End-to-end optimization of prosthetic vision
- PMID: 35703408
- PMCID: PMC8899855
- DOI: 10.1167/jov.22.2.20
End-to-end optimization of prosthetic vision
Abstract
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.
Figures
![Figure 1.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f001.gif)
![Figure 2.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f002.gif)
![Figure 3.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f003.gif)
![Figure 4.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f004.gif)
![Figure 5.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f005.gif)
![Figure 6.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f006.gif)
![Figure 7.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f007.gif)
![Figure 8.](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8899855/bin/jovi-22-2-20-f008.gif)
Similar articles
-
Towards biologically plausible phosphene simulation for the differentiable optimization of visual cortical prostheses.Elife. 2024 Feb 22;13:e85812. doi: 10.7554/eLife.85812. Elife. 2024. PMID: 38386406 Free PMC article.
-
The Influence of Phosphene Synchrony in Driving Object Binding in a Simulation of Artificial Vision.Invest Ophthalmol Vis Sci. 2023 Dec 1;64(15):5. doi: 10.1167/iovs.64.15.5. Invest Ophthalmol Vis Sci. 2023. PMID: 38051263 Free PMC article.
-
Semantic and structural image segmentation for prosthetic vision.PLoS One. 2020 Jan 29;15(1):e0227677. doi: 10.1371/journal.pone.0227677. eCollection 2020. PLoS One. 2020. PMID: 31995568 Free PMC article.
-
Simulating prosthetic vision: I. Visual models of phosphenes.Vision Res. 2009 Jun;49(12):1493-506. doi: 10.1016/j.visres.2009.02.003. Vision Res. 2009. PMID: 19504749 Review.
-
Rehabilitation regimes based upon psychophysical studies of prosthetic vision.J Neural Eng. 2009 Jun;6(3):035009. doi: 10.1088/1741-2560/6/3/035009. Epub 2009 May 20. J Neural Eng. 2009. PMID: 19458400 Review.
Cited by
-
Axonal stimulation affects the linear summation of single-point perception in three Argus II users.J Neural Eng. 2024 Apr 8;21(2):026031. doi: 10.1088/1741-2552/ad31c4. J Neural Eng. 2024. PMID: 38457841 Free PMC article.
-
Towards biologically plausible phosphene simulation for the differentiable optimization of visual cortical prostheses.Elife. 2024 Feb 22;13:e85812. doi: 10.7554/eLife.85812. Elife. 2024. PMID: 38386406 Free PMC article.
-
Neuromorphic hardware for somatosensory neuroprostheses.Nat Commun. 2024 Jan 16;15(1):556. doi: 10.1038/s41467-024-44723-3. Nat Commun. 2024. PMID: 38228580 Free PMC article. Review.
-
Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses.Adv Neural Inf Process Syst. 2022 Dec;35:22671-22685. Adv Neural Inf Process Syst. 2022. PMID: 37719469 Free PMC article.
-
A novel simulation paradigm utilising MRI-derived phosphene maps for cortical prosthetic vision.J Neural Eng. 2023 Aug 10;20(4):046027. doi: 10.1088/1741-2552/aceca2. J Neural Eng. 2023. PMID: 37531948 Free PMC article.
References
-
- Asgari Taghanaki, S., Abhishek, K., Cohen, J. P., Cohen-Adad, J., & Hamarneh, G. (2021). Deep semantic segmentation of natural and medical images: A review. Artificial Intelligence Review, 54(1), 137–178.
-
- Beauchamp, M. S., & Yoshor, D. (2020). Stimulating the brain to restore vision. Science, 370(6521), 1168–1169. - PubMed
-
- Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798–1828. - PubMed
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources