1
|
Guo R, Fan Y, Liu B, Qian X, Dai J, Si D, Wang Y, Wang A, Dong G, Jin Y, Xiao J, Ding H, Tang X. MyoFold: Joint myocardial tissue composition and wall motion quantification via a highly folded sequence. Magn Reson Med 2024; 92:1064-1078. [PMID: 38726772 DOI: 10.1002/mrm.30124] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 03/09/2024] [Accepted: 04/03/2024] [Indexed: 06/27/2024]
Abstract
PURPOSE This study aims to develop and evaluate a novel cardiovascular MR sequence, MyoFold, designed for the simultaneous quantifications of myocardial tissue composition and wall motion. METHODS MyoFold is designed as a 2D single breathing-holding sequence, integrating joint T1/T2 mapping and cine imaging. The sequence uses a 2-fold accelerated balanced SSFP (bSSFP) for data readout and incorporates electrocardiogram synchronization to align with the cardiac cycle. MyoFold initially acquires six single-shot inversion-recovery images, completed during the diastole of six successive heartbeats. T2 preparation (T2-prep) is applied to introduce T2 weightings for the last three images. Subsequently, over the following six heartbeats, segmented bSSFP is performed for the movie of the entire cardiac cycle, synchronized with an electrocardiogram. A neural network trained using numerical simulations of MyoFold is used for T1 and T2 calculations. MyoFold was validated through phantom and in vivo experiments, with comparisons made against MOLLI, SASHA, T2-prep bSSFP, and the conventional cine. RESULTS In phantom studies, MyoFold exhibited a 10% overestimation in T1 measurements, whereas T2 measurements demonstrated high accuracy. In vivo experiments revealed that MyoFold T1 had comparable accuracy to SASHA and precision similar to MOLLI. MyoFold demonstrated good agreement with T2-prep bSSFP in myocardial T2 measurements. No significant differences were observed in the quantification of left-ventricle wall thickness and function between MyoFold and the conventional cine. CONCLUSION MyoFold presents as a rapid, simple, and multitasking approach for quantitative cardiovascular MR examinations, offering simultaneous assessment of tissue composition and wall motion. The sequence's multitasking capabilities make it a promising tool for comprehensive cardiac evaluations in clinical settings.
Collapse
Affiliation(s)
- Rui Guo
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Yingwei Fan
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Bowei Liu
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Xiaofeng Qian
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Jiahuan Dai
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Dongyue Si
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Yuanyuan Wang
- School of Optics and Photonics, Beijing Institute of Technology, Beijing, China
| | - Ancong Wang
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Guozhao Dong
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Yongsheng Jin
- Department of Infectious Diseases, The Affiliated Hospital of Yan'an University, Shaanxi, China
| | - Jingjing Xiao
- Bio-Med Informatics Research Center and Clinical Research Center, Xinqiao Hospital, Army Medical University, Chongqing, China
| | - Haiyan Ding
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Xiaoying Tang
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| |
Collapse
|
2
|
Aromiwura AA, Cavalcante JL, Kwong RY, Ghazipour A, Amini A, Bax J, Raman S, Pontone G, Kalra DK. The role of artificial intelligence in cardiovascular magnetic resonance imaging. Prog Cardiovasc Dis 2024:S0033-0620(24)00092-6. [PMID: 38925255 DOI: 10.1016/j.pcad.2024.06.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/23/2024] [Accepted: 06/23/2024] [Indexed: 06/28/2024]
Abstract
Cardiovascular magnetic resonance (CMR) imaging is the gold standard test for myocardial tissue characterization and chamber volumetric and functional evaluation. However, manual CMR analysis can be time-consuming and is subject to intra- and inter-observer variability. Artificial intelligence (AI) is a field that permits automated task performance through the identification of high-level and complex data relationships. In this review, we review the rapidly growing role of AI in CMR, including image acquisition, sequence prescription, artifact detection, reconstruction, segmentation, and data reporting and analysis including quantification of volumes, function, myocardial infarction (MI) and scar detection, and prediction of outcomes. We conclude with a discussion of the emerging challenges to widespread adoption and solutions that will allow for successful, broader uptake of this powerful technology.
Collapse
Affiliation(s)
| | | | - Raymond Y Kwong
- Division of Cardiovascular Medicine, Brigham and Women's Hospital, Boston, MA, USA
| | - Aryan Ghazipour
- Medical Imaging Laboratory, Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY, USA
| | - Amir Amini
- Medical Imaging Laboratory, Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY, USA
| | - Jeroen Bax
- Department of Cardiology, Leiden University, Leiden, the Netherlands
| | - Subha Raman
- Division of Cardiology, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Gianluca Pontone
- Department of Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, University of Milan, Milan, Italy
| | - Dinesh K Kalra
- Division of Cardiology, Department of Medicine, University of Louisville, Louisville, KY, USA; Center for Artificial Intelligence in Radiological Sciences (CAIRS), Department of Radiology, University of Louisville, Louisville, KY, USA.
| |
Collapse
|
3
|
Tao Y, Lv Z, Liu W, Qi H, Hu P. Recurrent neural network-based simultaneous cardiac T1, T2, and T1ρ mapping. NMR IN BIOMEDICINE 2024:e5133. [PMID: 38520183 DOI: 10.1002/nbm.5133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Revised: 02/05/2024] [Accepted: 02/06/2024] [Indexed: 03/25/2024]
Abstract
The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free-breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN-based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN-based method was compared with a dictionary-matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN-based method and the dictionary-matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN-based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60-fold acceleration compared with the dictionary-matching method. The RNN-accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary-matching method for the free-breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications.
