A Deep Learning-based in silico Framework for Optimization on Retinal Prosthetic Stimulation
Abstract
We propose a neural network-based framework to optimize the perceptions simulated by the in silico retinal implant model pulse2percept. The overall pipeline consists of a trainable encoder, a pre-trained retinal implant model and a pre-trained evaluator. The encoder is a U-Net, which takes the original image and outputs the stimulus. The pre-trained retinal implant model is also a U-Net, which is trained to mimic the biomimetic perceptual model implemented in pulse2percept. The evaluator is a shallow VGG classifier, which is trained with original images. Based on 10,000 test images from the MNIST dataset, we show that the convolutional neural network-based encoder performs significantly better than the trivial downsampling approach, yielding a boost in the weighted F1-Score by 36.17% in the pre-trained classifier with 6×10 electrodes. With this fully neural network-based encoder, the quality of the downstream perceptions can be fine-tuned using gradient descent in an end-to-end fashion.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Image Quality Metrics: PSNR vs. SSIM
Hore, A., & Ziou, D. (2010) · 2010 20th International Conference on Pattern Recognition · doi:10.1109/icpr.2010.579 · Cited by 4,943 · see citing works
Quantitative analysis of cat retinal ganglion cell response to visual stimuli
Rodieck, R. W. (1965) · Vision Research · doi:10.1016/0042-6989(65)90033-7 · Cited by 766 · see citing works
Subretinal visual implant alpha IMS - clinical trial interim report
Stingl, K., Bartz-Schmidt, K. U., Besch, D., Chee, C. K., Cottriall, C. L., Gekeler, F., Groppe, M., Jackson, T. L., MacLaren, R. E., Koitschev, A., et al. (2015) · Vision Research · doi:10.1016/j.visres.2015.03.001 · Cited by 387 · see citing works
The Argus® II Retinal Prosthesis System
Luo, Y. H.-L., & da Cruz, L. (2016) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2015.09.003 · Cited by 351 · see citing works
Photovoltaic Restoration of Central Vision in Atrophic Age-Related Macular Degeneration
Palanker, D., Le Mer, Y., Mohand-Said, S., Muqit, M., & Sahel, J. A. (2020) · Ophthalmology · doi:10.1016/j.ophtha.2020.02.024 · Cited by 227 · cited 1× · see citing works
“Retinal prostheses aim to provide electrical stimulation to different layers of the human retina [1][2][3][4].”
BackgroundVisual Receptors and Retinal Interaction
Hartline, H. K. (1969) · Science · doi:10.1126/science.164.3877.270 · Cited by 181 · see citing works
Roessler, G. F., Laube, T., Brockmann, C., Kirschkamp, T., Mazinani, B. A. E., Goertz, M., Koch, C., Krisch, I., Sellhaus, B., Trieu, H. K., et al. (2009) · Investigative Ophthalmology & Visual Science · doi:10.1167/iovs.08-2752 · Cited by 161 · see citing works
Self-citationA model of ganglion axon pathways accounts for percepts elicited by retinal implants
Beyeler, M., Nanduri, D., Weiland, J. D., Rokem, A., Boynton, G. M., & Fine, I. (2019) · Scientific Reports · doi:10.1038/s41598-019-45416-4 · Cited by 143 · see citing works
Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation
Liu, C. K., Bridson, R., Spencer, S. N., Bargteil, A. W., & van de Panne, M. (2011) · doi:10.1145/2019406 · Cited by 142 · see citing works
A Bayesian interactive optimization approach to procedural animation design
Brochu, E., Brochu, T., & de Freitas, N. (2010) · doi:10.5555/1921427.1921443 · Cited by 132 · see citing works
Erickson-Davis, C., & Korzybska, H. (2021) · PLoS ONE · doi:10.1371/journal.pone.0229189 · Cited by 83 · see citing works
Lindsey, J. W., Ocko, S. A., Ganguli, S., & Deny, S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/511535 · Cited by 82 · see citing works
pulse2percept: A Python-based simulation framework for bionic vision
Beyeler, M., Boynton, G., Fine, I., & Rokem, A. (2017) · Proceedings of the 16th Python in Science Conference · doi:10.25080/shinma-7f4c6e7-00c · Cited by 56 · see citing works
End-to-end optimization of prosthetic vision
de Ruyter van Steveninck, J., Güçlü, U., van Wezel, R., & van Gerven, M. (2022) · Journal of Vision · doi:10.1167/jov.22.2.20 · Cited by 54 · see citing works
End-to-end optimization of prosthetic vision
de Ruyter van Steveninck, J., Güçlü, U., van Wezel, R., & van Gerven, M. (2020) · doi:10.1101/2020.12.19.423601 · Cited by 54 · cited 6× · see citing works
“The bottleneck at the predicted percept is kept as 28×28, which is narrower than 49×49 as in [19] or 256×256 as in [16].”
BackgroundMethodInfluentialvan der Grinten, M., de Ruyter van Steveninck, J., Lozano, A., Pijnacker, L., Rückauer, B., Roelfsema, P., van Gerven, M., van Wezel, R., Güçlü, U., & Güçlütürk, Y. (2022) · doi:10.1101/2022.12.23.521749 · Cited by 39 · see citing works
van der Grinten, M., de Ruyter van Steveninck, J., Lozano, A., Pijnacker, L., Rueckauer, B., Roelfsema, P., van Gerven, M., van Wezel, R., Güçlü, U., & Güçlütürk, Y. (2024) · eLife · doi:10.7554/elife.85812 · Cited by 39 · see citing works
Beyeler, M., & Sanchez-Garcia, M. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/aca69d · Cited by 34 · cited 1× · see citing works
“In the era of deep learning, convolutional neural networks (CNN) became the default option for many tasks [12], including those related to visual prostheses [13][14][15].”
