Training of an artificial intelligence algorithm for automatic detection of the Van Herick grade

Davide Cassanelli; Tommaso Fedullo; Giovanni Gibertoni; Giorgia Saporito; Manuela Ferrazza; Francesco Oddone; Ivano Riva; Luciano Quaranta; Federico Tramarin; Luigi Rovati

doi:10.1117/12.2607610

4 March 2022 Training of an artificial intelligence algorithm for automatic detection of the Van Herick grade

Davide Cassanelli, Tommaso Fedullo, Giovanni Gibertoni, Giorgia Saporito, Manuela Ferrazza, Francesco Oddone, Ivano Riva, Luciano Quaranta, Federico Tramarin, Luigi Rovati

Author Affiliations +

Proceedings Volume 11941, Ophthalmic Technologies XXXII; 119410C (2022) https://doi.org/10.1117/12.2607610
Event: SPIE BiOS, 2022, San Francisco, California, United States

Conference Poster

Abstract

Van Herick technique is a qualitative tool for assessing the anterior chamber angle and can be exploited as a simple screening alternative to gonioscopy. In our previous papers, we presented a novel instrument able to automatically perform the Van Herick manoeuvre. Therefore, to fully automate the screening method from the acquired images, it is still necessary to automatically determine the Van Herick grade. In this paper, we present a deep learning algorithm for automatically determining the Van Herick grade. In particular, the performances of three different Convolutional Neural Networks have been verified by acquiring the eye images of 80 patients. All the networks return the Van Herick grade classification with sufficient accuracy for a screening system and, after proper training, can offer a real-time response.

Conference Presentation

Citation Download Citation

Davide Cassanelli, Tommaso Fedullo, Giovanni Gibertoni, Giorgia Saporito, Manuela Ferrazza, Francesco Oddone, Ivano Riva, Luciano Quaranta, Federico Tramarin, and Luigi Rovati "Training of an artificial intelligence algorithm for automatic detection of the Van Herick grade", Proc. SPIE 11941, Ophthalmic Technologies XXXII, 119410C (4 March 2022); https://doi.org/10.1117/12.2607610

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available