article · Sensors
Retinal optical coherence tomography (OCT) imaging helps clinicians assess the back of the eye, aiding the diagnosis, monitoring, and treatment evaluation of both primary ocular conditions and systemic illnesses like diabetes. To improve diagnostic workflows, an enhanced optical coherence tomography classification model combines a modified ResNet-50 network with random forest algorithms. The training strategy employs the Adam optimiser to raise efficiency relative to standard pre-trained networks, including visual geometry group (VGG-16) and spatial separable convolutions. In experimental evaluations, the resulting model demonstrated high diagnostic performance, achieving an overall accuracy of 0.9788, a sensitivity of 0.9836, and a specificity of 0.9615. It also achieved low false discovery and false negative rates, underscoring its capability for precise automated image analysis.
Evaluating conditions in the back of the eye is crucial for managing sight-threatening eye conditions and systemic illnesses such as diabetes. Automated analysis of optical coherence tomography scans can assist clinical decisions and treatment monitoring. Delivering high sensitivity and specificity while minimising false readings provides a pathway toward reliable automated tools that support healthcare professionals during routine eye screenings.
The algorithm could enable automated diagnostic decision-support software for eye clinics and diagnostic imaging centres monitoring retinal conditions or diabetic complications. Because the abstract details algorithmic experimentation and statistical metrics rather than clinical trials, the technology is currently at an applied research stage. Progression toward commercialisation would require integration into clinical imaging platforms and formal clinical validation.
AI-generated from the published abstract. Always read the original work before citing.
Retinal optical coherence tomography (OCT) imaging is a valuable tool for assessing the condition of the back part of the eye. The condition has a great effect on the specificity of diagnosis, the monitoring of many physiological and pathological procedures, and the response and evaluation of therapeutic effectiveness in various fields of clinical practices, including primary eye diseases and systemic diseases such as diabetes. Therefore, precise diagnosis, classification, and automated image analysis models are crucial. In this paper, we propose an enhanced optical coherence tomography (EOCT) model to classify retinal OCT based on modified ResNet (50) and random forest algorithms, which are used in the proposed study's training strategy to enhance performance. The Adam optimizer is applied during the training process to increase the efficiency of the ResNet (50) model compared with the common pre-trained models, such as spatial separable convolutions and visual geometry group (VGG) (16). The experimentation results show that the sensitivity, specificity, precision, negative predictive value, false discovery rate, false negative rate accuracy, and Matthew's correlation coefficient are 0.9836, 0.9615, 0.9740, 0.9756, 0.0385, 0.0260, 0.0164, 0.9747, 0.9788, and 0.9474, respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/s23125393
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.
