Abstract
BackgroundEfficacy and high availability of surgery techniques for refractive defect correction increase the number of patients who undergo to this type of surgery. Regardless of that, with increasing age, more and more patients must undergo cataract surgery. Accurate evaluation of corneal power is an extremely important element affecting the precision of intraocular lens (IOL) power calculation and errors in this procedure could affect quality of life of patients and satisfaction with the service provided. The available device able to measure corneal power have been tested to be not reliable after myopic refractive surgery.MethodsArtificial neural networks with error backpropagation and one hidden layer were proposed for corneal power prediction. The article analysed the features acquired from the Pentacam HR tomograph, which was necessary to measure the corneal power. Additionally, several billion iterations of artificial neural networks were conducted for several hundred simulations of different network configurations and different features derived from the Pentacam HR. The analysis was performed on a PC with Intel® Xeon® X5680 3.33 GHz CPU in Matlab® Version 7.11.0.584 (R2010b) with Signal Processing Toolbox Version 7.1 (R2010b), Neural Network Toolbox 7.0 (R2010b) and Statistics Toolbox (R2010b).Results and conclusionsA total corneal power prediction error was obtained for 172 patients (113 patients forming the training set and 59 patients in the test set) with an average age of 32 ± 9.4 years, including 67% of men. The error was at an average level of 0.16 ± 0.14 diopters and its maximum value did not exceed 0.75 dioptres. The Pentacam parameters (measurement results) providing the above result are tangential anterial/posterior. The corneal net power and equivalent k-reading power. The analysis time for a single patient (a single eye) did not exceed 0.1 s, whereas the time of network training was about 3 s for 1000 iterations (the number of neurons in the hidden layer was 400).
Highlights
Efficacy and high availability of surgery techniques for refractive defect correction increase the number of patients who undergo to this type of surgery
If the patient further develop a cataract, there is the needing of corneal power measurement to perform intraocular lens (IOL) power calculation
The situation is quite different in the case of cataract patients who have been previously subjected to myopic refractive eye surgery: in these patients, the Oculus Pentacam and the other available devices do not allow for fully correct IOL power calculation [14, 15]
Summary
Efficacy and high availability of surgery techniques for refractive defect correction increase the number of patients who undergo to this type of surgery. If the patient further develop a cataract, there is the needing of corneal power measurement to perform IOL power calculation In naïve eyes, this type of measurement able to provide no, or very small, residual refractive defect after lens implantation so there is no need to wear eyeglasses [11,12,13]. The relationship between the performed measurements (corneal thickness, tangential curvature, axial/sagittal curvature, elevation, true power, keratomic power deviation etc.) and the lens power after corneal refractive surgery [21,22,23,24] is not precisely defined [25,26,27,28,29,30,31,32,33,34,35,36], so this article proposes the use of artificial intelligence methods. The proposed proprietary analysis algorithm and the results are presented later in this article
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.