Collapse
Affiliation(s)
- Yiming Tao
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| | - Zhenfeng Lv
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| | - Wenjian Liu
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| | - Haikun Qi
- School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, China
- Shanghai Clinical Research and Trial Center, ShanghaiTech University, Shanghai, China
| | - Peng Hu
- School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, China
- Shanghai Clinical Research and Trial Center, ShanghaiTech University, Shanghai, China
| |
Collapse
|
4
|
Qi Y, Wang F, Kong J, Cao JJ, Li YY. SwinUNet: a multiscale feature learning approach to cardiovascular magnetic resonance parametric mapping for myocardial tissue characterization. Physiol Meas 2024; 45:035007. [PMID: 38387052 DOI: 10.1088/1361-6579/ad2c15] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2023] [Accepted: 02/22/2024] [Indexed: 02/24/2024]
Abstract
Objective.Cardiovascular magnetic resonance (CMR) can measure T1 and T2 relaxation times for myocardial tissue characterization. However, the CMR procedure for T1/T2 parametric mapping is time-consuming, making it challenging to scan heart patients routinely in clinical practice. This study aims to accelerate CMR parametric mapping with deep learning.Approach. A deep-learning model, SwinUNet, was developed to accelerate T1/T2 mapping. SwinUNet used a convolutional UNet and a Swin transformer to form a hierarchical 3D computation structure, allowing for analyzing CMR images spatially and temporally with multiscale feature learning. A comparative study was conducted between SwinUNet and an existing deep-learning model, MyoMapNet, which only used temporal analysis for parametric mapping. The T1/T2 mapping performance was evaluated globally using mean absolute error (MAE) and structural similarity index measure (SSIM). The clinical T1/T2 indices for characterizing the left-ventricle myocardial walls were also calculated and evaluated using correlation and Bland-Altman analysis.Main results. We performed accelerated T1 mapping with ≤4 heartbeats and T2 mapping with 2 heartbeats in reference to the clinical standard, which required 11 heartbeats for T1 mapping and 3 heartbeats for T2 mapping. SwinUNet performed well in all the experiments (MAE < 50 ms, SSIM > 0.8, correlation > 0.75, and Bland-Altman agreement limits < 100 ms for T1 mapping; MAE < 1 ms, SSIM > 0.9, correlation > 0.95, and Bland-Altman agreement limits < 1.5 ms for T2 mapping). When the maximal acceleration was used (2 heartbeats), SwinUNet outperformed MyoMapNet and gave measurement accuracy similar to the clinical standard.Significance. SwinUNet offers an optimal solution to CMR parametric mapping for assessing myocardial diseases quantitatively in clinical cardiology.
Collapse
Affiliation(s)
- Yifan Qi
- Department of Computer Science, Stony Brook University, Stony Brook, NY 11790, United States of America
| | - Fusheng Wang
- Department of Computer Science, Stony Brook University, Stony Brook, NY 11790, United States of America
| | - Jun Kong
- Department of Mathematics and Statistics, Georgia State University, Atlanta, GA 30303, United States of America
| | - J Jane Cao
- DeMatteis Centre for Research and Education, St. Francis Hospital, Roslyn, NY 11576, United States of America
- Clinical medicine, Stony Brook University, Stony Brook, NY 11790, United States of America
| | - Yu Y Li
- DeMatteis Centre for Research and Education, St. Francis Hospital, Roslyn, NY 11576, United States of America
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY 11790, United States of America
| |
Collapse
|
5
|
Christodoulou AG, Cruz G, Arami A, Weingärtner S, Artico J, Peters D, Seiberlich N. The future of cardiovascular magnetic resonance: All-in-one vs. real-time (Part 1). J Cardiovasc Magn Reson 2024; 26:100997. [PMID: 38237900 PMCID: PMC11211239 DOI: 10.1016/j.jocmr.2024.100997] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2023] [Accepted: 01/10/2024] [Indexed: 02/26/2024] Open
Abstract
Cardiovascular magnetic resonance (CMR) protocols can be lengthy and complex, which has driven the research community to develop new technologies to make these protocols more efficient and patient-friendly. Two different approaches to improving CMR have been proposed, specifically "all-in-one" CMR, where several contrasts and/or motion states are acquired simultaneously, and "real-time" CMR, in which the examination is accelerated to avoid the need for breathholding and/or cardiac gating. The goal of this two-part manuscript is to describe these two different types of emerging rapid CMR. To this end, the vision of each is described, along with techniques which have been devised and tested along the pathway of clinical implementation. The pros and cons of the different methods are presented, and the remaining open needs of each are detailed. Part 1 will tackle the "all-in-one" approaches, and Part 2 the "real-time" approaches along with an overall summary of these emerging methods.
