On instabilities of deep learning in image reconstruction and the potential costs of AI

Vegard Antun, Francesco Renna, Clarice Poon, Ben Adcock, Anders C. Hansen

Research output: Contribution to journalArticle


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.
Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalProceedings of the National Academy of Sciences
Early online date11 May 2020
Publication statusE-pub ahead of print - 11 May 2020

Cite this