MR fingerprinting Deep RecOnstruction NEtwork (DRONE)

Cohen, Ouri; Zhu, Bin; Rosen, Matthew S.

doi:10.1002/mrm.27198

Cited by 251 publications

(357 citation statements)

References 28 publications

Supporting

Mentioning

322

Contrasting

Order By: Relevance

“…This probabilistic output layer can be adapted to any other neural network used for regression problems with only small changes to the network architecture. Hereby, it constitutes a simple way of enabling uncertainty estimation for similar deep learning approaches like the prediction of 9.4T contrasts from 3T Z‐spectra or reconstruction of MR fingerprinting data, a technique that has also found applications in CEST …”

Section: Discussionmentioning

confidence: 99%

DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T

Glang

Deshmane

Prokudin

et al. 2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose Calculation of sophisticated MR contrasts often requires complex mathematical modeling. Data evaluation is computationally expensive, vulnerable to artifacts, and often sensitive to fit algorithm parameters. In this work, we investigate whether neural networks can provide not only fast model fitting results, but also a quality metric for the predicted values, so called uncertainty quantification, investigated here in the context of multi‐pool Lorentzian fitting of CEST MRI spectra at 3T. Methods A deep feed‐forward neural network including a probabilistic output layer allowing for uncertainty quantification was set up to take uncorrected CEST‐spectra as input and predict 3T Lorentzian parameters of a 4‐pool model (water, semisolid MT, amide CEST, NOE CEST), including the B0 inhomogeneity. Networks were trained on data from 3 subjects with and without data augmentation, and applied to untrained data from 1 additional subject and 1 brain tumor patient. Comparison to conventional Lorentzian fitting was performed on different perturbations of input data. Results The deepCEST 3T networks provided fast and accurate predictions of all Lorentzian parameters and were robust to input perturbations because of noise or B0 artifacts. The uncertainty quantification detected fluctuations in input data by increase of the uncertainty intervals. The method generalized to unseen brain tumor patient CEST data. Conclusions The deepCEST 3T neural network provides fast and robust estimation of CEST parameters, enabling online reconstruction of sophisticated CEST contrast images without the typical computational cost. Moreover, the uncertainty quantification indicates if the predictions are trustworthy, enabling confident interpretation of contrast changes.

show abstract

Section: Discussionmentioning

confidence: 99%

DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T

Glang

Deshmane

Prokudin

et al. 2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

show abstract

“…For (C3), an optimal linear classifier Λ = c C + 1 T 1 + 2 T 2 was formed, with coefficients calculated using Equation 5. Its AUC was calculated using Equation 6.…”

Section: Kirov and Talmentioning

confidence: 99%

“…Several approaches to this end have been suggested, ranging from explicit model based estimations, [1][2][3] to simulated echo modulation curves, 4,5 to MR fingerprinting. [6][7][8] These schemes are almost universally multiparametric: they simultaneously uncover all, or most, parameters. Because T 1 and T 2 are known to change in disease, these additional data can be used to enhance clinical assessment and diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Potential clinical impact of multiparametric quantitative MR spectroscopy in neurological disorders: A review and analysis

Kirov

Tal

2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose Unlike conventional MR spectroscopy (MRS), which only measures metabolite concentrations, multiparametric MRS also quantifies their longitudinal (T1) and transverse (T2) relaxation times, as well as the radiofrequency transmitter inhomogeneity (B1+). To test whether knowledge of these additional parameters can improve the clinical utility of brain MRS, we compare the conventional and multiparametric approaches in terms of expected classification accuracy in differentiating controls from patients with neurological disorders. Theory and Methods A literature review was conducted to compile metabolic concentrations and relaxation times in a wide range of neuropathologies and regions of interest. Simulations were performed to construct receiver operating characteristic curves and compute the associated areas (area under the curve) to examine the sensitivity and specificity of MRS for detecting each pathology in each region. Classification accuracy was assessed using metabolite concentrations corrected using population‐averages for T1, T2, and B1+ (conventional MRS); using metabolite concentrations corrected using per‐subject values (multiparametric MRS); and using an optimal linear multiparametric estimator comprised of the metabolites' concentrations and relaxation constants (multiparametric MRS). Additional simulations were conducted to find the minimal intra‐subject precision needed for each parameter. Results Compared with conventional MRS, multiparametric approaches yielded area under the curve improvements for almost all neuropathologies and regions of interest. The median area under the curve increased by 0.14 over the entire dataset, and by 0.24 over the 10 instances with the largest individual increases. Conclusions Multiparametric MRS can substantially improve the clinical utility of MRS in diagnosing and assessing brain pathology, motivating the design and use of novel multiparametric sequences.

show abstract

“…In the work entitled MRF‐DRONE by Cohen et al, deep learning was applied to MRF signal evolutions, after image reconstruction, to learn the T 1 and T 2 values without direct dictionary matching. The TensorFlow framework was used to construct a fully connected neural network with four layers and two hidden layers, and the method was tested on both MRF‐EPI and MRF‐FISP sequences.…”

Section: Applications Of Machine and Deep Learning To Mrfmentioning

confidence: 99%

Magnetic resonance fingerprinting review part 2: Technique and directions

McGivney

Boyacıoğlu

Jiang

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Magnetic resonance fingerprinting (MRF) is a general framework to quantify multiple MR‐sensitive tissue properties with a single acquisition. There have been numerous advances in MRF in the years since its inception. In this work we highlight some of the recent technical developments in MRF, focusing on sequence optimization, modifications for reconstruction and pattern matching, new methods for partial volume analysis, and applications of machine and deep learning. Level of Evidence: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:993–1007.

show abstract

MR fingerprinting Deep RecOnstruction NEtwork (DRONE)

Abstract: Reconstruction of MRF data with a NN is accurate, 300- to 5000-fold faster, and more robust to noise and dictionary undersampling than conventional MRF dictionary-matching.

Cited by 251 publications

References 28 publications

DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T

DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T

Potential clinical impact of multiparametric quantitative MR spectroscopy in neurological disorders: A review and analysis

Magnetic resonance fingerprinting review part 2: Technique and directions

Contact Info

Product

Resources

About