Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program

Purpose: To develop DeepISP, a deep learning model that predicts the comprehensive visual field (VF) information of the Humphrey visual field analyzer (HFA) based on rapid screening perimetry (Imo/TEMPO screening program [ISP]). Design: A retrospective, cross-sectional, and longitudinal cohort datab...

Full description

Saved in:
Bibliographic Details
Main Authors: Kei Sano, MD, PhD, Euido Nishijima, MD, PhD, Shunsuke Sumi, MD, PhD, Takahiko Noro, MD, PhD, Shumpei Ogawa, MD, PhD, Yuka Igari, MD, Aiko Iwase, MD, PhD, Tadashi Nakano, MD, PhD
Format: Article
Language:English
Published: Elsevier 2025-11-01
Series:Ophthalmology Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666914525001034
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715909600477184
author Kei Sano, MD, PhD
Euido Nishijima, MD, PhD
Shunsuke Sumi, MD, PhD
Takahiko Noro, MD, PhD
Shumpei Ogawa, MD, PhD
Yuka Igari, MD
Aiko Iwase, MD, PhD
Tadashi Nakano, MD, PhD
author_facet Kei Sano, MD, PhD
Euido Nishijima, MD, PhD
Shunsuke Sumi, MD, PhD
Takahiko Noro, MD, PhD
Shumpei Ogawa, MD, PhD
Yuka Igari, MD
Aiko Iwase, MD, PhD
Tadashi Nakano, MD, PhD
author_sort Kei Sano, MD, PhD
collection DOAJ
description Purpose: To develop DeepISP, a deep learning model that predicts the comprehensive visual field (VF) information of the Humphrey visual field analyzer (HFA) based on rapid screening perimetry (Imo/TEMPO screening program [ISP]). Design: A retrospective, cross-sectional, and longitudinal cohort database study. Participants: One hundred eighty-seven actual ISPs from 112 patients who underwent both ISP and HFA 24-2 on the same day at the Jikei University School of Medicine Affiliated Hospital and 3470 synthesized ISPs from 883 patients who underwent VF measurements using HFA 24-2 and HFA 10-2 at 4 hospitals affiliated with Jikei University School of Medicine. Methods: We developed 2 variants of multitask neural networks designed to predict both current VF parameters and VF progression parameters. We also evaluated the efficacy of data augmentation to synthesize ISP tests created by combining 20 points from HFA 24-2 and 8 points from HFA 10-2, with thresholding applied to these 28 points. Main Outcome Measures: Mean absolute error for mean deviation (MD), pattern standard deviation (PSD), and visual field index (VFI). Mean F1 score for total deviation (TD) and pattern deviation (PD) probability plot classification. Area under the curve (AUC) for MD progression (MD slope <−1.0 decibel/year) and VFI progression (VFI slope <−1.8%/year). Results: DeepISP could predict current VF status. Mean absolute errors for predicting MD, PSD, and VFI were 1.869 ± 0.114, 1.918 ± 0.082, and 5.146 ± 0.487, respectively. The mean F1 scores for pointwise classification of TD and PD probability plots were 0.761 ± 0.002 and 0.775 ± 0.002, respectively. The AUC for classifying glaucoma hemifield test was 0.920 ± 0.008. DeepISP was also capable of predicting VF progression, with AUCs of 0.828 ± 0.060 and 0.832 ± 0.062 for predicting MD and VFI progression, respectively. Conclusions: We demonstrated ISP's versatility and capability in predicting comprehensive VF information, including current severity and progression risk. Our DeepISP serves as an efficient tool for screening and prioritizing patients with glaucoma for clinical intervention using only a single rapid ISP test. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
format Article
id doaj-art-cd7e2929bcb646fb8fb601e666bbbe11
institution DOAJ
issn 2666-9145
language English
publishDate 2025-11-01
publisher Elsevier
record_format Article
series Ophthalmology Science
spelling doaj-art-cd7e2929bcb646fb8fb601e666bbbe112025-08-20T03:13:11ZengElsevierOphthalmology Science2666-91452025-11-015610080510.1016/j.xops.2025.100805Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening ProgramKei Sano, MD, PhD0Euido Nishijima, MD, PhD1Shunsuke Sumi, MD, PhD2Takahiko Noro, MD, PhD3Shumpei Ogawa, MD, PhD4Yuka Igari, MD5Aiko Iwase, MD, PhD6Tadashi Nakano, MD, PhD7Department of Ophthalmology, The Jikei University School of Medicine, Tokyo, JapanDepartment of Ophthalmology, The Jikei University School of Medicine, Tokyo, Japan; Correspondence: Euido Nishijima, MD, PhD, Department of Ophthalmology, The Jikei University School of Medicine, 3-25-8, Nishi-Shimbashi, Minato-ku, Tokyo 105-8461, Japan.Institute for Quantitative Biosciences (IQB), University of Tokyo, Tokyo, Japan; Graduate School of Medicine, Kyoto University, Kyoto, Japan; Shunsuke