Evaluation of artificial intelligence models for the detection of asymmetric keratoconus eyes using Scheimpflug tomography
- 2 July 2022
- journal article
- research article
- Published by Wiley in Clinical & Experimental Ophthalmology
- Vol. 50 (7), 714-723
- https://doi.org/10.1111/ceo.14126
Abstract
Background To evaluate artificial intelligence (AI) models based on objective indices and raw corneal data from the Scheimpflug Pentacam HR system (OCULUS Optikgerate GmbH, Wetzlar, Germany) for the detection of clinically unaffected eyes in patients with asymmetric keratoconus (AKC) eyes. Methods A total of 1108 eyes of 1108 patients were enrolled, including 430 eyes from normal control subjects, 231 clinically unaffected eyes from patients with AKC, and 447 eyes from keratoconus (KC) patients. Eyes were divided into a training set (664 eyes), a test set (222 eyes) and a validation set (222 eyes). AI models were built based on objective indices (XGBoost, LGBM, LR and RF) and entire corneal raw data (KerNet). The discriminating performances of the AI models were evaluated by accuracy and the area under the ROC curve (AUC). Results The KerNet model showed great overall discriminating power in the test (accuracy = 94.67%, AUC = 0.985) and validation (accuracy = 94.12%, AUC = 0.990) sets, which were higher than the index-derived AI models (accuracy = 84.02%-86.98%, AUC = 0.944-0.968). In the test set, the KerNet model demonstrated good diagnostic power for the AKC group (accuracy = 95.24%, AUC = 0.984). The validation set also proved that the KerNet model was useful for AKC group diagnosis (accuracy = 94.12%, AUC = 0.983). Conclusions KerNet outperformed all the index-derived AI models. Based on the raw data of the entire cornea, KerNet was helpful for distinguishing clinically unaffected eyes in patients with AKC from normal eyes.Keywords
Funding Information
- National Key Research and Development Program of China (2020YFE0204400, 2019YFB1404802)
This publication has 38 references indexed in Scilit:
- SOAPdenovo2: an empirically improved memory-efficient short-read de novo assemblerGigaScience, 2012
- Topographic and Tomographic Properties of Forme Fruste Keratoconus CorneasInvestigative Ophthalmology & Visual Science, 2010
- Chasing the suspect: keratoconusBritish Journal of Ophthalmology, 2009
- Risk Assessment for Ectasia after Corneal Refractive SurgeryOphthalmology, 2008
- Changes in Collagen Orientation and Distribution in Keratoconus CorneasInvestigative Ophthalmology & Visual Science, 2005
- Efficient Training Algorithms for a Class of Shunting Inhibitory Convolutional Neural NetworksIEEE Transactions on Neural Networks, 2005
- Longitudinal study of the normal eyes in unilateral keratoconus patientsOphthalmology, 2004
- Subject independent facial expression recognition with robust face detection using a convolutional neural networkNeural Networks, 2003
- Unilateral KeratoconusOphthalmology, 1997
- Molecular Genetic Analysis in Autosomal Dominant KeratoconusCornea, 1992