Correction for the Influence of Cataract on Macular Pigment Measurement by Autofluorescence Technique Using Deep Learning

Abstract

Purpose Measurements of macular pigment optical density (MPOD) by the autofluorescence technique yield underestimations of actual values in eyes with cataract. We applied deep learning (DL) to correct this error. Subjects and Methods MPOD was measured by SPECTRALIS (Heidelberg Engineering, Heidelberg, Germany) in 197 eyes before and after cataract surgery. The nominal MPOD values (= preoperative value) were corrected by three methods: the regression equation (RE) method, subjective classification (SC) method (described in our previous study), and DL method. The errors between the corrected and true values (= postoperative value) were calculated for local MPODs at 0.25°, 0.5°, 1°, and 2° eccentricities and macular pigment optical volume (MPOV) within 9° eccentricity. Results The mean error for MPODs at four eccentricities was 32% without any correction, 15% with correction by RE, 16% with correction by SC, and 14% with correction by DL. The mean error for MPOV was 21% without correction and 14%, 10%, and 10%, respectively, with correction by the same methods. The errors with any correction were significantly lower than those without correction ( P < 0.001, linear mixed model with Tukey's test). The errors with DL correction were significantly lower than those with RE correction in MPOD at 1° eccentricity and MPOV ( P < 0.001) and were equivalent to those with SC correction. Conclusions The objective method using DL was useful to correct MPOD values measured in aged people. Translational Relevance MPOD can be obtained with small errors in eyes with cataract using DL.

Lutein and Zeaxanthin Distribution in the Healthy Macula and Its Association with Various Demographic Factors Examined in Pseudophakic Eyes

“…These values could represent a standard for future investigation on MP. MPOD(0.23), MPOD(0.5), MPOD(1), MPOD(2), and MPOV(9) were consistent with our previous studies [ 18 , 31 , 36 , 37 , 39 , 40 ], and this consistency was expected, since the current study was based in part on the same database, although the number of subjects in the present study was larger. The MPOD levels were higher in areas closer to the foveal center.…”

“…A reason for the present high MP levels was that all the present data were from pseudophakic eyes. In our previous study [ 37 ], the mean error for MPOV in eyes with cataract was 20.5% without any correction. When the values by Green-Gomez et al are corrected with this factor, MPOV(7) is 10,010, which is still lower than our present value.…”

“…Men were 108 (155 eyes), and women were 134 (197 eyes). Some eyes were described in our previous manuscripts and were analyzed in different ways [ 18 , 31 , 36 , 37 , 39 , 40 ].…”

“…Men were 108 (155 eyes), and women were 134 (197 eyes). Some eyes were described in our previous manuscripts and were analyzed in different ways [18,31,36,37,39,40]. All subjects underwent cataract surgery at Seirei Hamamatsu General Hospital between October 2016 and March 2021.…”

“…However, fundus AF spectroscopy has a shortcoming: cataractous lenses can attenuate MPOD levels by absorbing and scattering the excitation and emission light, especially the blue wavelengths. Some correction methods for opacity-induced MPOD level attenuations have been presented [ 34 , 35 , 36 , 37 ], but such models have limitations. Therefore, limiting the measurement of MPOD to eyes with an intraocular lens (IOL) can be useful in clinical studies, especially in aged subjects.…”