Patient-attentive sequential strategy for perimetry-based visual field acquisition

Kucur, Şerife Seda; Márquez-Neila, Pablo; Abegg, Mathias; Sznitman, Raphael

doi:10.1016/j.media.2019.03.002

Cited by 6 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This also agrees with the aforementioned observation that the Pearson correlation between visual field thresholds at different locations are very high. A larger artificial neural network, such as the ones used in more complicated algorithms [ 21 ], may provide a better performance, but defeats the practicality of a simple and robust method. Similarly, we have also tried ensembled-based methods, such as random forest and gradient boosting, which also has the capability to reduce overfitting, but they did not offer superior performance than TTPCR and PLS, and took much longer to train.…”

Section: Discussionmentioning

confidence: 99%

Improving the robustness of the Sequentially Optimized Reconstruction Strategy (SORS) for visual field testing

Shi,

Eizenman,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Perimetry, or visual field test, estimates differential light sensitivity thresholds across many locations in the visual field (e.g., 54 locations in the 24–2 grid). Recent developments have shown that an entire visual field may be relatively accurately reconstructed from measurements of a subset of these locations using a linear regression model. Here, we show that incorporating a dimensionality reduction layer can improve the robustness of this reconstruction. Specifically, we propose to use principal component analysis to transform the training dataset to a lower dimensional representation and then use this representation to reconstruct the visual field. We named our new reconstruction method the transformed-target principal component regression (TTPCR). When trained on a large dataset, our new method yielded results comparable with the original linear regression method, demonstrating that there is no underfitting associated with parameter reduction. However, when trained on a small dataset, our new method used on average 22% fewer trials to reach the same error. Our results suggest that dimensionality reduction techniques can improve the robustness of visual field testing reconstruction algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

Improving the robustness of the Sequentially Optimized Reconstruction Strategy (SORS) for visual field testing

Shi,

Eizenman,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…We tackle this issue explicitly by imposing a very low return to actions that have already affected the agent's state, whereby forcing the policy to assign them zero probability. Formally, we impose π(s, a t ) = 0 if a t ∈ A asked,t−1 as in Kucur et al (2019).…”

Section: Masked Policymentioning

confidence: 99%

A reinforcement learning approach for VQA validation: An application to diabetic macular edema grading

Fountoukidou

Sznitman

2023

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

“…For the third step, we use Zippy Estimation by Sequential Testing (ZEST) (King-Smith et al 1994) method to estimate the sensitivity threshold at each location. Our approach differs from recent works, such as Patient-Adaptive Sampling Strategy (PASS) (Kucur et al 2019), which only selects a predefined number of locations to be tested. Our method optimizes the entire visual field testing sequence and shows improved test accuracy compared to PASS.…”

Section: Introductionmentioning

confidence: 99%

“…To address this trade-off between speed and accuracy, previous research has either proposed reducing the testing duration by testing only a selected number of locations (Kucur and Sznitman 2017;Kucur et al 2019) or predicting the sensitivity threshold values (Shon, Sung, and Shin 2022;Park, Kim, and Lee 2019). In our work, we adopt a unique approach by using potential-based reward shaping to strike a balance between speed and accuracy.…”

Section: Introductionmentioning

confidence: 99%

RLPeri: Accelerating Visual Perimetry Test with Reinforcement Learning and Convolutional Feature Extraction

Verma,

Le Dinh,

Tan

et al. 2024

AAAI

View full text Add to dashboard Cite

Visual perimetry is an important eye examination that helps detect vision problems caused by ocular or neurological conditions. During the test, a patient's gaze is fixed at a specific location while light stimuli of varying intensities are presented in central and peripheral vision. Based on the patient's responses to the stimuli, the visual field mapping and sensitivity are determined. However, maintaining high levels of concentration throughout the test can be challenging for patients, leading to increased examination times and decreased accuracy. In this work, we present RLPeri, a reinforcement learning-based approach to optimize visual perimetry testing. By determining the optimal sequence of locations and initial stimulus values, we aim to reduce the examination time without compromising accuracy. Additionally, we incorporate reward shaping techniques to further improve the testing performance. To monitor the patient's responses over time during testing, we represent the test's state as a pair of 3D matrices. We apply two different convolutional kernels to extract spatial features across locations as well as features across different stimulus values for each location. Through experiments, we demonstrate that our approach results in a 10-20% reduction in examination time while maintaining the accuracy as compared to state-of-the-art methods. With the presented approach, we aim to make visual perimetry testing more efficient and patient-friendly, while still providing accurate results.

show abstract

Patient-attentive sequential strategy for perimetry-based visual field acquisition

Cited by 6 publications

References 33 publications

Improving the robustness of the Sequentially Optimized Reconstruction Strategy (SORS) for visual field testing

Improving the robustness of the Sequentially Optimized Reconstruction Strategy (SORS) for visual field testing

A reinforcement learning approach for VQA validation: An application to diabetic macular edema grading

RLPeri: Accelerating Visual Perimetry Test with Reinforcement Learning and Convolutional Feature Extraction

Contact Info

Product

Resources

About