Nl-Fr

View abstract

This abstract is assigned to session Free Papers Session 2
Presentation preference Oral presentation
TitleAutomated vitreous haze grading using ultrawide-field fundus photographs and deep learning
PurposeTo evaluate the performance of a deep learning algorithm for the automated grading of vitritis on ultra-wide field imaging.
MethodsUltra-wide field (UWF) fundus retinophotographs (Optos®, Dunfermline, United Kingdom) of patients followed for intermediate, posterior or pan-uveitis were used. Vitreous haze was defined on each UWF picture by two blinded experts according to the 6 steps of the Nussenblatt scale. Included images were automatically classified using the Inception V3 convolutional neural network from Google (California, USA). Images were fed to the model as follows: training (70%), validation (15%), and testing set (15%). The performance was assessed on the unused testing set.
ResultsA total of 1181 images from 443 patients were included. The performance of the model for the detection of vitritis was good with a sensitivity of 96% (95% CI: 0.89-0.98) and a specificity of 87% (95% CI: 0.78-0.89). The area under the ROC curve was 0.92 (95% CI: 0.78-0.99). For the classification of vitritis into 6 classes, the global accuracy of the model was 64% increasing to 85% when accepting a maximum error margin of one class (95% CI: 0.76-0.94).
ConclusionWe describe a new deep learning model based on UWF fundus imaging that produces an automated tool for the detection and grading of vitreous haze with a good performance.
Conflict of interestNo
Authors 1
Last nameTOUHAMI
Initials of first name(s)S
DepartmentOphthalmology
CityParis
CountryFrance
Authors 2
Last nameMhibik
Initials of first name(s)B
DepartmentOphthalmology
CityParis
CountryFrance
Authors 3
Last nameBchir
Initials of first name(s)C
DepartmentBiostatistics
CityParis
CountryFrance
Authors 4
Last nameGulic
Initials of first name(s)K
DepartmentOphthalmology
CityParis
CountryFrance
Authors 5
Last nameBodaghi
Initials of first name(s)B
DepartmentOphthalmology
CityParis
CountryFrance