Optimized Artificial Intelligence for Enhanced Ectasia Detection Using Scheimpflug-Based Corneal Tomography and Biomechanical Data - 02/06/23

Doi : 10.1016/j.ajo.2022.12.016

Renato Ambrósio ^a,^b,^c,^d,^e,^⁎ , Aydano P. Machado ^c,^d,^be, Edileuza Leão ^d,^f, João Marcelo G. Lyra ^d,^g, Marcella Q. Salomão ^b,^c,^d, Louise G. Pellegrino Esporcatte ^b,^c,^d, João B.R. da Fonseca Filho ^a,^b, Erica Ferreira-Meneses ^a,^b, Nelson B. Sena ^a,^b, Jorge S. Haddad ^c, Alexandre Costa Neto ^a,^d, Gildasio Castelo de Almeida ^d, Cynthia J. Roberts ^h, Ahmed Elsheikh ^i,^j,^k, Riccardo Vinciguerra ^i,^l, Paolo Vinciguerra ^m,ⁿ, Jens Bühren ^o,^p, Thomas Kohnen ^p, Guy M. Kezirian ^e,^q, Farhad Hafezi ^r,^s,^t,^u,^bd, Nikki L. Hafezi ^r,^s,^v,^bd, Emilio A. Torres-Netto ^c,^r,^bd, Nanji Lu ^v,^w,^x,^bd, David Sung Yong Kang ^y, Omid Kermani ^z, Shizuka Koh ^aa, Prema Padmanabhan ^ab, Suphi Taneri ^e,^ac,^ad, William Trattler ^ae, Luca Gualdi ^b,^af, José Salgado-Borges ^ag, Fernando Faria-Correia ^b,^ah,^ai, Elias Flockerzi ^aj, Berthold Seitz ^aj, Vishal Jhanji ^ak,^al, Tommy C.Y. Chan ^ak, Pedro Manuel Baptista ^am, Dan Z. Reinstein ^e,^an,^ao,^ap,^aq, Timothy J. Archer ^an, Karolinne M. Rocha ^ar, George O. Waring ^as, Ronald R. Krueger ^at, William J. Dupps ^au,^av,^aw, Ramin Khoramnia ^ax, Hassan Hashemi ^ay, Soheila Asgari ^ay, Hamed Momeni-Moghaddam ^az, Siamak Zarei-Ghanavati ^ba, Rohit Shetty ^bb, Pooja Khamar ^bb, Michael W. Belin ^bc, Bernardo T. Lopes b, c, d, i
^a From the Department of Ophthalmology, the Federal University of the State of Rio de Janeiro, Brazil
^b Rio de Janeiro Corneal Tomography and Biomechanics Study Group, Rio de Janeiro, Brazil
^c Department of Ophthalmology, Federal University of São Paulo, São Paulo, Brazil
^d Brazilian Artificial Intelligence Networking in Medicine (BrAIN), Maceio and Rio de Janeiro, Brazil
^e World College of Refractive Surgery & Visual Sciences, Scottsdale, Arizona, USA
^f Computing Institute, Federal University of Alagoas, Brazil
^g Universidade Estadual de Ciências da Saúde de Alagoas (UNCISAL), Maceio, Alagoas, Brazil
^h Department of Ophthalmology & Visual Sciences, Department of Biomedical Engineering, the Ohio State University, Columbus, Ohio, USA
ⁱ The School of Engineering, University of Liverpool, Liverpool, United Kingdom
^j Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, China
^k NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, United Kingdom
^l Humanitas San Pio X Hospital, Milano, Italy
^m Department of Biomedical Sciences, Humanitas University, Milan, Italy
ⁿ Humanitas Clinical and Research Center—IRCCS, Rozzano, Italy
^o Praxis für Augenheilkunde Prof. Bühren, Germany
^p Department of Ophthalmology, Goethe University Frankfurt, Frankfurt am Main, Germany
^q SurgiVision® Consultants, Inc, Scottsdale, Arizona, USA
^r ELZA Institute, Dietikon, Swisstzerland
^s Center for Applied Biotechnology and Molecular Medicine, University of Zurich, Zurich, Switzerland
^t USC Roski Eye Institute, Miller School of Medicine; Los Angeles, California, USA
^u School of Ophthalmology and Optometry, Wenzhou Medical University, Wenzhou, China
^v Faculty of Medicine and Health Sciences, University of Antwerp, Wilrijk, Belgium
^w Department of Ophthalmology, Antwerp University Hospital, Edegem, Belgium
^x Emmetropia Mediterranean Eye Institute, Heraklion, Greece
^y Eyereum Eye Clinic, Seoul, South Korea
^z Augenklinik am Neumarkt, Cologne, Germany
^aa Department of Ophthalmology, Osaka University Graduate School of Medicine, Osaka, Japan
^ab Department of Cornea and Refractive Surgery, Medical Research Foundation, Sankara Nethralaya, Chennai, Tamil Nadu, India
^ac Center for Refractive Surgery Muenster, Muenster
^ad University Eye-Clinic, Ruhr-University, Bochum, Germany
^ae Center for Excellence in Eye Care, Miami, Florida, USA
^af Diagnostica Oftalmologica e Microchirurgia Oculare (DOMA), Rome, Italy
^ag Clinica J. Salgado-Borges, Porto
^ah Department of Ophthalmology, Hospital de Braga
^ai Life and Health Sciences Research Institute (ICVS), Escola de Medicina, Universidade do Minho, Braga, Portugal
^aj Department of Ophthalmology, Saarland University Medical Center, Homburg, Germany
^ak Department of Ophthalmology and Visual Sciences, the Chinese University of Hong Kong, Hong Kong SAR, China
^al Department of Ophthalmology, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
^am Ophthalmology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
^an Reinstein Vision, London Vision Clinic, London, United Kingdom
^ao Columbia University Medical Center, New York, New York, USA
^ap Sorbonne Université, Paris, France
^aq Biomedical Science Research Institute, Ulster University, Coleraine, United Kingdom
^ar Storm Eye Institute, Medical University of South Carolina, Charleston
^as Waring Vision Institute, Mount Pleasant
^at South Carolina, Stanley M. Truhlsen Eye Institute, Department of Ophthalmology and Visual Sciences, University of Nebraska Medical Center, Omaha, Nebraska
^au Cole Eye Institute, Cleveland Clinic
^av Department of Biomedical Engineering, Lerner Research Institute
^aw Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
^ax The David J. Apple International Laboratory for Ocular Pathology, Department of Ophthalmology, University of Heidelberg, Heidelberg, Germany
^ay Noor Ophthalmology Research Center, Noor Eye Hospital, Tehran, Iran
^az Rehabilitation Sciences Research Center, Zahedan University of Medical Sciences, Zahedan, Iran
^ba Eye Research Center, Mashhad University of Medical Sciences, Mashhad, Iran
^bb Department of Cornea and Refractive Surgery, Narayana Nethralaya, Bangalore, India
^bc Department of Ophthalmology & Vision Science, University of Arizona, Tucson, Arizona, USA
^bd Light for Sight Foundation, Dietikon
^be Instituto de Computação, Federal University of Alagoas, Maceio, Brazil.

