Visual Prostheses in the Era of Artificial Intelligence Technology
Open accessThe DOI matches its Crossref record; 108 of the 108 references it cites were found in a registry or an index; 58 of the 88 sources its claims cite were checked for support.
Abstract
Background: Over the past few decades, technological advancements have transformed invasive visual prostheses from theoretical concepts into real-world applications. However, functional outcomes remain limited, especially in visual acuity. This review aims to summarize current developments in retinal and cortical prostheses (RCPs) and critically assess the role of artificial intelligence (AI) in advancing these systems. Purpose: To describe current RCPs and provide a systematic review on image and signal processing algorithms designed for improved clinical outcomes. Patients and Methods: We performed a systematic review of the literature related to AI subserving prosthetic vision, using mainly PubMed, but also, Elicit, a dedicated AI-based reference research assistant. A total of 455 studies were screened on PubMed, of which 23 were retained for inclusion. An additional 5 studies were identified and included through Elicit. Results: The analysis of current RCPs highlights various limitations affecting the quality of the visual flow provided by current artificial vision. Indeed, the 28 reviewed studies on AI covered two applications for RCPs including extraction of saliency in camera captured images, and consistency between electrical stimulation and perceived phosphenes. A total of 14 out of 28 studies involved the use of artificial neural networks, of which 12 included model training. Evaluation with data from a visual prosthesis was conducted in 7 studies, including 1 that was prospectively assessed with a human RCP. Validation with empirical data from human or animal data was performed in 22 out of 28 studies. Out of these, 15 were validated using simulated prosthetic vision. Finally, out of 22 studies leveraging a mathematical model for phosphenes perception, 14 used a symmetrical oversimplified modeling. Conclusion: AI algorithms show promise in optimizing prosthetic vision, particularly through enhanced image saliency extraction and stimulation strategies. However, most current studies are based on simulations. Further development and validation in real-world settings, especially through clinical testing with blind patients, are essential to assess their true effectiveness.
Overview
CoChat Summary
TL;DR
This systematic review examines retinal and cortical prostheses and AI/image-processing methods intended to improve prosthetic vision, identifying saliency extraction and stimulation–phosphene consistency as the two main applications. It finds most AI studies rely on simulations and oversimplified phosphene models, with limited validation in real prosthetic users.
Key findings
- Of 455 PubMed records screened, 23 met inclusion criteria and 5 additional studies were identified via Elicit, yielding 28 AI studies; 14/28 used artificial neural networks, and 12 included model training.
- Validation was mostly indirect: 22/28 studies used empirical human or animal data, 15 used simulated prosthetic vision, 7 used data from a visual prosthesis, and only 1 was prospectively assessed with a human RCP.
- Among 22 studies using a mathematical model of phosphene perception, 14 used symmetrical oversimplified modeling; only 8 used asymmetric models, including 5 with an axon-map model.
- AI applications split into saliency extraction from camera-captured images and optimization of consistency between electrical stimulation and perceived phosphenes; 12/28 studies included dynamic aspects of vision, while 16/28 considered only static measurements or images.
Methods
- Systematic review of literature on AI, machine learning, or image processing for retinal and cortical prostheses, mainly using PubMed plus Elicit; 455 studies were screened, 23 retained, and 5 added through Elicit, for 28 total studies; search last updated January 2025.
- One author (IS) extracted data on publication year, purpose, AI techniques, parameter tuning, phosphene assumptions, validation setting, human tasks, dynamic scenes, and electrode count, with study-by-study details in Table 2 and supplementary tables.
- The paper also provides a narrative overview of current retinal prostheses (epiretinal, subretinal, suprachoroidal) and cortical prostheses, plus methodological, clinical, and technological challenges.
Limitations
- Stated: most current AI studies are based on simulations; few are validated in real-world settings; only one study included an implanted human participant; oversimplified symmetrical phosphene models may inflate apparent performance and mask safety constraints; reviewed virtual-setting studies did not quantitatively assess safety limits, power draw, robustness stress-tests, uncertainty tracking, or fail-safes; heterogeneous tasks, metrics, datasets, and electrode counts hamper cross-study interpretation and benchmarking.
