Answers are grounded in this paper and cite their sources.
Retinal fundus images are a valuable source of information for ophthalmologists to diagnose retina problems. Early detection can improve chances of cure and also prevent blindness. Retinal problems like diabetic retinopathy, retinitis pigmentosa can be diagnosed using retinal fundus images by medical experts. In recent times, machine learning research has focused on diagnosing diseases like diabetic retinopathy by extracting features and then classifying the image. In this research our goal is to automatically classify images with retinal problems from those of the healthy ones without performing any explicit segmentation or feature extraction. Rather, we use a deep learning model to automatically classify any retinal fundus image as healthy or diseased. The architecture of the network is both simple and fast. The model has been tested on two datasets, including real patient retinal fundus images obtained from a local hospital. The accuracy of this model has been found to be in the range 96.5 % to 99.7%.
No takes yet. Share an insight, caveat, or question.
Jain et al. (2018) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: