Optimized artificial intelligence for enhanced ectasia detection using Scheimpflug-based corneal tomography and biomechanical data

Ambrósio, Renato, Machado, Aydano P, Leão, Edileuza, Lyra, João Marcelo G, Salomão, Marcella Q, Esporcatte, Louise G Pellegrino, Filho, João BR da Fonseca, Ferreira-Meneses, Erica, Sena, Nelson B, Haddad, Jorge S
et al (show 42 more authors) (2022) Optimized artificial intelligence for enhanced ectasia detection using Scheimpflug-based corneal tomography and biomechanical data. American Journal of Ophthalmology, 251. pp. 126-142.

[img] Text
Ambrosio - AI for ectasia detection using tomo & biomech data 2022.pdf - Author Accepted Manuscript

Download (2MB) | Preview


<h4>Purpose</h4>To optimize artificial intelligence (AI) algorithms to integrate Scheimpflug-based corneal tomography and biomechanics to enhance ectasia detection.<h4>Design</h4>Multicenter cross-sectional case-control retrospective study.<h4>Methods</h4>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.<h4>Results</h4>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).<h4>Conclusions</h4>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.

Item Type: Article
Uncontrolled Keywords: Cornea, Humans, Keratoconus, Dilatation, Pathologic, Tomography, Corneal Topography, Retrospective Studies, Cross-Sectional Studies, ROC Curve, Artificial Intelligence, Corneal Pachymetry
Divisions: Faculty of Science and Engineering > School of Engineering
Depositing User: Symplectic Admin
Date Deposited: 23 Dec 2022 08:21
Last Modified: 19 Dec 2023 02:30
DOI: 10.1016/j.ajo.2022.12.016
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3166770