Erschienen in:
01.12.2024 | Original Paper
Diagnosis of retinal damage using Resnet rescaling and support vector machine (Resnet-RS-SVM): a case study from an Indian hospital
verfasst von:
Santi Kumari Behera, Rina Mahakud, Millee Panigrahi, Prabira Kumar Sethy, Rasmikanta Pati
Erschienen in:
International Ophthalmology
|
Ausgabe 1/2024
Einloggen, um Zugang zu erhalten
Abstract
Purpose
This study aims to address the challenge of identifying retinal damage in medical applications through a computer-aided diagnosis (CAD) approach. Data was collected from four prominent eye hospitals in India for analysis and model development.
Methods
Data was collected from Silchar Medical College and Hospital (SMCH), Aravind Eye Hospital (Tamil Nadu), LV Prasad Eye Hospital (Hyderabad), and Medanta (Gurugram). A modified version of the ResNet-101 architecture, named ResNet-RS, was utilized for retinal damage identification. In this modified architecture, the last layer's softmax function was replaced with a support vector machine (SVM). The resulting model, termed ResNet-RS-SVM, was trained and evaluated on each hospital's dataset individually and collectively.
Results
The proposed ResNet-RS-SVM model achieved high accuracies across the datasets from the different hospitals: 99.17% for Aravind, 98.53% for LV Prasad, 98.33% for Medanta, and 100% for SMCH. When considering all hospitals collectively, the model attained an accuracy of 97.19%.
Conclusion
The findings demonstrate the effectiveness of the ResNet-RS-SVM model in accurately identifying retinal damage in diverse datasets collected from multiple eye hospitals in India. This approach presents a promising advancement in computer-aided diagnosis for improving the detection and management of retinal diseases.