AMDNet23: A combined deep Contour-based Convolutional Neural Network and Long Short Term Memory system to diagnose Age-related Macular Degeneration

TL;DR

This paper introduces AMDNet23, a hybrid deep learning system combining CNN and LSTM to automatically detect Age-related Macular Degeneration from fundus images, achieving high accuracy and robustness.

Contribution

The novel hybrid AMDNet23 model integrates CNN and LSTM for improved AMD detection from fundus images, enhancing diagnostic accuracy over existing methods.

Findings

Achieved 96.50% accuracy in AMD detection

High specificity of 99.32%

F1-score of 96.49%

Abstract

In light of the expanding population, an automated framework of disease detection can assist doctors in the diagnosis of ocular diseases, yields accurate, stable, rapid outcomes, and improves the success rate of early detection. The work initially intended the enhancing the quality of fundus images by employing an adaptive contrast enhancement algorithm (CLAHE) and Gamma correction. In the preprocessing techniques, CLAHE elevates the local contrast of the fundus image and gamma correction increases the intensity of relevant features. This study operates on a AMDNet23 system of deep learning that combined the neural networks made up of convolutions (CNN) and short-term and long-term memory (LSTM) to automatically detect aged macular degeneration (AMD) disease from fundus ophthalmology. In this mechanism, CNN is utilized for extracting features and LSTM is utilized to detect the extracted features. The dataset of this research is collected from multiple sources and afterward applied quality assessment techniques, 2000 experimental fundus images encompass four distinct classes equitably. The proposed hybrid deep AMDNet23 model demonstrates to detection of AMD ocular disease and the experimental result achieved an accuracy 96.50%, specificity 99.32%, sensitivity 96.5%, and F1-score 96.49.0%. The system achieves state-of-the-art findings on fundus imagery datasets to diagnose AMD ocular disease and findings effectively potential of our method.