Collapse
Affiliation(s)
- Anthony G Christodoulou
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, USA; Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Gastao Cruz
- Michigan Institute for Imaging Technology and Translation, Department of Radiology, University of Michigan, Ann Arbor, MI, USA
| | - Ayda Arami
- Department of Imaging Physics, Delft University of Technology, Delft, the Netherlands; Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands
| | - Sebastian Weingärtner
- Department of Imaging Physics, Delft University of Technology, Delft, the Netherlands
| | | | - Dana Peters
- Radiology & Biomedical Imaging, Yale University, New Haven, CT, USA
| | - Nicole Seiberlich
- Michigan Institute for Imaging Technology and Translation, Department of Radiology, University of Michigan, Ann Arbor, MI, USA.
| |
Collapse
|
6
|
Amyar A, Fahmy AS, Guo R, Nakata K, Sai E, Rodriguez J, Cirillo J, Pareek K, Kim J, Judd RM, Ruberg FL, Weinsaft JW, Nezafat R. Scanner-Independent MyoMapNet for Accelerated Cardiac MRI T 1 Mapping Across Vendors and Field Strengths. J Magn Reson Imaging 2024; 59:179-189. [PMID: 37052580 PMCID: PMC11218141 DOI: 10.1002/jmri.28739] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Revised: 03/30/2023] [Accepted: 03/31/2023] [Indexed: 04/14/2023] Open
Abstract
BACKGROUND In cardiac T1 mapping, a series of T1 -weighted (T1 w) images are collected and numerically fitted to a two or three-parameter model of the signal recovery to estimate voxel-wise T1 values. To reduce the scan time, one can collect fewer T1 w images, albeit at the cost of precision or/and accuracy. Recently, the feasibility of using a neural network instead of conventional two- or three-parameter fit modeling has been demonstrated. However, prior studies used data from a single vendor and field strength; therefore, the generalizability of the models has not been established. PURPOSE To develop and evaluate an accelerated cardiac T1 mapping approach based on MyoMapNet, a convolution neural network T1 estimator that can be used across different vendors and field strengths by incorporating the relevant scanner information as additional inputs to the model. STUDY TYPE Retrospective, multicenter. POPULATION A total of 1423 patients with known or suspected cardiac disease (808 male, 57 ± 16 years), from three centers, two vendors (Siemens, Philips), and two field strengths (1.5 T, 3 T). The data were randomly split into 60% training, 20% validation, and 20% testing. FIELD STRENGTH/SEQUENCE A 1.5 T and 3 T, Modified Look-Locker inversion recovery (MOLLI) for native and postcontrast T1 . ASSESSMENT Scanner-independent MyoMapNet (SI-MyoMapNet) was developed by altering the deep learning (DL) architecture of MyoMapNet to incorporate scanner vendor and field strength as inputs. Epicardial and endocardial contours and blood pool (by manually drawing a large region of interest in the blood pool) of the left ventricle were manually delineated by three readers, with 2, 8, and 9 years of experience, and SI-MyoMapNet myocardial and blood pool T1 values (calculated from four T1 w images) were compared with conventional MOLLI T1 values (calculated from 8 to 11 T1 w images). STATISTICAL TESTS Equivalency test with 95% confidence interval (CI), linear regression slope, Pearson correlation coefficient (r), Bland-Altman analysis. RESULTS The proposed SI-MyoMapNet successfully created T1 maps. Native and postcontrast T1 values measured from SI-MyoMapNet were strongly correlated with MOLLI, despite using only four T1 w images, at both field-strengths and vendors (all r > 0.86). For native T1 , SI-MyoMapNet and MOLLI were in good agreement for myocardial and blood T1 values in institution 1 (myocardium: 5 msec, 95% CI [3, 8]; blood: -10 msec, 95%CI [-16, -4]), in institution 2 (myocardium: 6 msec, 95% CI [0, 11]; blood: 0 msec, [-18, 17]), and in institution 3 (myocardium: 7 msec, 95% CI [-8, 22]; blood: 8 msec, [-14, 30]). Similar results were observed for postcontrast T1 . DATA CONCLUSION Inclusion of field strength and vendor as additional inputs to the DL architecture allows generalizability of MyoMapNet across different vendors or field strength. EVIDENCE LEVEL 2. TECHNICAL EFFICACY Stage 2.
Collapse
Affiliation(s)
- Amine Amyar
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Ahmed S. Fahmy
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Rui Guo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Kei Nakata
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Eiryu Sai
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Jennifer Rodriguez
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Julia Cirillo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Karishma Pareek
- Department of Medicine, Boston Medical Center, Boston, MA, USA
| | - Jiwon Kim
- Division of Cardiology, Weill Cornell Medicine, New York, NY, USA
| | - Robert M. Judd
- Department of Medicine (Cardiology Division), Duke University, Durham, NC, USA
| | - Frederick L. Ruberg
- Department of Medicine (Section of Cardiovascular Medicine and Amyloidosis Center), Boston Medical Center and Boston University School of Medicine, Boston, MA, USA
| | | | - Reza Nezafat
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
7
|
Guo R, Si D, Fan Y, Qian X, Zhang H, Ding H, Tang X. DeepFittingNet: A deep neural network-based approach for simplifying cardiac T 1 and T 2 estimation with improved robustness. Magn Reson Med 2023; 90:1979-1989. [PMID: 37415445 DOI: 10.1002/mrm.29782] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2022] [Revised: 05/12/2023] [Accepted: 06/13/2023] [Indexed: 07/08/2023]
Abstract
PURPOSE To develop and evaluate a deep neural network (DeepFittingNet) for T1 /T2 estimation of the most commonly used cardiovascular MR mapping sequences to simplify data processing and improve robustness. THEORY AND METHODS DeepFittingNet is a 1D neural network composed of a recurrent neural network (RNN) and a fully connected (FCNN) neural network, in which RNN adapts to the different number of input signals from various sequences and FCNN subsequently predicts A, B, and Tx of a three-parameter model. DeepFittingNet was trained using Bloch-equation simulations of MOLLI and saturation-recovery single-shot acquisition (SASHA) T1 mapping sequences, and T2 -prepared balanced SSFP (T2 -prep bSSFP) T2 mapping sequence, with reference values from the curve-fitting method. Several imaging confounders were simulated to improve robustness. The trained DeepFittingNet was tested using phantom and in-vivo signals, and compared to the curve-fitting algorithm. RESULTS In testing, DeepFittingNet performed T1 /T2 estimation of four sequences with improved robustness in inversion-recovery T1 estimation. The mean bias in phantom T1 and T2 between the curve-fitting and DeepFittingNet was smaller than 30 and 1 ms, respectively. Excellent agreements between both methods was found in the left ventricle and septum T1 /T2 with a mean bias <6 ms. There was no significant difference in the SD of both the left ventricle and septum T1 /T2 between the two methods. CONCLUSION DeepFittingNet trained with simulations of MOLLI, SASHA, and T2 -prep bSSFP performed T1 /T2 estimation tasks for all these most used sequences. Compared with the curve-fitting algorithm, DeepFittingNet improved the robustness for inversion-recovery T1 estimation and had comparable performance in terms of accuracy and precision.
