Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-41138
Titel: Prediction of corneal back surface power - Deep learning algorithm versus multivariate regression
VerfasserIn: Langenbucher, Achim
Szentmáry, Nóra
Cayless, Alan
Weisensee, Johannes
Wendelstein, Jascha
Hoffmann, Peter
Sprache: Englisch
Titel: Ophthalmic & Physiological Optics
Bandnummer: 42 (2022)
Heft: 1
Seiten: 185-194
Verlag/Plattform: Wiley
Erscheinungsjahr: 2021
Freie Schlagwörter: biometry
corneal back surface power
deep learning algorithm
feedforward multi-output network
neural network
posterior corneal astigmatism
DDC-Sachgruppe: 610 Medizin, Gesundheit
Dokumenttyp: Journalartikel / Zeitschriftenartikel
Abstract: Background: The corneal back surface is known to add some against the rule astigmatism, with implications in cataract surgery with toric lens implantation. This study aimed to set up and validate a deep learning algorithm to predict corneal back surface power from the corneal front surface power and biometric measures. Methods: This study was based on a large dataset of IOLMaster 700 measurements from two clinical centres. N = 19,553 measurements of 19,553 eyes with valid corneal front (CFSPM) and back surface power (CBSPM) data and other biometric measures. After a vector decomposition of CFSPM and CBSPM into equivalent power and projections of astigmatism to the 0°/90° and 45°/135° axes, a multioutput feedforward neural network was derived to predict vector components of CBSPM from CFSPM and other measurements. The predictions were compared with a multivariate linear regression model based on CFSPM components only. Results: After pre-conditioning, a network with two hidden layers each having 12 neurons was derived. The dataset was split into training (70%), validation (15%) and test (15%) subsets. The prediction error (predicted corneal back surface power CBSPP – CBSPM) of the network after training and crossvalidation showed no systematic offset, narrower distributions for CBSPP – CBSPM and no trend error of CBSPP – CBSPM vs. CBSPM for any of the vector components. The multivariate linear model also showed no systematic offset, but broader distributions of the prediction error components and a systematic trend of all vector components vs. CFSPM components. Conclusion: The neural network approach based on CFSPM vector components and other biometric measures outperforms the multivariate linear model in predicting corneal back surface power vector components. Modern biometers can supply all parameters required for this algorithm, enabling reliable predictions for corneal back surface data where direct corneal back surface data are unavailable.
DOI der Erstveröffentlichung: 10.1111/opo.12909
URL der Erstveröffentlichung: https://doi.org/10.1111/opo.12909
Link zu diesem Datensatz: urn:nbn:de:bsz:291--ds-411384
hdl:20.500.11880/36924
http://dx.doi.org/10.22028/D291-41138
ISSN: 1475-1313
0275-5408
Datum des Eintrags: 22-Nov-2023
Fakultät: M - Medizinische Fakultät
Fachrichtung: M - Augenheilkunde
Professur: M - Univ.-Prof. Dr. Dipl.-Ing. Achim Langenbucher
M - Prof. Dr. med. Nóra Szentmáry
Sammlung:SciDok - Der Wissenschaftsserver der Universität des Saarlandes



Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons