Optical Coherence Tomography (OCT) Image Classification for Retinal Disease Using a Random Forest Classifier

Optical coherence tomography (OCT) is a vital imaging technique that provides detailed images of the retina and plays a crucial role in diagnosing and monitoring various retinal conditions, such as diabetic macular edema (DME), choroidal neovascularization (CNV), and DRUSEN. However, there is a need to improve the early detection and treatment of these common eye diseases. While deep learning methods have demonstrated superior accuracy in analyzing OCT images, the potential of machine learning approaches, especially concerning data volume and computational efficiency, requires further exploration. This study aimed to improve the diagnosis and management of retinal diseases using OCT images through a machine learning framework employing a random forest classifier, with a focus on comparing its efficacy against that of popular image processing filters. We propose a novel approach that uses raw image data embedding (RIDE) as input to our machine learning model. This approach uses translated image raw data as opposed to metadata-driven preprocessing algorithms. We systematically benchmark its performance against established built-in methods, such as histogram of oriented gradients (HOG), local binary patterns (LBP), and features from the opponent space for filtering (FOSF). This comparative analysis serves to assess the efficacy of our approach in relation to these widely recognized methods. The proposed method achieves higher accuracy but also optimizes the time complexity of the system. The proposed model exhibited a commendable accuracy rate of 80% in the classification of retinal diseases, surpassing the performance of various other classifiers and methods. This research represents a small step toward the creation of an accurate and efficient machine learning-based system for diagnosing and monitoring retinal diseases, ultimately contributing to improved patient outcomes and diagnostic accuracy.