Cargando…
End-to-end optimization of prosthetic vision
Neural prosthetics may provide a promising solution to restore visual perception in some forms of blindness. The restored prosthetic percept is rudimentary compared to normal vision and can be optimized with a variety of image preprocessing techniques to maximize relevant information transfer. Extra...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Association for Research in Vision and Ophthalmology
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8899855/ https://www.ncbi.nlm.nih.gov/pubmed/35703408 http://dx.doi.org/10.1167/jov.22.2.20 |
_version_ | 1784663998600314880 |
---|---|
author | de Ruyter van Steveninck, Jaap Güçlü, Umut van Wezel, Richard van Gerven, Marcel |
author_facet | de Ruyter van Steveninck, Jaap Güçlü, Umut van Wezel, Richard van Gerven, Marcel |
author_sort | de Ruyter van Steveninck, Jaap |
collection | PubMed |
description | Neural prosthetics may provide a promising solution to restore visual perception in some forms of blindness. The restored prosthetic percept is rudimentary compared to normal vision and can be optimized with a variety of image preprocessing techniques to maximize relevant information transfer. Extracting the most useful features from a visual scene is a nontrivial task and optimal preprocessing choices strongly depend on the context. Despite rapid advancements in deep learning, research currently faces a difficult challenge in finding a general and automated preprocessing strategy that can be tailored to specific tasks or user requirements. In this paper, we present a novel deep learning approach that explicitly addresses this issue by optimizing the entire process of phosphene generation in an end-to-end fashion. The proposed model is based on a deep auto-encoder architecture and includes a highly adjustable simulation module of prosthetic vision. In computational validation experiments, we show that such an approach is able to automatically find a task-specific stimulation protocol. The results of these proof-of-principle experiments illustrate the potential of end-to-end optimization for prosthetic vision. The presented approach is highly modular and our approach could be extended to automated dynamic optimization of prosthetic vision for everyday tasks, given any specific constraints, accommodating individual requirements of the end-user. |
format | Online Article Text |
id | pubmed-8899855 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | The Association for Research in Vision and Ophthalmology |
record_format | MEDLINE/PubMed |
spelling | pubmed-88998552022-03-08 End-to-end optimization of prosthetic vision de Ruyter van Steveninck, Jaap Güçlü, Umut van Wezel, Richard van Gerven, Marcel J Vis Article Neural prosthetics may provide a promising solution to restore visual perception in some forms of blindness. The restored prosthetic percept is rudimentary compared to normal vision and can be optimized with a variety of image preprocessing techniques to maximize relevant information transfer. Extracting the most useful features from a visual scene is a nontrivial task and optimal preprocessing choices strongly depend on the context. Despite rapid advancements in deep learning, research currently faces a difficult challenge in finding a general and automated preprocessing strategy that can be tailored to specific tasks or user requirements. In this paper, we present a novel deep learning approach that explicitly addresses this issue by optimizing the entire process of phosphene generation in an end-to-end fashion. The proposed model is based on a deep auto-encoder architecture and includes a highly adjustable simulation module of prosthetic vision. In computational validation experiments, we show that such an approach is able to automatically find a task-specific stimulation protocol. The results of these proof-of-principle experiments illustrate the potential of end-to-end optimization for prosthetic vision. The presented approach is highly modular and our approach could be extended to automated dynamic optimization of prosthetic vision for everyday tasks, given any specific constraints, accommodating individual requirements of the end-user. The Association for Research in Vision and Ophthalmology 2022-02-28 /pmc/articles/PMC8899855/ /pubmed/35703408 http://dx.doi.org/10.1167/jov.22.2.20 Text en Copyright 2022 The Authors https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 International License. |
spellingShingle | Article de Ruyter van Steveninck, Jaap Güçlü, Umut van Wezel, Richard van Gerven, Marcel End-to-end optimization of prosthetic vision |
title | End-to-end optimization of prosthetic vision |
title_full | End-to-end optimization of prosthetic vision |
title_fullStr | End-to-end optimization of prosthetic vision |
title_full_unstemmed | End-to-end optimization of prosthetic vision |
title_short | End-to-end optimization of prosthetic vision |
title_sort | end-to-end optimization of prosthetic vision |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8899855/ https://www.ncbi.nlm.nih.gov/pubmed/35703408 http://dx.doi.org/10.1167/jov.22.2.20 |
work_keys_str_mv | AT deruytervansteveninckjaap endtoendoptimizationofprostheticvision AT gucluumut endtoendoptimizationofprostheticvision AT vanwezelrichard endtoendoptimizationofprostheticvision AT vangervenmarcel endtoendoptimizationofprostheticvision |