PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification.
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-...
| Published in: | Journal of Imaging Informatics in Medicine Vol. 38; no. 4; pp. 2071 - 2085 |
|---|---|
| Main Authors: | , , , , |
| Format: | diagnostic images equations & formulas pictorial research tables/charts Journal Article |
| Published: |
Springer Nature
Aug2025
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=187278945&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 187278945 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 29482925 NR3A jtl: Journal of Imaging Informatics in Medicine issn: 29482925 maglogo: N pubinfo: dt: Aug2025 vid: 38 iid: 4 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 187278945 187278945 189894361 187278945 10.1007/s10278-024-01250-3 187278945 ppf: 2071 ppct: 14 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification. aug: au: Ekanayake, Mevan Pawar, Kamlesh Chen, Zhifeng Egan, Gary Chen, Zhaolin affil: https://ror.org/02bfwt286 Monash Biomedical Imaging, Monash University, 3800, Clayton, VIC, Australia sug: subj: Image Processing, Computer Assisted Methods Magnetic Resonance Imaging Methods Deep Learning Utilization Uncertainty Evaluation Conceptual Framework Human Funding Source Systems Analysis Algorithms Correlational Studies Convolutional Neural Networks Brain Sensitivity and Specificity Probability Descriptive Statistics Quantitative Studies Linear Regression Goodness of Fit Chi Square Test Neoplasms Pathology Cost Benefit Analysis ab: 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. pubtype: Academic Journal doctype: diagnostic images equations & formulas pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|