Generative Modeling and Multispectral Imaging for Eye Fundus Classification

Background: The early diagnosis of eye fundus pathologies is crucial, as they may go unnoticed until reaching advanced stages. To offer an improved screening methodology for this purpose, the effectiveness of a conditional variational autoencoder (CVAE) based on multispectral (MS) imaging and operating from the visible to the near-infrared range (416–1213 nm) has been assessed. Methods: A total of 2040 images from 102 patients (66 females, 36 males; aged 19–91 years) were acquired with an MS fundus camera to feed a fine-tuned CVAE for classifying eye fundus as healthy or diseased. The performance of the neural network was assessed for different image resolutions and spectral ranges. Results: The proposed deep generative model showed excellent results, reaching 100% of accuracy, sensitivity and specificity for the set of MS images from 416 nm to 955 nm at maximum resolution (1757 × 1757 pixels). Other instances with different image resolutions and spectral ranges led to good classifications (accuracy between 96% and 98%, sensitivity between 92% and 98%, and specificity between 97% and 100%). The CVAE exhibited robust performance with convergence of the accuracy and loss through the different epochs for training and validation in all instances. Conclusions: This study proves that a CVAE approach based on MS imaging is a highly effective tool for diagnosing eye fundus conditions and could potentially serve as a valuable clinical support tool for screening. The approach performs remarkably well when high spatial resolution MS images ranging from 416 nm to 955 nm are used. This underscores the importance of combining spatial and spectral information, particularly of wavelengths beyond the visible range.