Improving Visual Field Trend Analysis with OCT and Deeply Regularized Latent-Space Linear Regression

Xu, Linchuan; Asaoka, Ryo; Murata, Hiroshi; Kiwaki, Taichi; Zheng, Yangong; Fujino, Yuri; Tanito, Masaki; Mori, Kazuhiko; Ikeda, Yoko; Kanamoto, Takashi; Yamanishi, Kenji

doi:10.1016/j.ogla.2020.08.002

Cited by 5 publications

(12 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, the complexity of data is reduced, the linear model is strengthened, and overfitting is reduced 11 . This method was used with deep learning models in several studies 1,2 . However, patients are unique even if they have the same pattern, leading to incorrect predictions.…”

Section: Discussionmentioning

confidence: 99%

“…Yuhui et al 12 used a linear regression method in latent space for predicting glaucoma progression. Furthermore, a deeply regularized latent-space linear regression model was applied in another study 1 . However, due to the noisy data, the linear models failed to capture the correct glaucoma progression, especially when only a short series of previous VF was provided.…”

Section: Discussionmentioning

confidence: 99%

“…To predict future VF, previous VF data are commonly used because the VF usually progresses based on the initial defect pattern. Therefore, in many studies, previous VFs were used for learning the progression patterns 1,2 . A variational autoencoder (VAE) was used to estimate future VF in a previous study 3 .…”

Section: Introductionmentioning

confidence: 99%

“…For predicting VF from OCT images, convolutional neural network (CNN) models were mainly used in previous studies 10,11 . To manage the image data, 3D CNN models were introduced in several studies 1,12 . However, the structure-function relationships are different for each individual 7 .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Multimodal Deep Learning Model for Predicting Future Visual Field in Glaucoma Patients

Pham

Han

Shin

2022

Preprint

View full text Add to dashboard Cite

Glaucoma is one of the most common reasons for blindness worldwide, especially in elderly people. Glaucoma can be monitored and treated using visual field (VF) tests. Therefore, predicting the future VF to monitor progression of glaucoma is important. In this paper, we proposed a deep learning model to predict future VF based on previous VF and optical coherence tomography (OCT) images (including thickness map, vertical tomogram, and horizontal tomogram). The image data were analyzed using a ResNet-50 model. Image features and previous VFs were combined, and a long short-term memory (LSTM) network was used to predict future VF. A weighted method was used to detect noisy data. The proposed method was improved when applying weighted loss. The mean absolute error (MAE) was 3.31 ± 1.37, and the root mean square error (RMSE) was 4.58 ± 1.77. The model showed high performance when combining VF data and OCT image data. Furthermore, the model was useful for detecting and re-weighting noisy data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Multimodal Deep Learning Model for Predicting Future Visual Field in Glaucoma Patients

Pham

Han

Shin

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Deeply regularized latent space linear regression focuses on the coefficient and the intercept of the latent space linear regression of the measurement sets to address the heterogeneity in time. This model outperformed PLR 21,33 because glaucomatous VF damage results from the loss of retinal ganglion cells and VF threshold also fluctuates in both the short 4 and long 5 terms. Moreover, VF measurements are associated with considerable noise, 6,7 which hampers the accurate estimation of the speed of VF progression, 8 whereas OCT measurements are highly reproducible.…”

Section: Prediction Of Visual Fieldmentioning

confidence: 99%

A Joint Multitask Learning Model for Cross-sectional and Longitudinal Predictions of Visual Field Using OCT

Asaoka

Murata

et al. 2021

Ophthalmology Science

Self Cite

View full text Add to dashboard Cite

Purpose: We constructed a multitask learning model (latent space linear regression and deep learning [LSLR-DL]) in which the 2 tasks of cross-sectional predictions (using OCT) of visual field (VF; central 10 ) and longitudinal progression predictions of VF (30 ) were performed jointly via sharing the deep learning (DL) component such that information from both tasks was used in an auxiliary manner (The Association for Computing Machinery's Special Interest Group on Knowledge Discovery and Data Mining [SIGKDD] 2021). The purpose of the current study was to investigate the prediction accuracy preparing an independent validation dataset.Design: Cohort study.Participants: Cross-sectional training and testing data sets included the VF (Humphrey Field Analyzer [HFA] 10-2 test) and an OCT measurement (obtained within 6 months) from 591 eyes of 351 healthy people or patients with open-angle glaucoma (OAG) and from 155 eyes of 131 patients with OAG, respectively. Longitudinal training and testing data sets included 7984 VF results (HFA 24-2 test) from 998 eyes of 592 patients with OAG and 1184 VF results (HFA 24-2 test) from 148 eyes of 84 patients with OAG, respectively. Each eye had 8 VF test results (HFA 24-2 test). The OCT sequences within the observation period were used.Methods: Root mean square error (RMSE) was used to evaluate the accuracy of LSLR-DL for the crosssectional prediction of VF (HFA 10-2 test). For the longitudinal prediction, the final (eighth) VF test (HFA 24-2 test) was predicted using a shorter VF series and relevant OCT images, and the RMSE was calculated. For comparison, RMSE values were calculated by applying the DL component (cross-sectional prediction) and the ordinary pointwise linear regression (longitudinal prediction).Main Outcome Measures: Root mean square error in the cross-sectional and longitudinal predictions.Results: Using LSLR-DL, the mean RMSE in the cross-sectional prediction was 6.4 dB and was between 4.4 dB (VF tests 1 and 2) and 3.7 dB (VF tests 1e7) in the longitudinal prediction, indicating that LSLR-DL significantly outperformed other methods.Conclusions: The results of this study indicate that LSLR-DL is useful for both the cross-sectional prediction of VF (HFA 10-2 test) and the longitudinal progression prediction of VF (HFA 24-2 test). Ophthalmology

show abstract

VF-HM: Vision Loss Estimation Using Fundus Photograph for High Myopia

Yan,

Liang,

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Improving Visual Field Trend Analysis with OCT and Deeply Regularized Latent-Space Linear Regression

Cited by 5 publications

References 61 publications

A Multimodal Deep Learning Model for Predicting Future Visual Field in Glaucoma Patients

A Multimodal Deep Learning Model for Predicting Future Visual Field in Glaucoma Patients

A Joint Multitask Learning Model for Cross-sectional and Longitudinal Predictions of Visual Field Using OCT

VF-HM: Vision Loss Estimation Using Fundus Photograph for High Myopia

Contact Info

Product

Resources

About