View abstract

Cet abstract a été assigné à session AOB Free Papers 1

Type de présentation	Oral presentation
Titre	Visual field estimation using OCT and Artificial Intelligence in a glaucoma clinic population

But	Standard automated perimetry is the gold standard to monitor visual field (VF) loss in glaucoma management, but it is prone to intrasubject variability. We trained and validated a customized deep learning (DL) model that estimates pointwise and overall VF sensitivity from unsegmented optical coherence tomography (OCT) scans.
Méthodes	DL regression models have been trained with four imaging modalities (circumpapillary OCT at 3.5 mm, 4.1 mm, and 4.7 mm diameter) and scanning laser ophthalmoscopy en face images to estimate mean deviation (MD) and 52 threshold values. This retrospective study used data from patients who underwent a complete glaucoma examination, including a reliable Humphrey Field Analyzer (HFA) 24-2 SITA Standard (SS) VF exam and a SPECTRALIS OCT.
Résultats	For MD estimation, weighted prediction averaging of all four individuals yielded a mean absolute error (MAE) of 2.89 dB (2.50–3.30) on 186 test images, reducing the baseline by 54% (MAEdecr%). For 52 VF threshold values’ estimation, the weighted ensemble model resulted in an MAE of 4.82 dB (4.45–5.22), representing an MAEdecr% of 38% from baseline when predicting the pointwise mean value. DL managed to explain 75% and 58% of the variance (R2) in MD and pointwise sensitivity estimation, respectively.
Conclusion	Deep learning can estimate global and pointwise VF sensitivities that fall almost entirely within the 90% test–retest confidence intervals of the 24-2 SS test. Fast and consistent VF prediction from unsegmented OCT scans could become a solution for visual function estimation in patients unable to perform reliable VF exams.
Conflit d'intérêt	Non

Auteur 1

Nom	Hemelings
Initiales	R
Institut	KU Leuven
Ville	Leuven

Auteur 2

Nom	Stalmans
Initiales	I
Institut	UZ Leuven
Ville	Leuven