- Evident from the text: screening and data extraction were performed by a single author (IS), which may limit reliability, and the synthesis is descriptive rather than meta-analytic.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
39 Valid · 16 Not valid · 14 Not checked · 114 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In the case of cortical prostheses, phosphene location depends on numerous factors, including the individual’s specific retinotopic maps and displacement or degradation of the cortical implant over time.58”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Methodological, Clinical, and Technological Challenges Associated with RCPs
What the sources say
- Partly supportedcites [58] Towle, 2020, J Neural Eng sourceExperimental — accuracy not yet measured
Section 3.2 links electrode position relative to cortical sulci with where phosphenes appeared, and the Abstract reports that the array rotated over time. But section 4.4 says this subject’s unusual phosphene pattern could not be explained by unusual cortical anatomy, while section 4.2 documents electrode degradation without showing that it changed phosphene locations. The paper therefore supports implant placement as relevant, but not all the claimed factors as determinants of location. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Of note, stimulation of the visual cortex in congenitally blind individuals can inadvertently produce tactile sensations rather than visual phosphenes, particularly in blind subjects who had undertaken extensive training with sensory substitution systems.39–41”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Cortical Prostheses
What the sources say
- Not checked — no full text of the sourcecites [39] Kupers, 2006, Proc Natl Acad Sci source
- Not checked — no full text of the sourcecites [40] Ptito, 2007, Exp Brain Res source
- Could not verifycites [41] Kupers, 2010, Proc Natl Acad Sci sourceExperimental — accuracy not yet measured
The Abstract and Discussion describe visual-cortex activation during a tactile route-recognition task after sensory-substitution training, not sensations produced by stimulating the cortex. A title listed in the References mentions stimulation-induced qualia, but our copy does not say whether these were tactile rather than visual phosphenes or whether extensive training affected them (searched: phosphenes, stimulation-induced tactile sensations). (LLM, conf=0.74)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In comparison, studies on suprachoroidal devices25,36 have generally assessed patient autonomy, mobility, and object discrimination, rather than visual acuity.”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Methodological, Clinical, and Technological Challenges Associated with RCPs
What the sources say
- Partly supportedcites [25] Petoe, 2021, Transl Vis Sci Amp Technol sourceExperimental — accuracy not yet measured
The Methods sections on Tabletop Search and FLORA assess object identification, daily activities, and mobility, supporting the description of this trial’s emphasis. But the Methods and Results sections on Screen-based Assessments also report a Basic Grating Acuity test, so visual acuity was not wholly set aside. This single trial also does not establish what suprachoroidal-device studies have generally assessed; the indexed passages provide no page numbers. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [36] Fujikado, 2016, Investig Opthalmol Amp Vis Sci source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The Argus II and PRIMA devices were designed to reduce FOV even further, thereby providing improved image resolution through a digital zoom.9,10,65”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Methodological, Clinical, and Technological Challenges Associated with RCPs
What the sources say
- Not checked — no full text of the sourcecites [9] Luo, 2016, Prog Retin Eye Res source
- Partly supportedcites [10] Palanker, 2022, Nat Commun sourceExperimental — accuracy not yet measured
The Results report that PRIMA-2 offers electronic magnification, and the Discussion reports improved acuity with magnification. But the paper does not say Argus II and PRIMA were designed to reduce field of view for that purpose; the Results give PRIMA-2 a slightly wider projected field than PRIMA-1 (18.5° versus 17.5°). Argus II appears only in a reference, not in this design comparison. (LLM, conf=0.88)
- Not matchedcites [65] Sahel, 2013, Invest Ophthalmol Vis Sci
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, empirical data show that phosphenes are not symmetric, either for retinal101 or cortical42 implants.”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Saliency Extraction
What the sources say
- Supportedcites [101] Hou, 2024, J Neural Eng source
