Prediction of the axial lens position after cataract surgery using deep learning algorithms and multilinear regression

Abstract

Background The prediction of anatomical axial intraocular lens position (ALP) is one of the major challenges in cataract surgery. The purpose of this study was to develop and test prediction algorithms for ALP based on deep learning strategies. Methods We evaluated a large data set of 1345 biometric measurements from the IOLMaster 700 before and after cataract surgery. The target parameter was the intraocular lens (IOL) equator plane at half the distance between anterior and posterior apex. The relevant input parameters from preoperative biometry were extracted using a principal component analysis. A selection of neural network algorithms was tested using a 5‐fold cross‐validation procedure to avoid overfitting. The results were then compared with a traditional multilinear regression in terms of root mean squared prediction error (RMSE). Results Corneal radius of curvature, axial length, anterior chamber depth, corneal thickness, lens thickness and patient age were identified as effective predictive parameters, whereas pupil size, horizontal corneal diameter and Chang–Waring chord did not enhance the model. From the tested algorithms, the Gaussian prediction regression and the Support Vector Machine algorithms performed best (RMSE = 0.2805 and 0.2731 mm), outperforming the multilinear prediction model (0.3379 mm). The mean absolute prediction error yielded 0.1998, 0.1948 and 0.2415 mm for the respective models. Conclusion Modern prediction techniques may have the potential to outperform traditional multilinear regression techniques as they can deal easily with nonlinearities between input and output parameters. However, in all cases a cross‐validation is mandatory to avoid overfitting and misinterpretation of the results.

Prediction of IOL decentration, tilt and axial position using anterior segment OCT data

“…We must, however, be aware that there is no common standard as to whether the axial position of the front apex, back apex, IOL equator or the image side principal plane is mentioned. Since the ELP is a fictitious parameter and is biassed by all assumptions and simplifications in IOL power calculation schemes based on a pseudophakic model eye, this value cannot be measured by any practical means [ 5 ].…”

“…This, however, does not coincide with the geometrical axial IOL position in the pseudophakic eye, mostly due to assumptions on the conversion of corneal front surface radius to corneal power. However, modern formulae or numerical raytracing mostly deal with the ‘anatomically correct’ axial lens position (ALP), and this has to be predicted during the biometry and IOL power calculation before cataract surgery [ 4 , 5 ].…”

“…The prediction of the IOL position seems to be a ‘Holy Grail’ of theoretical-optical lens power formulae or raytracing [ 2 , 5 ]. An over-estimation/under-estimation makes the patient’s eye (treated with an IOL with plus power) myopic/hyperopic.…”

Monte‐Carlo simulation of a thick lens IOL power calculation

“…The corresponding calculation scheme for LT or ET from the IOL refractive index and either the radii of the front and back surface or PL and CL is described in another paper (Langenbucher, Hoffmann, et al, 2022). In a previous study, the axial position of the equatorial plane of the crystalline lens (EP) was reported to be located at EP = 0.0393•AL + 0.7549•ACD pre +0.3823•LT pre behind the corneal front vertex (coefficient of determination R 2 = 0.70, root-mean-squared prediction error 0.189 mm, Langenbucher, Szentmáry, et al, 2022c). For our model, we assumed that the thin lens IOL as well as the haptic plane of the thick lens IOL (defined by the centre plane of the optic edge) both match the EP of the phakic eye.…”

Considerations on the Calculation of Multifocal Duet Implantation in a Monovision Scenario for the Correction of Presbyopia – A Case Example

“…3 ). The Castrop formula ELP prediction mode was chosen, as it predicts the axial lens position as the distance from the corneal front surface to the IOL equator 14 , 15 , 16 . Hence, in order to accurately calculate the distance from the corneal front surface to the IOL front surface, the ELP prediction mode has to be corrected by half the central IOL thickness.…”