigorously tested on the IDRiD dataset classified into five severity tiers, the hybrid model yields remarkable performance, achieving a 99.18% accuracy, 98.15% sensitivity, and 100% specificity in VTDR detection, thus surpassing existing methods. These results underscore a more potent avenue for diagnosing and addressing this crucial ocular condition while underscoring AI’s transformative potential in medical care, particularly in ophthalmology.

show abstract

“…Glaucoma is a progressive eye condition that can result in permanent vision damage. [2]. The diagnosis typically entails a comprehensive ophthalmic evaluation, complemented by an array of examinations such as visual field assessment, Optical Coherence Tomography (OCT), tonometry, and fundus photography [3].…”

Section: Introductionmentioning

confidence: 99%

Multi-Modal Imaging-Based Feature Fusion for Accurate Glaucoma Diagnosis with Deep Learning

Krishna¹,

Nagamani²

2023

Preprint

View full text Add to dashboard Cite

Glaucoma, a leading cause of irreversible blindness worldwide, affects over 76 million people currently and is projected to increase to 111.8 million by 2040 according to the World Health Organization. Glaucoma is often asymptomatic and progresses gradually, making early detection and treatment crucial to prevent irreversible vision loss. Ophthalmologists commonly use eye analysis machines such as ophthalmoscopy and fundus photography to obtain scans for accurate diagnosis and treatment of glaucoma. However, clinical-decision support techniques in medical imaging face challenges in interpretability and reliability. To overcome these challenges and accurately detect glaucoma, this study presents a novel Fire Hawk Optimized Deep Learning Based Retinal Disease Grading and Classification (FHODLB-RDGC) utilizing multi-modal feature fusion from Optical Coherence Tomography (OCT) and Fundus images. Radiomics features for OCT images using DL Technique and cup-to-disc ratio for fundus images using NestNet model are extracted using Deep Learning (DL) techniques and merged. The proposed FHODLB-RDGC technique is of great interest in the field of ophthalmology and has demonstrated enhanced retinal disease classification results in extensive simulations on a benchmark database, particularly in accurately diagnosing glaucoma. Therefore, glaucoma, a severe and potentially blinding retinal disease, has the potential of being more accurately recognised and treated early on owing to the FHODLB-RDGC technique.

show abstract

Deep learning system applicability for rapid glaucoma prediction from fundus images across various data sets

Cited by 38 publications

References 63 publications

A Deep Learning System for Detecting Cardiomegaly Disease Based on CXR Image

A Deep Learning System for Detecting Cardiomegaly Disease Based on CXR Image

Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification

Multi-Modal Imaging-Based Feature Fusion for Accurate Glaucoma Diagnosis with Deep Learning

Contact Info

Product

Resources

About