The Introduction says phosphenes from a single Argus II retinal electrode are predominantly elongated along underlying nerve fiber bundles. The Results section also reports that more eccentric phosphenes tended to be more elongated in one participant. This supports the retinal-implant portion of the sentence, to which this source is cited; the cortical-implant portion has a separate citation. (LLM, conf=0.90)
- Partly supportedcites [42] Fernández, 2021, J Clin Invest sourceExperimental — accuracy not yet measured
For the cortical-implant portion of the sentence, the Results report that the participant perceived more elongated phosphenes as the distance between two stimulated electrodes increased. This supports the narrower point that cortical stimulation can produce non-round percepts, but it does not establish that cortical phosphenes are generally asymmetric. The retinal-implant portion is attributed to a different citation. (LLM, conf=0.78)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
83 more claims · 13 with their cited sources checked
Create a free account to see all 183 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 54
- Probably not a substantial claim. 55
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Systematic Review on the Use of AI for RCPs
“| [90] | 2022 | Saliency Extraction | TF | None | None |”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > References
“90. White J, Ruiz-Serra J, Petrie S, Kameneva T, McCarthy C. Self-attention based vision processing for prosthetic vision. In: 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE; 2023: 1– 4.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Saliency Extraction
“Among the 14-feature engineering-based studies identified in our literature search, the most common feature type used for saliency map extraction was image contours”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Saliency Extraction
“Only one out of the 15 feature engineering studies has been implemented in human real prosthetic vision settings77 with a suprachoroidal device.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Systematic Review on the Use of AI for RCPs
“| [96] | 2023 | SP Optimization | NN, ML | RSPV data | No |”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > References
“96. Fauvel T, Chalk M. Human-in-the-loop optimization of visual prosthetic stimulation. J Neural Eng. 2022; 19: 036038.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Retinal and Cortical Prostheses
“The 245 electrode IMIE 256 developed by IntelliMicro Medical (China) and Golden Eye Bionics (US)23 is currently the only epiretinal prosthesis undergoing evaluation in humans.”
§ Visual Prostheses in the Era of Artificial Intelligence Technology > Introduction > Cortical Prostheses
“| | PRIMA | Argus II | Alpha-AMS | STS | SRP | IMIE | | --- | --- | --- | --- | --- | --- | --- | | Type | Sub. | Epi. | Sub. | Supra. | Supra. | Epi. | | Clinical Target | GA | RP | RP | RP | RP | RP | | Electrodes | 378 | 60 | 1600 | 49 | 49 | 256 |”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Neural Mechanisms of Selective Visual Attention
Desimone, R., & Duncan, J. (1995) · Annual Review of Neuroscience · doi:10.1146/annurev.ne.18.030195.001205 · Cited by 8,388 · cited 1×
“105 With artificial vision, the dynamics of extrapolation achieved through multiple views of the same scene may convey crucial information to blind patients.”
Bourne, R. R. A., Flaxman, S. R., Braithwaite, T., Cicinelli, M. V., Das, A., Jonas, J. B., Keeffe, J., Kempen, J. H., Leasher, J., Limburg, H., et al. (2017) · The Lancet Global Health · doi:10.1016/s2214-109x(17)30293-0 · Cited by 2,213
Bourne, R., Steinmetz, J. D., Flaxman, S., Briant, P. S., Taylor, H. R., Resnikoff, S., Casson, R. J., Abdoli, A., Abu-Gharbieh, E., Afshin, A., et al. (2021) · The Lancet Global Health · doi:10.1016/s2214-109x(20)30425-3 · Cited by 1,431
The sensations produced by electrical stimulation of the visual cortex
Brindley, G. S., & Lewin, W. S. (1968) · The Journal of Physiology · doi:10.1113/jphysiol.1968.sp008519 · Cited by 1,170 · cited 2×
“In 1968, the first proof-of-concept was provided that focal electrical stimulation of the human visual cortex can evoke discrete phosphenes, 37 paving the way for later cortical visual-prosthesis research.”
Visual perception in a blind subject with a chronic microelectronic retinal prosthesis
Humayun, M. S., Weiland, J. D., Fujii, G. Y., Greenberg, R., Williamson, R., Little, J., Mech, B., Cimmarusti, V., Van Boemel, G., Dagnelie, G., et al. (2003) · Vision Research · doi:10.1016/s0042-6989(03)00457-7 · Cited by 856 · cited 2×
“20 In 2001, the American company “Second Sight” developed the first modern epiretinal device 18 designed for blind individuals blinded from outer retinal degenerative disease.”
