Automatic Method of Macular Diseases Detection Using Deep CNN-GRU Network in OCT Images
Pubblicato online: 30 ott 2024
Pagine: 697 - 706
Ricevuto: 24 lug 2023
Accettato: 07 apr 2024
DOI: https://doi.org/10.2478/ama-2024-0074
Parole chiave
© 2024 Pawel Powroznik et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The increasing development of Deep Learning mechanism allowed ones to create semi-fully or fully automated diagnosis software solutions for medical imaging diagnosis. The convolutional neural networks are widely applied for central retinal diseases classification based on OCT images. The main aim of this study is to propose a new network, Deep CNN-GRU for classification of early-stage and end-stages macular diseases as age-related macular degeneration and diabetic macular edema (DME). Three types of disorders have been taken into consideration: drusen, choroidal neovascularization (CNV), DME, alongside with normal cases. The created automatic tool was verified on the well-known Labelled Optical Coherence Tomography (OCT) dataset. For the classifier evaluation the following measures were calculated: accuracy, precision, recall, and F1 score. Based on these values, it can be stated that the use of a GRU layer directly connected to a convolutional network plays a pivotal role in improving previously achieved results. Additionally, the proposed tool was compared with the state-of-the-art of deep learning studies performed on the Labelled OCT dataset. The Deep CNN-GRU network achieved high performance, reaching up to 98.90% accuracy. The obtained results of classification performance place the tool as one of the top solutions for diagnosing retinal diseases, both early and late stage.