paper-with-me

홈 › Papers

On instabilities of deep learning in image reconstruction - Does AI come at a cost?

2019-02-14 · Vegard Antun, Francesco Renna, Clarice Poon, Ben Adcock, Anders C. Hansen

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 unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) 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 tumour, may not be captured in the reconstructed image and (3) (a counterintuitive type of instability) more samples may yield poorer performance. Our new 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.

📄 PDF Abstract BibTeX arXiv:1902.05300

Code (1)

vegarant/Invfool 공식 구현 tf

Tasks

Deep Learningimage-classificationImage ClassificationImage Reconstruction

Similar Papers 제목 키워드 기반

Stabilizing Deep Tomographic Reconstruction

2020-08-04 · Weiwen Wu, Dianlin Hu, Wenxiang Cong, Hongming Shan 외

Tomographic image reconstruction with deep learning is an emerging field, but a recent landmark study reveals that several deep reconstruction networks are unstable for computed tomography (CT) and magnetic resonance ima…

Adversarial Attackcompressed sensingComputed Tomography (CT)Image Reconstruction

Interval Neural Networks as Instability Detectors for Image Reconstructions

2020-03-27 · Jan Macdonald, Maximilian März, Luis Oala, Wojciech Samek

This work investigates the detection of instabilities that may occur when utilizing deep learning models for image reconstruction tasks. Although neural networks often empirically outperform traditional reconstruction me…

Deep LearningImage ReconstructionUncertainty Quantification

Regularizing Instabilities in Image Reconstruction Arising from Learned Denoisers

2021-08-21 · Abinash Nayak

It's well-known that inverse problems are ill-posed and to solve them meaningfully one has to employ regularization methods. Traditionally, popular regularization methods have been the penalized Variational approaches. I…

Image ReconstructionRolling Shutter Correction

On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations

2021-02-25 · Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller 외

Although deep learning (DL) has received much attention in accelerated MRI, recent studies suggest small perturbations may lead to instabilities in DL-based reconstructions, leading to concern for their clinical applicat…

MRI Reconstruction

On the Robustness of deep learning-based MRI Reconstruction to image transformations

2022-11-09 · Jinghan Jia, Mingyi Hong, Yimeng Zhang, Mehmet Akçakaya 외

Although deep learning (DL) has received much attention in accelerated magnetic resonance imaging (MRI), recent studies show that tiny input perturbations may lead to instabilities of DL-based MRI reconstruction models. …

image-classificationImage ClassificationImage ReconstructionMRI Reconstruction