^⁎Inquiries to Renato Ambrósio Jr, Department of Ophthalmology, the Federal University of the State of Rio de Janeiro, Rio de Janeiro, BrazilDepartment of Ophthalmologythe Federal University of the State of Rio de JaneiroRio de JaneiroBrazil

Résumé

Purpose

To optimize artificial intelligence (AI) algorithms to integrate Scheimpflug-based corneal tomography and biomechanics to enhance ectasia detection.

Design

Multicenter cross-sectional case-control retrospective study.

Methods

A total of 3886 unoperated eyes from 3412 patients had Pentacam and Corvis ST (Oculus Optikgeräte GmbH) examinations. The database included 1 eye randomly selected from 1680 normal patients (N) and from 1181 “bilateral” keratoconus (KC) patients, along with 551 normal topography eyes from patients with very asymmetric ectasia (VAE-NT), and their 474 unoperated ectatic (VAE-E) eyes. The current TBIv1 (tomographic-biomechanical index) was tested, and an optimized AI algorithm was developed for augmenting accuracy.

Results

The area under the receiver operating characteristic curve (AUC) of the TBIv1 for discriminating clinical ectasia (KC and VAE-E) was 0.999 (98.5% sensitivity; 98.6% specificity [cutoff: 0.5]), and for VAE-NT, 0.899 (76% sensitivity; 89.1% specificity [cutoff: 0.29]). A novel random forest algorithm (TBIv2), developed with 18 features in 156 trees using 10-fold cross-validation, had a significantly higher AUC (0.945; DeLong, P < .0001) for detecting VAE-NT (84.4% sensitivity and 90.1% specificity; cutoff: 0.43; DeLong, P < .0001) and a similar AUC for clinical ectasia (0.999; DeLong, P = .818; 98.7% sensitivity; 99.2% specificity [cutoff: 0.8]). Considering all cases, the TBIv2 had a higher AUC (0.985) than TBIv1 (0.974; DeLong, P < .0001).

Conclusions

AI optimization to integrate Scheimpflug-based corneal tomography and biomechanical assessments augments accuracy for ectasia detection, characterizing ectasia susceptibility in the diverse VAE-NT group. Some patients with VAE may have true unilateral ectasia. Machine learning considering additional data, including epithelial thickness or other parameters from multimodal refractive imaging, will continuously enhance accuracy. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

Le texte complet de cet article est disponible en PDF.

Plan

METHODS

Participants

Artificial intelligence optimizing protocol and statistics

Statistical analysis

RESULTS

DISCUSSION

	Author Bio available at AJO.com.
	Meeting Presentation: This work was partially presented as a paper in the virtual meeting of the ASCRS (American Society of Cataract and Refractive Surgery) 2020.

Export

Vol 251

P. 126-142 - juillet 2023 Retour au numéro

Article précédent

Sutureless Conjunctiva-Sparing Posterior Ptosis Repair Surgery: A Novel Technique
Ronald Mancini, Parsha Forouzan, Zachary G. Keenum, Phillip A. Tenzel, W. Matthew Petroll

| Article suivant

Large-Diameter Modified Big-Bubble Deep Anterior Lamellar Keratoplasty in Post–Radial Keratotomy Eyes
Marco Pellegrini, Angeli Christy Yu, Massimo Busin

Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.

Déjà abonné à cette revue ?

connectez-vous ou créez un compte

Optimized Artificial Intelligence for Enhanced Ectasia Detection Using Scheimpflug-Based Corneal Tomography and Biomechanical Data - 02/06/23

Résumé

Purpose

Design

Methods

Results

Conclusions

Plan

Export citations

Fichier

Contenu

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL