Citation :

Z Abdul Basith, M Sulthan Ibrahim, "Visual Interpretability in Glaucoma Detection Using Grad-CAM-Driven Transfer Learning," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 5, pp. 35-51, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I5P103

Abstract

Glaucoma is a progressive eye disease characterized by damage to the optic nerve. Early detection and management are crucial to preserving vision, making the prediction of glaucoma risk. To improve accurate prediction, a Gradient-weighted Class Activation Mapped Deep Transfer Learning (GWCAMDTL) model is developed with higher accuracy of glaucoma prediction and lesser time. Retinal fundus images are collected from a dataset in image acquisition. Deep transfer learning involves adapting a pre-trained deep learning model for performing glaucoma prediction. Initially, layers in the pre-trained model are usually frozen to preserve the learned features from the infected regions. Transferring information from previously learned results by the pre-trained mode to new tasks has the potential to significantly improve feature learning efficiency by the congruence correlation coefficient. Gradient-weighted Class Activation Mapping generates visual explanations for predictions made by the model. Fine-tuning layers is a crucial part of transfer learning. During fine-tuning for glaucoma prediction, the model weights of certain layers are updated to better fit specific characteristics of the new glaucoma dataset, leading to a reduction in both training and validation error. This approach improves the accuracy of glaucoma prediction by applying the strengths of the pre-trained model and adapting it to the clinical features of retinal fundus images. Experiments are conducted using various evaluation metrics. Results of GWCAMDTL achieve higher accuracy by 96%, precision by 0.95, sensitivity by 0.96, F1 score by 0.95, and specificity by 0.93 with reduced time by 27% as well as error by 0.042 than existing methods.

Keywords

Glaucoma Disease Prediction, Deep Transfer Learning, Multilayer Perceptron Classifier, Congruence Correlation Coefficient, Gradient-Weighted Class Activation Mapping.

References

[1] Yeganeh Madadi, Hashem Abu-Serhan, and Siamak Yousefi, “Domain Adaptation-based Deep Learning Models for Forecasting and Diagnosis of Glaucoma Disease,” Biomedical Signal Processing and Control, vol. 92, pp. 1-14, 2024.

[CrossRef] [Google Scholar] [Publisher Link]

