Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Obana A

PROVIDER: S-EPMC10863874 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Obana Akira A Ote Kibo K Gohto Yuko Y Yamada Hidenao H Hashimoto Fumio F Okazaki Shigetoshi S Asaoka Ryo R

PloS one 20240213 2

<h4>Purpose</h4>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.<h4>Methods</h4>MPODs at 0.25°, 0.5°, 1°, and 2° eccentrici ...[more]

PMID: 38349916

Similar Datasets

Project description:IntroductionTo highlight the differences in macular pigment optical density (MPOD) between eyes with vitreoretinal interface syndrome and healthy control eyes, to assess the changes in MPOD in eyes treated with macular peeling, to investigate the relationships between MPOD changes and measures of retinal sensitivity such as best corrected visual acuity (BCVA) and microperimetry.MethodsIn this cross-sectional comparative study, 30 eyes affected by idiopathic epiretinal membrane (iERM, 15eyes) or full-thickness macular hole (FTMH, 15eyes) were compared with 60 eyes from 30 healthy age-matched patients. MPOD values (mean MPOD, maximum MPOD, MPOD area, and MPOD volume) were measured in a range of 4°-7° of eccentricity around the fovea, using the one-wavelength reflectometry method (Visucam 200, Carl-Zeiss Meditec). Patients affected by iERM and FTMH were treated with vitrectomy and epiretinal membrane-inner limiting membrane (ERM-ILM) peeling, with follow-up examinations performed preoperatively and 6 months postoperatively. The main outcome measures were the differences in MPOD between eyes with vitreoretinal interface syndrome and healthy eyes, changes in MPOD after ERM-ILM peeling, and relationships between MPOD and functional changes.ResultsMean MPOD differed significantly between control eyes and those with iERM (P = .0001) or FTMH (P = .0006). The max MPOD and MPOD area increased, but not significantly. After peeling, the only significant change in MPOD was in MPOD volume (P = .01). In the ERM group, postoperative mean MPOD correlated significantly with best-corrected visual acuity (r = .739, P = .002).ConclusionsMPOD was reduced in patients with iERM or FTMH compared with healthy eyes. We found a significant correlation between the mean postoperative MPOD and postoperative BCVA, hypothesizing that the postoperative increase in mean MPOD could be due to a change in distribution for unfolding and expansion of the fovea after the peeling. MOPD may be considered as a prognostic factor associated with a good visual prognosis in patients with iERM.

Project description:BackgroundPistachios are a bioavailable source of the xanthophyll lutein. Along with zeaxanthin, these plant pigments are major components of macular pigment (MP) in the human retina. MP can be non-invasively measured and is referred to as MP optical density (MPOD). MPOD is modifiable with dietary interventions that include lutein and zeaxanthin (L/Z). Higher MPOD protects the eye from light damage and is positively associated with eye health.ObjectivesThis dietary intervention study aimed to evaluate the effect of pistachio consumption on MPOD.MethodsThis single-blinded, randomized controlled trial compared a 12-week pistachio intervention (2 oz/d) with usual diet (UD) on MPOD and serum L/Z in middle-aged to older healthy adults (n = 36) in a 1:1 randomization scheme. Participants were selected for habitually low L/Z intake and low baseline MPOD. MPOD was measured using heterochromatic flicker photometry at 4 retinal eccentricities during baseline, week 6, and week 12 study visits. Serum L/Z was analyzed using high-performance liquid chromatography. Primary statistical analysis was conducted on an intent-to-treat basis using repeated-measure analysis of variance.ResultsCompared with UD, MPOD of the participants in the pistachio intervention group (PIS) had significantly increased (P < 0.001) at all eccentricities over the initial 6-wk period. This increase was maintained at week 12. MPOD in the UD participants did not change during the 12-week period. Serum lutein concentration followed a similar pattern to MPOD; serum cis-lutein and zeaxanthin did not change in either group over the 12-wk intervention.ConclusionsThe results of our study demonstrate that a dietary intervention with pistachios is efficacious in increasing MPOD in healthy adults selected for habitually low intake of L/Z and low baseline MPOD. This suggests that pistachio consumption could be an effective dietary strategy for preserving eye health. Future studies need to evaluate the generalizability of our findings to other populations. This trial was registered at clinicaltrials.gov as NCT05283941.

Project description:BackgroundSerum lutein (L) and zeaxanthin (Z) positively correlate with macular pigment optical density (MPOD); hence, the latter is a valuable indirect tool for measuring L and Z content in the macula. L and Z have been attributed antioxidant capacity and protection from certain retinal diseases but their uptake within the eye is thought to depend on genetic, age, and environmental factors. In particular, gene variants within beta-carotene monooxygenase (BCMO1) are thought to modulate MPOD in the macula.ObjectivesTo determine the effect of BCMO1 single nucleotide polymorphisms (SNPs) rs11645428, rs6420424, and rs6564851 on MPOD in a cohort of young healthy participants of Caucasian origin with normal ocular health.DesignIn this cohort study, MPOD was assessed in 46 healthy participants (22 male and 24 female) with a mean age of 23.8 ± 4.0 years (range 19-33). The three SNPs, rs11645428, rs6420424, rs6564851 that have established associations with MPOD were determined using MassEXTEND (hME) Sequenom assay. One-way analysis of variance was performed on groups segregated into homozygous and heterozygous BCMO1 genotypes. Correlations between body mass index (BMI), iris color, gender, central retinal thickness (CRT), diet, and MPOD were investigated.ResultsMacular pigment optical density neither significantly varied with BCMO1 rs11645428 (F 2,41 = 0.70, p = 0.503), rs6420424 (F 2,41 = 0.21, p = 0.801) nor rs6464851 homozygous or heterozygous genotypes (F 2,41 = 0,13, p = 0.88), in this young healthy cohort. The combination of these three SNPs into triple genotypes based on plasma conversion efficiency did not affect MPOD (F 2,41 = 0.07, p = 0.9). There was a significant negative correlation with MPOD and CRT (r = -0.39, p = 0.01) but no significant correlation between BMI, iris color, gender, and MPOD.ConclusionOur results indicate that macular pigment deposition within the central retina is not dependent on BCMO1 gene variants in young healthy people. We propose that MPOD is saturated in younger persons and/or other gene variant combinations determine its deposition.

Dataset Information

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

Purpose

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets