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

PLOS ONE · 11 authors, 4 centres

AI SUMMARY

FIDELITY 100%

POPULATIONEyes with cataracts undergoing cataract surgery (157 validation eyes from a Japanese single-facility cohort)

INTERVENTIONDeep learning–based correction of preoperative MPOD and MPOV values using a VGG16 network trained on autofluorescence images

COMPARISONUncorrected preoperative MPOD and MPOV values versus postoperative measured values (ground truth)

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

Correction was effective for high- and moderate-quality autofluorescence images but not for poor-quality images.

Full summary

827 CHARS

This study externally validated a deep learning correction method for cataract-induced underestimation of macular pigment optical density (MPOD) measured by autofluorescence spectroscopy. MPOD at four eccentricities and macular pigment optical volume (MPOV) were measured in 197 training eyes and 157 validation eyes before and after cataract surgery using SPECTRALIS. A VGG16-based deep learning model was trained to predict correction factors from preoperative autofluorescence images, and its performance was evaluated on the external validation dataset. Mean absolute errors for DL-corrected MPOD and MPOV ranged from 8.2% to 12.4%, significantly lower than uncorrected errors of 21.2% to 39.0% (P < 0.001). The method is proposed as suitable for estimating MPOV in eyes with relatively good autofluorescence image quality.

PICO

PPOPULATION

Eyes with cataracts undergoing cataract surgery (157 validation eyes from a Japanese single-facility cohort)

IINTERVENTION

Deep learning–based correction of preoperative MPOD and MPOV values using a VGG16 network trained on autofluorescence images

OOUTCOME

Mean absolute error of corrected MPOD at 0.25°, 0.5°, 1°, and 2° eccentricities and MPOV within 9° eccentricity

STUDY TYPE

cohort

SPECIALTY

ophthalmology

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10863874

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

PLOS ONE

READ THE FULL PAPER

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.

CITATION EXPORT

Akira Obana, Kibo Ote, Yuko Gohto et al.. Deep learning-based correction of cataract-induced influence on macular pigment optical density measurement by autofluorescence spectroscopy. PLOS ONE. (2024). https://doi.org/10.1371/journal.pone.0298132

AUTHORS

11 · 4 CENTRES

Akira Obana, Kibo Ote, Yuko Gohto, Hidenao Yamada, Fumio Hashimoto, Shigetoshi Okazaki, Ryo Asaoka, Tatsuya Inoue, Tatsuya Inoue, Tatsuya Inoue, Tatsuya Inoue

1 Department of Ophthalmology, Seirei Hamamatsu General Hospital, Hamamatsu City, Shizuoka, Japan
2 Department of Medical Spectroscopy, Institute for Medical Photonics Research, Preeminent Medical Photonics Education & Research Center, Hamamatsu University School of Medicine, Hamamatsu, Shizuoka, Japan
3 Central Research Laboratory, Hamamatsu Photonics K.K., Hamamatsu, Shizuoka, Japan
Yokohama City University, JAPAN

EDITOR / REVIEWER

Tatsuya Inoue