The usefulness of the Deep Learning method of variational autoencoder to reduce measurement noise in glaucomatous visual fields

Efficacy of Smoothing Algorithms to Enhance Detection of Visual Field Progression in Glaucoma

Purpose

To evaluate and compare the effectiveness of nearest neighbor (NN)- and variational autoencoder (VAE)-smoothing algorithms to reduce variability and enhance the performance of glaucoma visual field (VF) progression models.

Design

Longitudinal cohort study.

Subjects

7150 eyes (4232 patients), with ≥ 5 years of follow-up and ≥ 6 visits.

Methods

Vsual field thresholds were smoothed with the NN and VAE algorithms. The mean total deviation (mTD) and VF index rates, pointwise linear regression (PLR), permutation of PLR (PoPLR), and the glaucoma rate index were applied to the unsmoothed and smoothed data.

Main Outcome Measures

The proportion of progressing eyes and the conversion to progression were compared between the smoothed and unsmoothed data. A simulation series of noiseless VFs with various patterns of glaucoma damage was used to evaluate the specificity of the smoothing models.

Results

The mean values of age and follow-up time were 62.8 (standard deviation: 12.6) years and 10.4 (standard deviation: 4.7) years, respectively. The proportion of progression was significantly higher for the NN and VAE smoothed data compared with the unsmoothed data. VF progression occurred significantly earlier with both smoothed data compared with unsmoothed data based on mTD rates, PLR, and PoPLR methods. The ability to detect the progressing eyes was similar for the unsmoothed and smoothed data in the simulation data.

Conclusions

Smoothing VF data with NN and VAE algorithms improves the signal-to-noise ratio for detection of change, results in earlier detection of VF progression, and could help monitor glaucoma progression more effectively in the clinical setting.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Prediction of visual field progression in glaucoma: existing methods and artificial intelligence

Timely treatment is essential in the management of glaucoma. However, subjective assessment of visual field (VF) progression is not recommended, because it can be unreliable. There are two types of artificial intelligence (AI) strong and weak (machine learning). Weak AIs can perform specific tasks. Linear regression is a method of weak AI. Using linear regression in the real-world clinic has enabled analyzing and predicting VF progression. However, caution is still required when interpreting the results, because whenever the number of VF data sets investigated is small, the predictions can be inaccurate. Several other non-ordinal, or modern AI methods have been constructed to improve prediction accuracy, such as clustering and more modern AI methods of Analysis with Non-Stationary Weibull Error Regression and Spatial Enhancement (ANSWERS), Variational Bayes Linear Regression (VBLR), Kalman Filter and sparse modeling (The least absolute shrinkage and selection operator regression: Lasso). It is also possible to improve the prediction performance using retinal thickness measured with optical coherence tomography by using machine learning methods, such as multitask learning.

Use of artificial intelligence in forecasting glaucoma progression

Artificial intelligence (AI) has been widely used in ophthalmology for disease detection and monitoring progression. For glaucoma research, AI has been used to understand progression patterns and forecast disease trajectory based on analysis of clinical and imaging data. Techniques such as machine learning, natural language processing, and deep learning have been employed for this purpose. The results from studies using AI for forecasting glaucoma progression however vary considerably due to dataset constraints, lack of a standard progression definition and differences in methodology and approach. While glaucoma detection and screening have been the focus of most research that has been published in the last few years, in this narrative review we focus on studies that specifically address glaucoma progression. We also summarize the current evidence, highlight studies that have translational potential, and provide suggestions on how future research that addresses glaucoma progression can be improved.

Survey on electronic visual field data transfer practices among Japan Glaucoma Society board members

BACKGROUND

Visual field (VF) testing in combination with a specialized VF analysis software is critical for characterizing and monitoring visual loss in glaucoma. Although performing glaucoma progression analysis requires original VF data rather than printouts or image files, extent of VF data transfer between referring and referred ophthalmologists is unclear. Here, we surveyed glaucoma specialists who belong to the Japan Glaucoma Society (JGS).

METHODS

An internet survey of daily practice patterns regarding electronic VF data transfer at the time of glaucoma referrals (referring/referred) was sent to all 50 JGS board members. The survey consisted with 11 questionnaires, and the response rate was 100%.

RESULTS

The respondents included 33 university hospital ophthalmologists (66%) (Q1), and those scattered throughout Japan (Q2). All respondents used Humphrey Visual Filed Analyzer (HFA) (Q3) and at least one of a VF progression analysis software (Q4). Ten respondents (20%) actively transferred electronic VF data, while 40 (80%) did not (Q5). The major reasons for not actively transferring data electronically were that there was no support for data transfer by neighboring (n = 26, 65%) and/or own (25, 63%) institutes (Q6). All 40 inactive respondents responded that electronic data transfer is ideal (Q7). All 10 active respondents transferred data using USB flash memory (Q8). Of the 10 active respondents, seven (70%) reported that the percentage of referral letters accompanying electronic VF data in a format that allows for progression analysis from the beginning was less than 25% (Q9). When the referral letters did not accompany the electronic VF data, four (40%) reported that they further requested the data transfer in < 25% of cases (Q10). When the 10 active respondents were requested to transfer data, six (60%) had experienced rejection due to various reasons (Q11).

CONCLUSION

An internet survey showed that 80% of the JGS board members were not actively transferring VF data mainly because of the absence of a system in place at institutions for sending and receiving data, although they feel that the electronic VF data transfer is ideal. The results provide basic data for future discussions on the promotion of the VF data transfer.

Deep learning-assisted (automatic) diagnosis of glaucoma using a smartphone

BACKGROUND/AIMS

To validate a deep learning algorithm to diagnose glaucoma from fundus photography obtained with a smartphone.

METHODS

A training dataset consisting of 1364 colour fundus photographs with glaucomatous indications and 1768 colour fundus photographs without glaucomatous features was obtained using an ordinary fundus camera. The testing dataset consisted of 73 eyes of 73 patients with glaucoma and 89 eyes of 89 normative subjects. In the testing dataset, fundus photographs were acquired using an ordinary fundus camera and a smartphone. A deep learning algorithm was developed to diagnose glaucoma using a training dataset. The trained neural network was evaluated by prediction result of the diagnostic of glaucoma or normal over the test datasets, using images from both an ordinary fundus camera and a smartphone. Diagnostic accuracy was assessed using the area under the receiver operating characteristic curve (AROC).

RESULTS

The AROC with a fundus camera was 98.9% and 84.2% with a smartphone. When validated only in eyes with advanced glaucoma (mean deviation value < -12 dB, N=26), the AROC with a fundus camera was 99.3% and 90.0% with a smartphone. There were significant differences between these AROC values using different cameras.

CONCLUSION

The usefulness of a deep learning algorithm to automatically screen for glaucoma from smartphone-based fundus photographs was validated. The algorithm had a considerable high diagnostic ability, particularly in eyes with advanced glaucoma.