Collapse
Affiliation(s)
- Rui Guo
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Dongyue Si
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Yingwei Fan
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Xiaofeng Qian
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Haina Zhang
- Center for Community Health Service, Peking University Health Science Center, Beijing, China
| | - Haiyan Ding
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Xiaoying Tang
- School of Life Science, Beijing Institute of Technology, Beijing, China
| |
Collapse
|
8
|
Shih SF, Kafali SG, Calkins KL, Wu HH. Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R 2 * quantification using self-gated stack-of-radial MRI. Magn Reson Med 2023; 89:1567-1585. [PMID: 36426730 PMCID: PMC9892263 DOI: 10.1002/mrm.29525] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 10/02/2022] [Accepted: 10/25/2022] [Indexed: 11/26/2022]
Abstract
PURPOSE To develop a deep learning-based method for rapid liver proton-density fat fraction (PDFF) and R2 * quantification with built-in uncertainty estimation using self-gated free-breathing stack-of-radial MRI. METHODS This work developed an uncertainty-aware physics-driven deep learning network (UP-Net) to (1) suppress radial streaking artifacts because of undersampling after self-gating, (2) calculate accurate quantitative maps, and (3) provide pixel-wise uncertainty maps. UP-Net incorporated a phase augmentation strategy, generative adversarial network architecture, and an MRI physics loss term based on a fat-water and R2 * signal model. UP-Net was trained and tested using free-breathing multi-echo stack-of-radial MRI data from 105 subjects. UP-Net uncertainty scores were calibrated in a validation dataset and used to predict quantification errors for liver PDFF and R2 * in a testing dataset. RESULTS Compared with images reconstructed using compressed sensing (CS), UP-Net achieved structural similarity index >0.87 and normalized root mean squared error <0.18. Compared with reference quantitative maps generated using CS and graph-cut (GC) algorithms, UP-Net achieved low mean differences (MD) for liver PDFF (-0.36%) and R2 * (-0.37 s-1 ). Compared with breath-holding Cartesian MRI results, UP-Net achieved low MD for liver PDFF (0.53%) and R2 * (6.75 s-1 ). UP-Net uncertainty scores predicted absolute liver PDFF and R2 * errors with low MD of 0.27% and 0.12 s-1 compared to CS + GC results. The computational time for UP-Net was 79 ms/slice, whereas CS + GC required 3.2 min/slice. CONCLUSION UP-Net rapidly calculates accurate liver PDFF and R2 * maps from self-gated free-breathing stack-of-radial MRI. The pixel-wise uncertainty maps from UP-Net predict quantification errors in the liver.
Collapse
Affiliation(s)
- Shu-Fu Shih
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
- Department of Bioengineering, University of California Los Angeles, Los Angeles, CA, USA
| | - Sevgi Gokce Kafali
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
- Department of Bioengineering, University of California Los Angeles, Los Angeles, CA, USA
| | - Kara L. Calkins
- Department of Pediatrics, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Holden H. Wu
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
- Department of Bioengineering, University of California Los Angeles, Los Angeles, CA, USA
| |
Collapse
|
9
|
Park J, Jang M, Heier L, Limperopoulos C, Zun Z. Rapid anatomical imaging of the neonatal brain using T 2 -prepared 3D balanced steady-state free precession. Magn Reson Med 2023; 89:1456-1468. [PMID: 36420869 PMCID: PMC10208121 DOI: 10.1002/mrm.29537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Revised: 10/18/2022] [Accepted: 11/03/2022] [Indexed: 11/25/2022]
Abstract
PURPOSE To develop a new approach to 3D gradient echo-based anatomical imaging of the neonatal brain with a substantially shorter scan time than standard 3D fast spin echo (FSE) methods, while maintaining a high SNR. METHODS T2 -prepration was employed immediately prior to image acquisition of 3D balanced steady-state free precession (bSSFP) with a single trajectory of center-out k-space view ordering, which requires no magnetization recovery time between imaging segments during the scan. This approach was compared with 3D FSE, 2D single-shot FSE, and product 3D bSSFP imaging in numerical simulations, plus phantom and in vivo experiments. RESULTS T2 -prepared 3D bSSFP generated image contrast of gray matter, white matter, and CSF very similar to that of reference T2 -weighted imaging methods, without major image artifacts. Scan time of T2 -prepared 3D bSSFP was remarkably shorter compared to 3D FSE, whereas SNR was comparable to that of 3D FSE and higher than that of 2D single-shot FSE. Specific absorption rate of T2 -prepared 3D bSSFP remained within the safety limit. Determining an optimal imaging flip angle of T2 -prepared 3D bSSFP was critical to minimizing blurring of images. CONCLUSION T2 -prepared 3D bSSFP offers an alternative method for anatomical imaging of the neonatal brain with dramatically reduced scan time compared to standard 3D FSE and higher SNR than 2D single-shot FSE.