Optimization of Electrical Stimulation for a High-Fidelity Artificial Retina
Shah, N. P., Madugula, S., Grosberg, L., Mena, G., Tandon, P., Hottowy, P., Sher, A., Litke, A., Mitra, S., & Chichilnisky, E. J. (2019) · 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER) · doi:10.1109/ner.2019.8716987 · Cited by 32 · see citing works
A computational model of phosphene appearance for epiretinal prostheses
Granley, J., & Beyeler, M. (2021) · 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629663 · Cited by 27 · see citing works
Deep Learning–Based Perceptual Stimulus Encoder for Bionic Vision
Relic, L., Zhang, B., Tuan, Y.-L., & Beyeler, M. (2022) · Augmented Humans International Conference (AHs) · doi:10.1145/3519391.3524034 · Cited by 18 · see citing works
Human-in-the-loop optimization of visual prosthetic stimulation
Fauvel, T., & Chalk, M. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac7615 · Cited by 15 · see citing works
Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses
Granley, J., Relic, L., & Beyeler, M. (2022) · arXiv · doi:10.48550/arxiv.2205.13623 · Cited by 14 · see citing works
Walter, P., & Mokwa, W. (2005) · Der Ophthalmologe · doi:10.1007/s00347-005-1250-2 · Cited by 12 · see citing works
Self-citationEfficient Exploration in Binary and Preferential Bayesian OptimizationPreprint
Fauvel, T., & Chalk, M. (2021) · arXiv.org · doi:10.48550/arxiv.2110.09361 · Cited by 9 · see citing works
Hu, Z., & Beyeler, M. (2021) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner49283.2021.9441194 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Neural Activity Shaping in Visual Prostheses with Deep Learning
Castro, D., Grayden, D. B., Meffin, H., & Spencer, M. (2023) · doi:10.1101/2023.12.20.572123 · Cited by 4 · see citing works
Neural activity shaping in visual prostheses with deep learning
Castro, D., Grayden, D. B., Hamish Meffin, A., & Spencer, M. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad6186 · Cited by 4 · see citing works
“Also, the decoders presented in the previously mentioned studies (Granley et al 2022, Relic et al 2022, Wu et al 2023) estimate an intermediate mathematical model that approximates the phosphenes elicited by stimulation, as described by the implantee.”
Visual Prostheses in the Era of Artificial Intelligence Technology
Sarbout, I., Gungor, A., Ounissi, M., Zaher, S., Ptito, M., Kupers, R., Racoceanu, D., & Milea, D. (2025) · Eye and Brain · doi:10.2147/eb.s524322 · Cited by 3 · see citing works
“Of the five end-to-end studies that we identified, two relied on auto-encoding strategies, 88,91 where the task to be learnt is reconstructing an original image, and three entailed reinforcement learning approaches, 87,89,90 for which the scope of learned tasks is wider.”
Visual Fixation-Based Retinal Prosthetic Simulation
Wu, Y., Nguyen, D. D. T., Konermann, H., Yilmaz, R., Walter, P., & Stegmaier, J. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980954 · Cited by 1 · see citing works
“To optimize the electrical stimulus delivered to the electrode array of a retinal implant, we utilize a neural network-based encoder positioned at the interface between the camera and the electrode array, following the approach outlined in [7].”
MethodSelf-citationLavoie, J., Besrour, M., Lemaire, W., Rouat, J., Fontaine, R., & Plourde, É. (2023) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/acf1a5
“Many improvements to the original algorithms that use more advanced image processing meth-ods such as Difference of Gaussian [16], constrained optimization [17], and deep learning [18, 19] obtained better results in simulation [20].”
Evaluating Cross-Subject and Cross-Device Consistency in Visual Fixation Prediction
Wu, Y., Konermann, H., Mededovic, E., Walter, P., & Stegmaier, J. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11252754
“Recent studies leverage visual fixation information to enhance the precision of neuroprosthetics [10], [11], which can be integrated into existing neural encoding approaches for visual prosthetics, e.g., [12], [13].”
Self-citationAdaptive vision transformer for enhanced perception in visual prostheses
Tomas-Barba, J., Pérez-Yus, A., Martínez-Cantín, R., Guerrero, J. J., & Bermúdez-Cameo, J. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11253400
“Other methods, which include the axon map model [17], fix patient parameters during training, requiring retraining for each patient [31], [32], [33].”
Influential
- Authors
- Wu, Y., Karetić, I., Stegmaier, J., Walter, P., & Merhof, D.
- Affiliations
- RWTH Aachen University (DE)
- University of Regensburg (DE)
- Venue
- 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
- Publisher
- IEEE
- Published
- 2023-07-24
- Volume
- 2023
- Pages
- 1-4
- ISSN
- 2375-7477 (ISSN-L)
- OpenAlex
- W4389543137
- Cited by
- 6
- References
- 29
- Citations by year
- 2025: 4 · 2024: 1 · 2023: 1
- FWCI
- 7.20
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Deutsche Forschungsgemeinschaft
- Topics
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuroscience and Neural Engineering
- Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Retinal Development and Disorders
- Keywords
- retinal prosthesis, stimulus optimization, U-Net encoder, end-to-end fine-tuning, visual perception simulation, MNIST classification
- MeSH terms
- Deep Learning, Computer Simulation, Image Processing, Computer-Assisted, Retina, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
