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

Deep learning-based correction of cataract-induced influence on macular pigment optical density measurement by autofluorescence spectroscopy

PURPOSE

Measurements of macular pigment optical density (MPOD) using the autofluorescence spectroscopy yield underestimations of actual values in eyes with cataracts. Previously, we proposed a correction method for this error using deep learning (DL); however, the correction performance was validated through internal cross-validation. This cross-sectional study aimed to validate this approach using an external validation dataset.

METHODS

MPODs at 0.25°, 0.5°, 1°, and 2° eccentricities and macular pigment optical volume (MPOV) within 9° eccentricity were measured using SPECTRALIS (Heidelberg Engineering, Heidelberg, Germany) in 197 (training dataset inherited from our previous study) and 157 eyes (validating dataset) before and after cataract surgery. A DL model was trained to predict the corrected value from the pre-operative value using the training dataset, and we measured the discrepancy between the corrected value and the actual postoperative value. Subsequently, the prediction performance was validated using a validation dataset.

RESULTS

Using the validation dataset, the mean absolute values of errors for MPOD and MPOV corrected using DL ranged from 8.2 to 12.4%, which were lower than values with no correction (P < 0.001, linear mixed model with Tukey's test). The error depended on the autofluorescence image quality used to calculate MPOD. The mean errors in high and moderate quality images ranged from 6.0 to 11.4%, which were lower than those of poor quality images.

CONCLUSION

The usefulness of the DL correction method was validated. Deep learning reduced the error for a relatively good autofluorescence image quality. Poor-quality images were not corrected.

Positive Association between Macular Pigment Optical Density and Glomerular Filtration Rate: A Cross-Sectional Study

Although decreased macular pigment density is associated with the development of age-related macular degeneration (AMD), exactly how this decrease may contribute to the development of AMD is still not fully understood. In this study, we investigated the relationship between macular pigment optical density (MPOD) and estimated glomerular filtration rate (eGFR). MPOD was measured using MPS II (Electron Technology, Cambridge, UK) in 137 participants who showed no clinical signs of AMD at 3 months after cataract surgery, and simple and multiple linear regression analyses were performed to determine the associations with age, sex, abdominal circumference, diabetes, hypertension, smoking, intraocular lens color, visual acuity before and after surgery, and eGFR. The participants were divided into two groups based on the median MPOD (0.58): the high-pigment and low-pigment groups. The mean value of eGFR in the high-pigment group was significantly higher than that in the low-pigment group (64.2 vs. 58.1, p = 0.02). The simple linear regression analysis revealed a significant positive association between MPOD and eGFR (β = 0.0034, 95% confidence interval [CI]: 0.0011-0.0056, p = 0.0038), and this association was independent of age, sex, abdominal circumference, diabetes, smoking, hypertension, best-corrected visual acuity (BCVA) before surgery, BCVA after surgery, and intraocular lens color (β = 0.0033, 95% CI: 0.00090-0.0058, p = 0.0076). These results show a strong association of renal dysfunction with the decrease in MPOD.

Macular and Plasma Xanthophylls Are Higher in Age-related Macular Degeneration than in Normal Aging: Alabama Study on Early Age-related Macular Degeneration 2 Baseline

Purpose

Quantification of retinal xanthophyll carotenoids in eyes with and without age-related macular degeneration (AMD) via macular pigment optical volume (MPOV), a metric for xanthophyll abundance from dual wavelength autofluorescence, plus correlations to plasma levels, could clarify the role of lutein (L) and zeaxanthin (Z) in health, AMD progression, and supplementation strategies.

Design

Cross-sectional observational study (NCT04112667).

Participants

Adults ≥ 60 years from a comprehensive ophthalmology clinic, with healthy maculas or maculas meeting fundus criteria for early or intermediate AMD.

Methods

Macular health and supplement use was assessed by the Age-related Eye Disease Study (AREDS) 9-step scale and self-report, respectively. Macular pigment optical volume was measured from dual wavelength autofluorescence emissions (Spectralis, Heidelberg Engineering). Non-fasting blood draws were assayed for L and Z using high-performance liquid chromatography. Associations among plasma xanthophylls and MPOV were assessed adjusting for age.

Main Outcome Measures

Age-related macular degeneration presence and severity, MPOV in fovea-centered regions of radius 2.0° and 9.0°; plasma L and Z (μM/ml).

Results

Of 809 eyes from 434 persons (89% aged 60-79, 61% female), 53.3% eyes were normal, 28.2% early AMD, and 18.5% intermediate AMD. Macular pigment optical volume 2° and 9° were similar in phakic and pseudophakic eyes, which were combined for analysis. Macular pigment optical volume 2° and 9° and plasma L and Z were higher in early AMD than normal and higher still in intermediate AMD (P < 0.0001). For all participants, higher plasma L was correlated with higher MPOV 2° (Spearman correlation coefficient [Rs] = 0.49; P < 0.0001). These correlations were significant (P < 0.0001) but lower in normal (Rs = 0.37) than early and intermediate AMD (Rs = 0.52 and 0.51, respectively). Results were similar for MPOV 9°. Plasma Z, MPOV 2°, and MPOV 9° followed this same pattern of associations. Associations were not affected by supplement use or smoking status.

Conclusions

A moderate positive correlation of MPOV with plasma L and Z comports with regulated xanthophyll bioavailability and a hypothesized role for xanthophyll transfer in soft drusen biology. An assumption that xanthophylls are low in AMD retina underlies supplementation strategies to reduce progression risk, which our data do not support. Whether higher xanthophyll levels in AMD are due to supplement use cannot be determined in this study.

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

The macular pigment consisting of lutein (L) and zeaxanthin (Z) protects photoreceptors via its antioxidative and barrier activities. This study aimed to determine L and Z distribution in the healthy macula and their association with various demographic factors. Macular pigment optical density (MPOD) was measured using fundus autofluorescence spectroscopy in 352 pseudophakic eyes with no fundus diseases. Pseudophakia was chosen to avoid the influence of cataract in the measurement of fundus autofluorescence. The mean patient age was 72.3 ± 8.6 years. MPOD was analyzed separately in three zones, i.e., A: a central area within a radius of 0.5°, mainly containing Z; B: a ring area with radii from 0.5° to 1.3°, containing Z and L; C: a ring area with radii from 1.3° to 9°, containing L. Multivariate analyses were performed with MPOD as the dependent variable and sex, supplement intake, smoking habits, glaucoma, diabetes, age, body mass index (BMI), skin carotenoid levels, retinal thickness, retinal volume, axial length as the independent variables. The mean total MPOD volume within 9° eccentricity was 20,121 ± 6293. Age was positively associated with MPOD in all zones. Supplement and BMI were positively and negatively associated with MPOD in zones B and C. Smoking was negatively associated with MPOD in zone A. This study revealed the standard MP values of aged Japanese, which resulted to be higher than the previously reported values in other races. Age was found to have a positive association with MP values. L in the outer foveola was affected by BMI and supplements, but Z in the foveola was not. The amount of Z in the Müller cell cone may not be changed easily by factors such as hunger and satiety in the context of preservation of homeostasis in the human body, but tobacco had a negative effect on Z.