[2] Abeer Aljohani, and Rua Y. Aburasain, “A Hybrid Framework for Glaucoma Detection Through Federated Machine Learning and Deep Learning Models,” BMC Medical Informatics and Decision Making, vol. 24, no. 1, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Sumaiya Pathan et al., “An Automated Classification Framework for Glaucoma Detection in Fundus Images using Ensemble of Dynamic Selection Methods,” Progress in Artificial Intelligence, vol. 12, no. 3, pp. 287-301, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Jahanzaib Latif et al., “ODGNet: A Deep Learning Model for Automated Optic Disc Localization and Glaucoma Classification using Fundus Images,” SN Applied Science, vol. 4, no. 4, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Lucas Pascal et al., “Multi-Task Deep Learning for Glaucoma Detection from Color Fundus Images,” Scientific Reports, vol. 12, no. 1, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Sajib Saha, Janardhan Vignarajan, and Shaun Frost, “A Fast and Fully Automated System for Glaucoma Detection using Color Fundus Photographs,” Scientific Reports, vol. 13, no. 1, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[7] N.K. Jisy et al., “Early Detection of Glaucoma: Feature Visualization with a Deep Convolutional Network,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, vol. 12, no.1, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Adnan Haider et al., “Artificial Intelligence-based Computer-Aided Diagnosis of Glaucoma using Retinal Fundus Images,” Expert Systems with Applications, vol. 207, pp. 1-25, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Ali Raza et al., “Assisting Glaucoma Screening Process using Feature Excitationand Information Aggregation Techniques in Retinal Fundus Images,” Mathematics, vol. 11, no. 2, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Mingquan Lin et al., “Automated Diagnosing Primary Open-Angle Glaucoma from Fundus Image by Simulating Human’s Grading with Deep Learning,” Scientific Reports, vol. 12, no. 1, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Rohit Thanki, “A Deep Neural Network and Machine Learning Approach for Retinal Fundus image Classification,” Healthcare Analytics, vol. 3, pp. 1-9, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Thisara Shyamalee et al., “Automated Tool Support for Glaucoma Identification with Explainability using Fundus Images,” IEEE Access, vol. 12, pp. 17290-17307, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Ahlam Shamsan, Ebrahim Mohammed Senan, and Hamzeh Salameh Ahmad Shatnawi, “Automatic Classification of Colour Fundus Images for Prediction Eye Disease Types based on Hybrid Features,” Diagnostics, vol. 13, no. 10, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Xiaoling Huang et al., “GRAPE: A Multi-Modal Dataset of Longitudinal Follow-Up Visual Field and Fundus Images for Glaucoma Management,” Scientific Data, vol. 10, no. 1, pp. 1-10, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Thisara Shyamalee, and Dulani Meedeniya, “Glaucoma Detection with Retinal Fundus Images using Segmentation and Classification,” Machine Intelligence Research, vol. 19, no. 6, pp. 563-580, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[16] You-Sang Cho et al., “Attention Mechanism-based Glaucoma Classification Model using Retinal Fundus Images,” Sensors, vol. 24, no. 14, pp. 1-9, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Xiaoyan Hu et al., “GLIM-Net: Chronic Glaucoma ForecastTransformer for Irregularly Sampled Sequential Fundus Images,” IEEE Transactions on Medical Imaging, vol. 42, no. 6, pp. 1875-1884, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Sanli Yi et al., “MTRA-CNN: A Multi-Scale Transfer Learning Framework for Glaucoma Classification in Retinal Fundus Images,” IEEE Access, vol. 11, pp. 142689-142701, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Carlos A. Vásquez-Rochín et al., “Multi-Stage Ensemble-based System for Glaucomatous Optic Neuropathy Diagnosis in Fundus Images,” Electronics, vol. 12, no. 4, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Xiaoyi Raymond Gao et al., “Automated Vertical Cup-to-Disc Ratio Determination from Fundus Images for Glaucoma Detection,” Scientific Reports, vol. 14, no. 1, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Thangam Palaniswamy, and Mahendiran Vellingiri, “Internet of Things and Deep Learning Enabled Diabetic Retinopathy Diagnosis using Retinal Fundus Images,” IEEE Access, vol. 11, pp. 27590-27601, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Shumoos Al-Fahdawi et al., “Fundus-Deep Net: Multi-Label Deep Learning Classification System for Enhanced Detection of Multiple Ocular Diseases Through Data Fusion of Fundus Images,” Information Fusion, vol. 102, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] K. Alice et al., “Effect of Multi Filters in Glucoma Detection using Random Forest Classifier,” Measurement: Sensors, vol. 25, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Shaista Hussai et al., “Predicting Glaucoma Progression using Deep Learning Framework Guided by Generative Algorithm,” Scientific Reports, vol. 13, no. 1, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Ayesha Shoukat et al., “Automatic Diagnosis of Glaucoma from Retinal Images using Deep Learning Approach,” Diagnostics, vol. 13, no. 10, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Yi Li et al., “A Transfer Learning-based Multimodal Neural Network Combining Metadata and Multiple Medical Images for Glaucoma Type Diagnosis,” Scientific Reports, vol. 13, no. 1, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Vijaya Kumar Velpula et al., “Glaucoma Detection with Explainable AI using Convolutional Neural Networks based Feature Extraction and Machine Learning Classifiers,” IET Image Processing, vol. 18, no. 13, pp. 3827-3853, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Anita Desiani et al., “Multi-Stage CNN: U-Net and Xcep-Dense of Glaucoma Detection in Retinal Images,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, vol. 5, no. 4, pp. 211-222, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Cemil Közkurt et al., “Trish: An Efcient Activation Function for CNN Models and Analysis of its Effectiveness with Optimizers in Diagnosing Glaucoma,” The Journal of Supercomputing, vol. 80, no. 11, pp. 15485-15516, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[30] B.P. Pradeep kumar, Pramod K.B. Rangaiah, and Robin Augustine, “Enhanced Glaucoma Detection using U-Net and U-Net+ Architectures using Deep Learning Techniques,” Photodiagnosis and Photodynamic Therapy, vol. 54, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Maheen Anwar et al., “E-GlauNet: A CNN-based Ensemble Deep Learning Model for Glaucoma Detection and Staging using Retinal Fundus Images,” Computers, Materials and Continua, vol. 84, no. 2, pp. 3477-3502, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Venkatesh Guntreddi, and V. Sivakumar, “Deep Learning based Glaucoma Detection using Majority Voting Ensemble of ResNet50, VGG16, and Swin Transformer,” Results in Engineering, vol. 28, pp. 1-13, 2025.
[CrossRef] [Google Scholar] [Publisher Link]