Convolutional Neural Network Based on Fluorescein Angiography Images for Retinopathy of Prematurity Management

Abstract

The purpose of this study was to explore the use of fluorescein angiography (FA) images in a convolutional neural network (CNN) in the management of retinopathy of prematurity (ROP). Methods: The dataset involved a total of 835 FA images of 149 eyes (90 patients), where each eye was associated with a binary outcome (57 "untreated" eyes and 92 "treated"; 308 "untreated" images, 527 "treated"). The resolution of the images was 1600 and 1200 px in 20% of cases, whereas the remaining 80% had a resolution of 640 and 480 px. All the images were resized to 640 and 480 px before training and no other preprocessing was applied. A CNN with four convolutional layers was trained on 90% of the images (n = 752) randomly chosen. The accuracy of the prediction was assessed on the remaining 10% of images (n = 83). Keras version 2.2.0 for R with Tensorflow backend version 1.11.0 was used for the analysis. Results: The validation accuracy after 100 epochs was 0.88, whereas training accuracy was 0.97. The receiver operating characteristic (ROC) presented an area under the curve (AUC) of 0.91. Conclusions: Our study showed, we believe for the first time, the applicability of artificial intelligence (CNN) technology in the ROP management driven by FA. Further studies are needed to exploit different fields of applications of this technology. Translational Relevance: This algorithm is the basis for a system that could be applied to both ROP as well as experimental oxygen induced retinopathy.

Artificial Intelligence and OCT Angiography in Full Thickness Macular Hole. New Developments for Personalized Medicine

“…Ophthalmology, and more specifically retinal surgery, are exemplar subspecialties in which a remarkable use of several data sources (i.e., imaging, functional tests, electric retinal activity) is performed for the definition of comprehensive diagnosis, prognostic stratification, and follow-up strategies of patients affected by ocular diseases [ 4 , 5 ].…”

Building an Artificial Intelligence Laboratory Based on Real World Data: The Experience of Gemelli Generator

“…As an example of how we can understand the functioning of an opaque algorithm, heat maps can be generated to show what areas of a medical image contributed most to a given classification, giving an insight to medical doctors to better understand and possibly formulate new clinical hypotheses. Figure 12 shows the use of this method to visualize the areas of a fluorescein angiography of the fundus oculi that were most relevant for the output of a deep learning algorithm trained on images to predict retinal detachment in prematurely born infants (Lepore et al, 2020).…”

Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy

“…Diabetes-related neuropathy could be diagnosed by CNN from confocal microscopy [159] and retinopathy from fluoresceing angiography images [160].…”