Collapse
Affiliation(s)
- Jinho Park
- Department of Cardiology, Yonsei University, Seoul, Korea
| | - MinJung Jang
- Department of Radiology, Weill Cornell Medicine, New York, NY, USA
- Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan, Korea
| | - Linda Heier
- Department of Radiology, Weill Cornell Medicine, New York, NY, USA
| | - Catherine Limperopoulos
- Developing Brain Institute, Division of Diagnostic Imaging and Radiology, Children’s National Hospital, Washington, DC, USA
- Division of Fetal and Transitional Medicine, Children’s National Hospital, Washington, DC, USA
- Department of Pediatrics, School of Medicine and Health Sciences, George Washington University, Washington, DC, USA
- Department of Radiology, School of Medicine and Health Sciences, George Washington University, Washington, DC, USA
| | - Zungho Zun
- Department of Radiology, Weill Cornell Medicine, New York, NY, USA
| |
Collapse
|
10
|
Cascade of Denoising and Mapping Neural Networks for MRI R2* Relaxometry of Iron-Loaded Liver. Bioengineering (Basel) 2023; 10:bioengineering10020209. [PMID: 36829703 PMCID: PMC9952355 DOI: 10.3390/bioengineering10020209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 02/01/2023] [Accepted: 02/02/2023] [Indexed: 02/09/2023] Open
Abstract
MRI of effective transverse relaxation rate (R2*) measurement is a reliable method for liver iron concentration quantification. However, R2* mapping can be degraded by noise, especially in the case of iron overload. This study aimed to develop a deep learning method for MRI R2* relaxometry of an iron-loaded liver using a two-stage cascaded neural network. The proposed method, named CadamNet, combines two convolutional neural networks separately designed for image denoising and parameter mapping into a cascade framework, and the physics-based R2* decay model was incorporated in training the mapping network to enforce data consistency further. CadamNet was trained using simulated liver data with Rician noise, which was constructed from clinical liver data. The performance of CadamNet was quantitatively evaluated on simulated data with varying noise levels as well as clinical liver data and compared with the single-stage parameter mapping network (MappingNet) and two conventional model-based R2* mapping methods. CadamNet consistently achieved high-quality R2* maps and outperformed MappingNet at varying noise levels. Compared with conventional R2* mapping methods, CadamNet yielded R2* maps with lower errors, higher quality, and substantially increased efficiency. In conclusion, the proposed CadamNet enables accurate and efficient iron-loaded liver R2* mapping, especially in the presence of severe noise.
Collapse
|
11
|
Amyar A, Guo R, Cai X, Assana S, Chow K, Rodriguez J, Yankama T, Cirillo J, Pierce P, Goddu B, Ngo L, Nezafat R. Impact of deep learning architectures on accelerated cardiac T 1 mapping using MyoMapNet. NMR IN BIOMEDICINE 2022; 35:e4794. [PMID: 35767308 PMCID: PMC9532368 DOI: 10.1002/nbm.4794] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/05/2022] [Revised: 05/19/2022] [Accepted: 06/25/2022] [Indexed: 05/10/2023]
Abstract
The objective of the current study was to investigate the performance of various deep learning (DL) architectures for MyoMapNet, a DL model for T1 estimation using accelerated cardiac T1 mapping from four T1 -weighted images collected after a single inversion pulse (Look-Locker 4 [LL4]). We implemented and tested three DL architectures for MyoMapNet: (a) a fully connected neural network (FC), (b) convolutional neural networks (VGG19, ResNet50), and (c) encoder-decoder networks with skip connections (ResUNet, U-Net). Modified Look-Locker inversion recovery (MOLLI) images from 749 patients at 3 T were used for training, validation, and testing. The first four T1 -weighted images from MOLLI5(3)3 and/or MOLLI4(1)3(1)2 protocols were extracted to create accelerated cardiac T1 mapping data. We also prospectively collected data from 28 subjects using MOLLI and LL4 to further evaluate model performance. Despite rigorous training, conventional VGG19 and ResNet50 models failed to produce anatomically correct T1 maps, and T1 values had significant errors. While ResUNet yielded good quality maps, it significantly underestimated T1 . Both FC and U-Net, however, yielded excellent image quality with good T1 accuracy for both native (FC/U-Net/MOLLI = 1217 ± 64/1208 ± 61/1199 ± 61 ms, all p < 0.05) and postcontrast myocardial T1 (FC/U-Net/MOLLI = 578 ± 57/567 ± 54/574 ± 55 ms, all p < 0.05). In terms of precision, the U-Net model yielded better T1 precision compared with the FC architecture (standard deviation of 61 vs. 67 ms for the myocardium for native [p < 0.05], and 31 vs. 38 ms [p < 0.05], for postcontrast). Similar findings were observed in prospectively collected LL4 data. It was concluded that U-Net and FC DL models in MyoMapNet enable fast myocardial T1 mapping using only four T1 -weighted images collected from a single LL sequence with comparable accuracy. U-Net also provides a slight improvement in precision.