Sumi, MD, PhD, Institute for Quantitative Biosciences (IQB), University of Tokyo, 1-1-1 Yayoi, Bunkyo-ku, Tokyo 113-0032, Japan.Department of Ophthalmology, The Jikei University School of Medicine, Tokyo, JapanDepartment of Ophthalmology, The Jikei University School of Medicine, Tokyo, JapanDepartment of Ophthalmology, The Jikei University School of Medicine, Tokyo, JapanTajimi Iwase Eye Clinic, Tajimi, JapanDepartment of Ophthalmology, The Jikei University School of Medicine, Tokyo, Japan; Tadashi Nakano, MD, PhD, Department of Ophthalmology, The Jikei University School of Medicine, 3-25-8, Nishi-Shimbashi, Minato-ku, Tokyo 105-8461, Japan.Purpose: To develop DeepISP, a deep learning model that predicts the comprehensive visual field (VF) information of the Humphrey visual field analyzer (HFA) based on rapid screening perimetry (Imo/TEMPO screening program [ISP]). Design: A retrospective, cross-sectional, and longitudinal cohort database study. Participants: One hundred eighty-seven actual ISPs from 112 patients who underwent both ISP and HFA 24-2 on the same day at the Jikei University School of Medicine Affiliated Hospital and 3470 synthesized ISPs from 883 patients who underwent VF measurements using HFA 24-2 and HFA 10-2 at 4 hospitals affiliated with Jikei University School of Medicine. Methods: We developed 2 variants of multitask neural networks designed to predict both current VF parameters and VF progression parameters. We also evaluated the efficacy of data augmentation to synthesize ISP tests created by combining 20 points from HFA 24-2 and 8 points from HFA 10-2, with thresholding applied to these 28 points. Main Outcome Measures: Mean absolute error for mean deviation (MD), pattern standard deviation (PSD), and visual field index (VFI). Mean F1 score for total deviation (TD) and pattern deviation (PD) probability plot classification. Area under the curve (AUC) for MD progression (MD slope <−1.0 decibel/year) and VFI progression (VFI slope <−1.8%/year). Results: DeepISP could predict current VF status. Mean absolute errors for predicting MD, PSD, and VFI were 1.869 ± 0.114, 1.918 ± 0.082, and 5.146 ± 0.487, respectively. The mean F1 scores for pointwise classification of TD and PD probability plots were 0.761 ± 0.002 and 0.775 ± 0.002, respectively. The AUC for classifying glaucoma hemifield test was 0.920 ± 0.008. DeepISP was also capable of predicting VF progression, with AUCs of 0.828 ± 0.060 and 0.832 ± 0.062 for predicting MD and VFI progression, respectively. Conclusions: We demonstrated ISP's versatility and capability in predicting comprehensive VF information, including current severity and progression risk. Our DeepISP serves as an efficient tool for screening and prioritizing patients with glaucoma for clinical intervention using only a single rapid ISP test. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.http://www.sciencedirect.com/science/article/pii/S2666914525001034GlaucomaVisual fieldPerimetryScreeningDeep learning
spellingShingle Kei Sano, MD, PhD
Euido Nishijima, MD, PhD
Shunsuke Sumi, MD, PhD
Takahiko Noro, MD, PhD
Shumpei Ogawa, MD, PhD
Yuka Igari, MD
Aiko Iwase, MD, PhD
Tadashi Nakano, MD, PhD
Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program
Ophthalmology Science
Glaucoma
Visual field
Perimetry
Screening
Deep learning
title Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program
title_full Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program
title_fullStr Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program
title_full_unstemmed Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program
title_short Deep Learning–Based Prediction of Glaucoma Severity and Progression Using Imo/TEMPO Screening Program
title_sort deep learning based prediction of glaucoma severity and progression using imo tempo screening program
topic Glaucoma
Visual field
Perimetry
Screening
Deep learning
url http://www.sciencedirect.com/science/article/pii/S2666914525001034
work_keys_str_mv AT keisanomdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT euidonishijimamdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT shunsukesumimdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT takahikonoromdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT shumpeiogawamdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT yukaigarimd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT aikoiwasemdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram
AT tadashinakanomdphd deeplearningbasedpredictionofglaucomaseverityandprogressionusingimotemposcreeningprogram