Optimizing glaucoma diagnosis using fundus and optical coherence tomography image fusion based on multi-modal convolutional neural network approach

Abstract

A novel approach that combines segmented fundus images (FIs) and optical coherence tomography image (OCTIs) are presented here, by incorporating deep learning network (DLN) techniques, to address the imperative need for advanced diagnostic algorithms in detecting and classifying glaucoma. By combining these two images, glaucoma diagnoses are made to improve the accuracy with more reliability. Multi modal convolutional neural networks (MMCNNs) are proposed for automatically extracting discriminatory features from both segmented FIs and OCTIs, allowing for comprehensive ocular analysis. A significant improvement in glaucoma diagnosis is achieved through segmentation of both FIs and OCTIs, ensuring robustness generalization to diverse clinical scenarios, DLN models are trained on datasets encompassing a wide range of glaucoma cases. The integrated approach outperforms individual modalities in terms of early detection of glaucoma and accurate classification. This method demonstrates promising potential in early glaucoma detection due to its effectiveness. By combining segmented features from both FIs and OCTIs through MMCNNs, improved efficiency in diagnosing predominant ocular glaucoma disorder is achieved compared to existing methods. Within the scope of this research, GoogLeNet (GN) is applied to independently classify glaucoma (uni-modal) in segmented FIs and OCTIs, providing a basis for comparison with the evaluation of MMCNNs.