Collapse
Affiliation(s)
- Amine Amyar
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Rui Guo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Xiaoying Cai
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
- Siemens Medical Solutions USA, Inc., Boston, Massachusetts, USA
| | - Salah Assana
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Kelvin Chow
- Siemens Medical Solutions USA, Inc., Chicago, Illinois, USA
| | - Jennifer Rodriguez
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Tuyen Yankama
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Julia Cirillo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Patrick Pierce
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Beth Goddu
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Long Ngo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| | - Reza Nezafat
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
12
|
Eyre K, Lindsay K, Razzaq S, Chetrit M, Friedrich M. Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: Basic concepts and status of clinical development. Front Cardiovasc Med 2022; 9:953823. [PMID: 36277755 PMCID: PMC9582154 DOI: 10.3389/fcvm.2022.953823] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Accepted: 09/22/2022] [Indexed: 11/13/2022] Open
Abstract
Simultaneous multi-parametric acquisition and reconstruction techniques (SMART) are gaining attention for their potential to overcome some of cardiovascular magnetic resonance imaging's (CMR) clinical limitations. The major advantages of SMART lie within their ability to simultaneously capture multiple "features" such as cardiac motion, respiratory motion, T1/T2 relaxation. This review aims to summarize the overarching theory of SMART, describing key concepts that many of these techniques share to produce co-registered, high quality CMR images in less time and with less requirements for specialized personnel. Further, this review provides an overview of the recent developments in the field of SMART by describing how they work, the parameters they can acquire, their status of clinical testing and validation, and by providing examples for how their use can improve the current state of clinical CMR workflows. Many of the SMART are in early phases of development and testing, thus larger scale, controlled trials are needed to evaluate their use in clinical setting and with different cardiac pathologies.
Collapse
Affiliation(s)
- Katerina Eyre
- McGill University Health Centre, Montreal, QC, Canada,Department of Experimental Medicine, McGill University, Montreal, QC, Canada,*Correspondence: Katerina Eyre,
| | - Katherine Lindsay
- McGill University Health Centre, Montreal, QC, Canada,Department of Experimental Medicine, McGill University, Montreal, QC, Canada
| | - Saad Razzaq
- Department of Experimental Medicine, McGill University, Montreal, QC, Canada
| | - Michael Chetrit
- McGill University Health Centre, Montreal, QC, Canada,Department of Experimental Medicine, McGill University, Montreal, QC, Canada
| | - Matthias Friedrich
- McGill University Health Centre, Montreal, QC, Canada,Department of Experimental Medicine, McGill University, Montreal, QC, Canada
| |
Collapse
|
13
|
Li Y, Wu C, Qi H, Si D, Ding H, Chen H. Motion correction for native myocardial T 1 mapping using self-supervised deep learning registration with contrast separation. NMR IN BIOMEDICINE 2022; 35:e4775. [PMID: 35599351 DOI: 10.1002/nbm.4775] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Revised: 05/15/2022] [Accepted: 05/18/2022] [Indexed: 06/15/2023]
Abstract
In myocardial T1 mapping, undesirable motion poses significant challenges because uncorrected motion can affect T1 estimation accuracy and cause incorrect diagnosis. In this study, we propose and evaluate a motion correction method for myocardial T1 mapping using self-supervised deep learning based registration with contrast separation (SDRAP). A sparse coding based method was first proposed to separate the contrast component from T1 -weighted (T1w) images. Then, a self-supervised deep neural network with cross-correlation (SDRAP-CC) or mutual information as the registration similarity measurement was developed to register contrast separated images, after which signal fitting was performed on the motion corrected T1w images to generate motion corrected T1 maps. The registration network was trained and tested in 80 healthy volunteers with images acquired using the modified Look-Locker inversion recovery (MOLLI) sequence. The proposed SDRAP was compared with the free form deformation (FFD) registration method regarding (1) Dice similarity coefficient (DSC) and mean boundary error (MBE) of myocardium contours, (2) T1 value and standard deviation (SD) of T1 fitting, (3) subjective evaluation score for overall image quality and motion artifact level, and (4) computation time. Results showed that SDRAP-CC achieved the highest DSC of 85.0 ± 3.9% and the lowest MBE of 0.92 ± 0.25 mm among the methods compared. Additionally, SDRAP-CC performed the best by resulting in lower SD value (28.1 ± 17.6 ms) and higher subjective image quality scores (3.30 ± 0.79 for overall quality and 3.53 ± 0.68 for motion artifact) evaluated by a cardiologist. The proposed SDRAP took only 0.52 s to register one slice of MOLLI images, achieving about sevenfold acceleration over FFD (3.7 s/slice).
