article · Frontiers in Computer Science
Early identification of ophthalmic conditions is vital for effective retinal treatment, as irrecoverable tissue damage can lead to permanent visual impairment or total blindness. Deep learning techniques offer effective methods for extracting diagnostic features from medical scans. A Convolutional Neural Network model categorises Optical Coherence Tomography scans into four distinct groups: healthy retina, Diabetic Macular Edema, Choroidal Neovascular Membranes, and Age-related Macular Degeneration. Using a publicly available collection of retinal images for evaluation, the system demonstrates significant improvements in classification accuracy across the targeted diseases. This computational approach highlights the utility of automated image analysis in identifying subtle retinal abnormalities that are crucial for timely clinical intervention, offering a structured way to distinguish pathological changes from normal ocular tissue.
Prompt diagnosis of retinal disorders is crucial because unaddressed damage to ocular tissues is irreversible and can result in lasting vision loss or complete blindness. Automated classification using deep learning aids the precise detection of complex diseases such as macular degeneration and diabetic edema, supporting earlier clinical evaluation before structural retinal harm becomes permanent.
The algorithm could serve as an automated diagnostic assistance tool for ophthalmologists and clinical technicians reviewing Optical Coherence Tomography scans. Potential integration into retinal imaging software could accelerate screening workflows for eye clinics. However, because testing was conducted solely on publicly available image datasets, the technology represents early-stage research that requires prospective clinical validation before real-world deployment.
AI-generated from the published abstract. Always read the original work before citing.
Deep learning shows promising results in extracting useful information from medical images. The proposed work applies a Convolutional Neural Network (CNN) on retinal images to extract features that allow early detection of ophthalmic diseases. Early disease diagnosis is critical to retinal treatment. Any damage that occurs to retinal tissues that cannot be recovered can result in permanent degradation or even complete loss of sight. The proposed deep-learning algorithm detects three different diseases from features extracted from Optical Coherence Tomography (OCT) images. The deep-learning algorithm uses CNN to classify OCT images into four categories. The four categories are Normal retina, Diabetic Macular Edema (DME), Choroidal Neovascular Membranes (CNM), and Age-related Macular Degeneration (AMD). The proposed work uses publicly available OCT retinal images as a dataset. The experimental results show significant enhancement in classification accuracy while detecting the features of the three listed diseases.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3389/fcomp.2023.1252295
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