The Artificial Silicon Retina Microchip for the Treatment of VisionLoss From Retinitis Pigmentosa
Chow, A. Y. (2004) · Archives of Ophthalmology · doi:10.1001/archopht.122.4.460 · Cited by 511 · cited 1×
“Among the various models, Artificial Silicon Retina (ASR) retinal implant 30 developed by “Optobionics” (USA) was the first to receive FDA approval, in 2000.”
Artificial vision with wirelessly powered subretinal electronic implant alpha-IMS
Stingl, K., Bartz-Schmidt, K. U., Besch, D., Braun, A., Bruckmann, A., Gekeler, F., Greppmaier, U., Hipp, S., Hörtdörfer, G., Kernstock, C., et al. (2013) · Proceedings of the Royal Society B: Biological Sciences · doi:10.1098/rspb.2013.0077 · Cited by 473 · cited 4×
“9,10,22,24 By this metric, comparison of visual acuity with the device switched ON and OFF showed improvement only for the PRIMA 35 and Argus II 9 devices.”
InfluentialDobelle, W. H., Mladejovsky, M. G., & Girvin, J. P. (1974) · Science · doi:10.1126/science.183.4123.440 · Cited by 440 · cited 1×
“In the 1970s, the Dobelle Eye, 38 consisting of 68 platinum electrodes connected to a camera, was implanted in a blind adult patient.”
Research works printed but not linked: 5
- Tassicker, 1956, Br J Physiol Opt, 13, 102
- Barry, 2023, Invest Ophthalmol Vis Sci, 64, 2842
- Huo, 2023, Invest Ophthalmol Vis Sci, 64, 5518
- Diaz, 2023, Invest Ophthalmol Vis Sci, 64, 5519
- Sahel, 2013, Invest Ophthalmol Vis Sci, 54, 1389
Cited by
Kim, S., Shim, H., & Im, M. (2026) · Advanced Intelligent Systems · doi:10.1002/aisy.202501360 · Cited by 2
Aniorte, A., Gea, M., Garrigós, J., Martínez, J. J., & Ferrández, J. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-27314-7_38
Metadata
- Authors
- Sarbout, I., Gungor, A., Ounissi, M., Zaher, S., Ptito, M., Kupers, R., Racoceanu, D., & Milea, D.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Hôpital Rothschild (FR)
- Montreal Neurological Institute and Hospital (CA)
- UCLouvain (BE)
- Venue
- Eye and Brain
- Publisher
- Informa UK Limited
- Published
- 2025-08
- Volume
- Volume 17
- Issue
- 6
- Pages
- 95-113
- ISSN
- 1179-2744 (ISSN-L)
- PMC
- PMC12405713
- OpenAlex
- W4413808600
- Semantic Scholar
- c89d2d9273048c906ce8cb086272f4b2226b720c
- Cited by
- 3
- References
- 101
- Citations by year
- 2026: 3
- FWCI
- 0.36
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Eye and Brain (publishedVersion, cc-by-nc)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by-nc)
- Research at the University of Copenhagen (University of Copenhagen) (publishedVersion, cc-by-nc)
- HAL (submittedVersion, other-oa)
- Dove Medical Press (Taylor and Francis Group) (submittedVersion, cc-by-nc)
- Topics
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuroscience and Neural Engineering
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
- Keywords
- retinal prosthesis, artificial intelligence, artificial neural networks, phosphenes, electrical stimulation, visual acuity, simulated prosthetic vision, blind patients
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Visual Prostheses in the Era of Artificial Intelligence Technology. https://app.cochat.ai/papers/10.2147/eb.s524322
- The paper
- Sarbout, I., Gungor, A., Ounissi, M., Zaher, S., Ptito, M., Kupers, R., Racoceanu, D., & Milea, D. (2025). Visual Prostheses in the Era of Artificial Intelligence Technology. Eye and Brain. https://doi.org/10.2147/eb.s524322
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.