Collapse
Affiliation(s)
- Yuze Li
- Center for Biomedical Imaging Research (CBIR), School of Medicine, Tsinghua University, Beijing, China
| | - Chunyan Wu
- Center for Biomedical Imaging Research (CBIR), School of Medicine, Tsinghua University, Beijing, China
| | - Haikun Qi
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| | - Dongyue Si
- Center for Biomedical Imaging Research (CBIR), School of Medicine, Tsinghua University, Beijing, China
| | - Haiyan Ding
- Center for Biomedical Imaging Research (CBIR), School of Medicine, Tsinghua University, Beijing, China
| | - Huijun Chen
- Center for Biomedical Imaging Research (CBIR), School of Medicine, Tsinghua University, Beijing, China
| |
Collapse
|
14
|
Jarkman C, Carlhäll CJ, Henningsson M. Clinical evaluation of the Multimapping technique for simultaneous myocardial T1 and T2 mapping. Front Cardiovasc Med 2022; 9:960403. [PMID: 36148079 PMCID: PMC9485633 DOI: 10.3389/fcvm.2022.960403] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Accepted: 08/05/2022] [Indexed: 11/16/2022] Open
Abstract
The Multimapping technique was recently proposed for simultaneous myocardial T1 and T2 mapping. In this study, we evaluate its correlation with clinical reference mapping techniques in patients with a range of cardiovascular diseases (CVDs) and compare image quality and inter- and intra-observer repeatability. Multimapping consists of an ECG-triggered, 2D single-shot bSSFP readout with inversion recovery and T2 preparation modules, acquired across 10 cardiac cycles. The sequence was implemented at 1.5T and compared to clinical reference mapping techniques, modified Look-Locker inversion recovery (MOLLI) and T2 prepared bSSFP with four echo times (T2bSSFP), and compared in 47 patients with CVD (of which 44 were analyzed). In diseased myocardial segments (defined as the presence of late gadolinium enhancement), there was a high correlation between Multimapping and MOLLI for native myocardium T1 (r2 = 0.73), ECV (r2 = 0.91), and blood T1 (r2 = 0.88), and Multimapping and T2bSSFP for native myocardial T2 (r2 = 0.80). In healthy myocardial segments, a bias for native T1 (Multimapping = 1,116 ± 21 ms, MOLLI = 1,002 ± 21, P < 0.001), post-contrast T1 (Multimapping = 479 ± 31 ms, MOLLI = 426 ± 27 ms, 0.001), ECV (Multimapping = 21.5 ± 1.9%, MOLLI = 23.7 ± 2.3%, P = 0.001), and native T2 (Multimapping = 48.0 ± 3.0 ms, T2bSSFP = 53.9 ± 3.5 ms, P < 0.001) was observed. The image quality for Multimapping was scored as higher for all mapping techniques (native T1, post-contrast T1, ECV, and T2bSSFP) compared to the clinical reference techniques. The inter- and intra-observer agreements were excellent (intraclass correlation coefficient, ICC > 0.9) for most measurements, except for inter-observer repeatability of Multimapping native T1 (ICC = 0.87), post-contrast T1 (ICC = 0.73), and T2bSSFP native T2 (ICC = 0.88). Multimapping shows high correlations with clinical reference mapping techniques for T1, T2, and ECV in a diverse cohort of patients with different cardiovascular diseases. Multimapping enables simultaneous T1 and T2 mapping and can be performed in a short breath-hold, with image quality superior to that of the clinical reference techniques.
Collapse
Affiliation(s)
- Charlotta Jarkman
- Department of Clinical Physiology in Linköping, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | - Carl-Johan Carlhäll
- Department of Clinical Physiology in Linköping, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Division of Diagnostics and Specialist Medicine, Department of Health, Medicine and Caring Sciences (HMV), Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | - Markus Henningsson
- Department of Clinical Physiology in Linköping, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Division of Diagnostics and Specialist Medicine, Department of Health, Medicine and Caring Sciences (HMV), Linköping University, Linköping, Sweden
- *Correspondence: Markus Henningsson
| |
Collapse
|
15
|
Guo R, Chen Z, Amyar A, El-Rewaidy H, Assana S, Rodriguez J, Pierce P, Goddu B, Nezafat R. Improving accuracy of myocardial T 1 estimation in MyoMapNet. Magn Reson Med 2022; 88:2573-2582. [PMID: 35916305 DOI: 10.1002/mrm.29397] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Revised: 07/01/2022] [Accepted: 07/05/2022] [Indexed: 11/09/2022]
Abstract
PURPOSE To improve the accuracy and robustness of T1 estimation by MyoMapNet, a deep learning-based approach using 4 inversion-recovery T1 -weighted images for cardiac T1 mapping. METHODS MyoMapNet is a fully connected neural network for T1 estimation of an accelerated cardiac T1 mapping sequence, which collects 4 T1 -weighted images by a single Look-Locker inversion-recovery experiment (LL4). MyoMapNet was originally trained using in vivo data from the modified Look-Locker inversion recovery sequence, which resulted in significant bias and sensitivity to various confounders. This study sought to train MyoMapNet using signals generated from numerical simulations and phantom MR data under multiple simulated confounders. The trained model was then evaluated by phantom data scanned using new phantom vials that differed from those used for training. The performance of the new model was compared with modified Look-Locker inversion recovery sequence and saturation-recovery single-shot acquisition for measuring native and postcontrast T1 in 25 subjects. RESULTS In the phantom study, T1 values measured by LL4 with MyoMapNet were highly correlated with reference values from the spin-echo sequence. Furthermore, the estimated T1 had excellent robustness to changes in flip angle and off-resonance. Native and postcontrast myocardium T1 at 3 Tesla measured by saturation-recovery single-shot acquisition, modified Look-Locker inversion recovery sequence, and MyoMapNet were 1483 ± 46.6 ms and 791 ± 45.8 ms, 1169 ± 49.0 ms and 612 ± 36.0 ms, and 1443 ± 57.5 ms and 700 ± 57.5 ms, respectively. The corresponding extracellular volumes were 22.90% ± 3.20%, 28.88% ± 3.48%, and 30.65% ± 3.60%, respectively. CONCLUSION Training MyoMapNet with numerical simulations and phantom data will improve the estimation of myocardial T1 values and increase its robustness to confounders while also reducing the overall T1 mapping estimation time to only 4 heartbeats.
