The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
On instabilities of deep learning in image reconstruction and the potential costs of AI
Open accessAbstract
Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper, we demonstrate a crucial phenomenon: Deep learning typically yields unstable methods for image reconstruction. The instabilities usually occur in several forms: 1) Certain tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction; 2) a small structural change, for example, a tumor, may not be captured in the reconstructed image; and 3) (a counterintuitive type of instability) more samples may yield poorer performance. Our stability test with algorithms and easy-to-use software detects the instability phenomena. The test is aimed at researchers, to test their networks for instabilities, and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Sparse MRI: The application of compressed sensing for rapid MR imaging
Lustig, M., Donoho, D., & Pauly, J. M. (2007) · Magnetic Resonance in Medicine · doi:10.1002/mrm.21391 · Cited by 6,952
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317
Scope of validity of PSNR in image/video quality assessment
Huynh-Thu, Q., & Ghanbari, M. (2008) · Electronics Letters · doi:10.1049/el:20080522 · Cited by 2,959
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Cited by
Deep learning for tomographic image reconstruction
Wang, G., Ye, J. C., & De Man, B. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00273-z · Cited by 531
Results of the 2020 fastMRI challenge for machine learning MR image reconstruction
Muckley, M. J., Riemenschneider, B., Radmanesh, A., Kim, S., Jeong, G., Ko, J., Jun, Y., Shin, H., Hwang, D., Mostapha, M., et al. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3075856 · Cited by 313
Larson, D. B., Harvey, H., Rubin, D. L., Irani, N., Tse, J. R., & Langlotz, C. P. (2021) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2020.09.060 · Cited by 198
Resnik, D. B., & Hosseini, M. (2025) · AI and Ethics · doi:10.1007/s43681-024-00493-8 · Cited by 228
“AI systems also make errors in reading, classifying, and reconstructing radiological images, but the error rate is decreasing, and AI systems will soon outperform humans in terms of speed and accuracy of image reading [12, 17, 103, 228].”
Implicit data crimes: Machine learning bias arising from misuse of public data
Shimron, E., Tamir, J. I., Wang, K., & Lustig, M. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2117203119 · Cited by 112
Metadata
- Authors
- Antun, V., Renna, F., Poon, C., Adcock, B., & Hansen, A. C.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2020-05-11
- Volume
- 117
- Issue
- 48
- Pages
- 30088-30095
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W2911290743
- Cited by
- 779
- References
- 12
- FWCI
- 47.51
- Type
- journal article
- Language
- en
- Open access
- bronze
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: On instabilities of deep learning in image reconstruction and the potential costs of AI. https://app.cochat.ai/papers/10.1073/pnas.1907377117
- The paper
- Antun, V., Renna, F., Poon, C., Adcock, B., & Hansen, A. C. (2020). On instabilities of deep learning in image reconstruction and the potential costs of AI. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.1907377117
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.
