EUVIMEDEUVIMED entdecken
Open Access

PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification

Mevan Ekanayake, Kamlesh Pawar, Zhifeng Chen, Gary Egan, Zhaolin Chen

Journal of Imaging Informatics in Medicine · 2024

DOI: 10.1007/s10278-024-01250-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2024. Verfasst von Mevan Ekanayake und 4 weiteren Autor:innen. Beteiligte Einrichtung: Monash Biomedical Imaging, Monash University, Clayton, VIC, 3800, Australia. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) models are effective in leveraging latent representations from MR data, emerging as state-of-the-art solutions for accelerated MRI reconstruction. However, challenges arise due to the inherent uncertainties associated with undersampling in k-space, coupled with the over- or under-parameterized and opaque nature of DL models. Addressing uncertainty has thus become a critical issue in DL MRI reconstruction. Monte Carlo (MC) inference techniques are commonly employed to estimate uncertainty, involving multiple reconstructions of the same scan to compute variance as a measure of uncertainty. Nevertheless, these methods entail significant computational expenses, requiring multiple inferences through the DL model. In this context, we propose a novel approach to uncertainty estimation during MRI reconstruction using a pixel classification framework. Our method, PixCUE (Pixel Classification Uncertainty Estimation), generates both the reconstructed image and an uncertainty map in a single forward pass through the DL model. We validate the efficacy of this approach by demonstrating that PixCUE-generated uncertainty maps exhibit a strong correlation with reconstruction errors across various MR imaging sequences and under diverse adversarial conditions. We present an empirical relationship between uncertainty estimations using PixCUE and established reconstruction metrics such as NMSE, PSNR, and SSIM. Furthermore, we establish a correlation between the estimated uncertainties from PixCUE and the conventional MC method. Our findings affirm that PixCUE reliably estimates uncertainty in MRI reconstruction with minimal additional computational cost.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingImage Processing, Computer-AssistedDeep LearningHumansUncertaintyMonte Carlo MethodBrainAlgorithms

Stichwörter der Autor:innen

Convolutional Neural NetworkDeep Learning Uncertainty EstimationMR Image ReconstructionPixel Classification Framework

Autor:innen und Institutionen

  • Monash Biomedical Imaging, Monash University, Clayton, VIC, 3800, Australia.
  • Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, 3800, Australia.
  • Department of Data Science and AI, Faculty of IT, Monash University, Clayton, VIC, 3800, Australia.
  • School of Psychological Sciences, Monash University, Clayton, VIC, 3800, Australia.
  • Monash Biomedical Imaging, Monash University, Clayton, VIC, 3800, Australia. zhaolin.chen@monash.edu.
  • Department of Data Science and AI, Faculty of IT, Monash University, Clayton, VIC, 3800, Australia. zhaolin.chen@monash.edu.

Zitieren

APA

Ekanayake, M., Pawar, K., Chen, Z., Egan, G., & Chen, Z. (2024). PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01250-3

Vancouver

Ekanayake M, Pawar K, Chen Z, Egan G, Chen Z. PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification. Journal of Imaging Informatics in Medicine. 2024. doi:10.1007/s10278-024-01250-3

BibTeX
@article{Ekanayake2024,
  author = {Ekanayake, Mevan and Pawar, Kamlesh and Chen, Zhifeng and Egan, Gary and Chen, Zhaolin},
  title = {PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2024},
  doi = {10.1007/s10278-024-01250-3}
}
Kostenlos starten →