MétaCan
Menu
Back to cohort
Record W4409944661 · doi:10.35882/jeeemi.v7i2.706

A Novel Deep Learning Framework for Enhanced Glaucoma Detection Using Attention-Gated U-Net, Deep Wavelet Scattering, and Vision Transformers

2025· article· en· W4409944661 on OpenAlex
Vijaya Krishnamoorthy, S Sivanantham, V Akshaya, Sivakumar Depuru, M. Manikandan

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Electronics Electromedical Engineering and Medical Informatics · 2025
Typearticle
Languageen
FieldMedicine
TopicRetinal Imaging and Analysis
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsDeep learningGlaucomaTransformerArtificial intelligenceWaveletComputer sciencePattern recognition (psychology)MedicineEngineeringOphthalmologyElectrical engineering

Abstract

fetched live from OpenAlex

Globally, Glaucoma is a major cause of permanent blindness, and maintaining eyesight depends on early detection. Here, a brand-new deep-learning system for glaucoma prediction. In this work, we offer a novel deep-learning approach for enhanced glaucoma prediction that uses a denoising generative adversarial network for preprocessing the input image is provided, later the segmentation is carried out by Attention-Gated U-Net with Dilated Convolutions to segment the optic cup and optic disc. Feature Extraction Using a Deep Wavelet Scattering Network and finally the glaucoma classification is carried out by the Vision Transformers. An attention-gated U-Net with dilated convolutions for segmentation, which improves the accuracy of optic disc and cup boundaries by 7% compared to conventional U-Net methods is introduced. A Deep Wavelet Scattering Network (DWSN) for feature extraction that achieves a 5% improvement in feature discrimination over conventional CNNs by capturing multiscale texture and structural information is suggested. Lastly, ViT, which is based on transfer learning, is used for classification; it has a 94.6% accuracy rate, a 93.8% sensitivity rate, and a 95.2% specificity rate. The suggested approach outperformed CNN-based models by improving by about 4% on all criteria. The system achieved an F1 score of 0.95 and an AUC (Area Under Curve) of 0.96 when tested on publicly accessible glaucoma datasets. Multi-stage deep-learning processing for glaucoma prediction by integrating a denoising generative adversarial network for image preprocessing, Attention-Gated U-Net with Dilated Convolutions for exact optic cup and disc segmentation, deep wavelet scattering for feature extraction, and Vision Transformers for glaucoma classification.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.982
Threshold uncertainty score0.775

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.004
GPT teacher head0.273
Teacher spread0.269 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it