Assessment and training of functional vision in rehabilitation using Virtual Reality

This project is under the supervision of Gera de Haan, Joost Heutink and Frans Cornelissen, centered at the Royal Dutch Visio and LEO lab at the UMCG. Royal Dutch Visio, as the main beneficiary, aims to improve the wellbeing of partially sighted or blind patients. This research is focused on the analysis of the Hemianopia patients to extract useful knowledge in this regard.

Personal Background and Interest:

Master’s study in Computer Science – Artificial Intelligence with experience in Medical Image Analysis, Pattern Recognition, Machine Learning, and Deep Learning.

Aim of the project: 

The aim of this project is to assess the accuracy, reliability, and feasibility of performing functional vision prediction and training, with a focus on standardized, simulated or real-world environments.

Current activities:

To date, I have designed and tested an automated method for detecting eye-movement events, as measured with modern mobile eye-trackers, during natural viewing experiments. This method uses an artificial intelligence approach, named ACE-DNV, that is capable of accurately classifying gaze events (i.e., replicating human labeling) based only on gaze movement signals and scene camera video footage. Such an automated method can help therapists and researchers quantify scanning behavior while performing daily tasks and therefore help evaluate functional vision in relation to their daily-life activities. I’m currently preparing a manuscript describing this automated method for submission. 

As a secondment, I have recently (March 2023) started a short-term project in the Artificial Intelligence Department at the Donder Institute (Radboud University Nijmegen). Here I’ll create a representation method that encodes information to make it understandable and processable by machines of prosthetic vision for blind people. In this method, I will focus on representing the visual environment while incorporating the blind people's eye-movements.

Future directions:

In the future, I will focus on testing and comparing ACE-DNV with other existing methods on other datasets. Furthermore, I will also focus on using the outputs of ACE-DNV with other artificial intelligence methods for discriminating between people with and without visual field defect.