Self-supervised denoising of visual field data improves detection of glaucoma progression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Sean, Chen, Jun Yu, Mohammadzadeh, Vahid, Besharati, Sajad, Lee, Jaewon, Nouri-Mahdavi, Kouros, Caprioli, Joseph, Fei, Zhe, Scalzo, Fabien
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916487110852608
author Wu, Sean
Chen, Jun Yu
Mohammadzadeh, Vahid
Besharati, Sajad
Lee, Jaewon
Nouri-Mahdavi, Kouros
Caprioli, Joseph
Fei, Zhe
Scalzo, Fabien
author_facet Wu, Sean
Chen, Jun Yu
Mohammadzadeh, Vahid
Besharati, Sajad
Lee, Jaewon
Nouri-Mahdavi, Kouros
Caprioli, Joseph
Fei, Zhe
Scalzo, Fabien
contents Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12146
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-supervised denoising of visual field data improves detection of glaucoma progression
Wu, Sean
Chen, Jun Yu
Mohammadzadeh, Vahid
Besharati, Sajad
Lee, Jaewon
Nouri-Mahdavi, Kouros
Caprioli, Joseph
Fei, Zhe
Scalzo, Fabien
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression.
title Self-supervised denoising of visual field data improves detection of glaucoma progression
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.12146