Collapse
Affiliation(s)
- Rui Guo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Zhensen Chen
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, People's Republic of China
| | - Amine Amyar
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Hossam El-Rewaidy
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Salah Assana
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Jennifer Rodriguez
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Patrick Pierce
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Beth Goddu
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Reza Nezafat
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
16
|
Fast, Accurate, and Robust T2 Mapping of Articular Cartilage by Neural Networks. Diagnostics (Basel) 2022; 12:diagnostics12030688. [PMID: 35328240 PMCID: PMC8947694 DOI: 10.3390/diagnostics12030688] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2022] [Revised: 02/25/2022] [Accepted: 03/09/2022] [Indexed: 12/31/2022] Open
Abstract
For T2 mapping, the underlying mono-exponential signal decay is traditionally quantified by non-linear Least-Squares Estimation (LSE) curve fitting, which is prone to outliers and computationally expensive. This study aimed to validate a fully connected neural network (NN) to estimate T2 relaxation times and to assess its performance versus LSE fitting methods. To this end, the NN was trained and tested in silico on a synthetic dataset of 75 million signal decays. Its quantification error was comparatively evaluated against three LSE methods, i.e., traditional methods without any modification, with an offset, and one with noise correction. Following in-situ acquisition of T2 maps in seven human cadaveric knee joint specimens at high and low signal-to-noise ratios, the NN and LSE methods were used to estimate the T2 relaxation times of the manually segmented patellofemoral cartilage. In-silico modeling at low signal-to-noise ratio indicated significantly lower quantification error for the NN (by medians of 6−33%) than for the LSE methods (p < 0.001). These results were confirmed by the in-situ measurements (medians of 10−35%). T2 quantification by the NN took only 4 s, which was faster than the LSE methods (28−43 s). In conclusion, NNs provide fast, accurate, and robust quantification of T2 relaxation times.
Collapse
|
17
|
Guo R, El-Rewaidy H, Assana S, Cai X, Amyar A, Chow K, Bi X, Yankama T, Cirillo J, Pierce P, Goddu B, Ngo L, Nezafat R. Accelerated cardiac T 1 mapping in four heartbeats with inline MyoMapNet: a deep learning-based T 1 estimation approach. J Cardiovasc Magn Reson 2022; 24:6. [PMID: 34986850 PMCID: PMC8734349 DOI: 10.1186/s12968-021-00834-0] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2021] [Accepted: 11/30/2021] [Indexed: 11/24/2022] Open
Abstract
PURPOSE To develop and evaluate MyoMapNet, a rapid myocardial T1 mapping approach that uses fully connected neural networks (FCNN) to estimate T1 values from four T1-weighted images collected after a single inversion pulse in four heartbeats (Look-Locker, LL4). METHOD We implemented an FCNN for MyoMapNet to estimate T1 values from a reduced number of T1-weighted images and corresponding inversion-recovery times. We studied MyoMapNet performance when trained using native, post-contrast T1, or a combination of both. We also explored the effects of number of T1-weighted images (four and five) for native T1. After rigorous training using in-vivo modified Look-Locker inversion recovery (MOLLI) T1 mapping data of 607 patients, MyoMapNet performance was evaluated using MOLLI T1 data from 61 patients by discarding the additional T1-weighted images. Subsequently, we implemented a prototype MyoMapNet and LL4 on a 3 T scanner. LL4 was used to collect T1 mapping data in 27 subjects with inline T1 map reconstruction by MyoMapNet. The resulting T1 values were compared to MOLLI. RESULTS MyoMapNet trained using a combination of native and post-contrast T1-weighted images had excellent native and post-contrast T1 accuracy compared to MOLLI. The FCNN model using four T1-weighted images yields similar performance compared to five T1-weighted images, suggesting that four T1 weighted images may be sufficient. The inline implementation of LL4 and MyoMapNet enables successful acquisition and reconstruction of T1 maps on the scanner. Native and post-contrast myocardium T1 by MOLLI and MyoMapNet was 1170 ± 55 ms vs. 1183 ± 57 ms (P = 0.03), and 645 ± 26 ms vs. 630 ± 30 ms (P = 0.60), and native and post-contrast blood T1 was 1820 ± 29 ms vs. 1854 ± 34 ms (P = 0.14), and 508 ± 9 ms vs. 514 ± 15 ms (P = 0.02), respectively. CONCLUSION A FCNN, trained using MOLLI data, can estimate T1 values from only four T1-weighted images. MyoMapNet enables myocardial T1 mapping in four heartbeats with similar accuracy as MOLLI with inline map reconstruction.
Collapse
Affiliation(s)
- Rui Guo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Hossam El-Rewaidy
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Salah Assana
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Xiaoying Cai
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
- Siemens Medical Solutions USA, Inc, Boston, MA, USA
| | - Amine Amyar
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Kelvin Chow
- Siemens Medical Solutions USA, Inc, Chicago, IL, USA
| | - Xiaoming Bi
- Siemens Medical Solutions USA, Inc, Chicago, IL, USA
| | - Tuyen Yankama
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Julia Cirillo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Patrick Pierce
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Beth Goddu
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Long Ngo
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA
| | - Reza Nezafat
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline Avenue, MA, 02215, Boston, USA.
| |
Collapse
|
18
|
Sabidussi ER, Klein S, Caan MWA, Bazrafkan S, den Dekker AJ, Sijbers J, Niessen WJ, Poot DHJ. Recurrent inference machines as inverse problem solvers for MR relaxometry. Med Image Anal 2021; 74:102220. [PMID: 34543912 DOI: 10.1016/j.media.2021.102220] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2020] [Revised: 06/10/2021] [Accepted: 08/26/2021] [Indexed: 11/25/2022]
Abstract
In this paper, we propose the use of Recurrent Inference Machines (RIMs) to perform T1 and T2 mapping. The RIM is a neural network framework that learns an iterative inference process based on the signal model, similar to conventional statistical methods for quantitative MRI (QMRI), such as the Maximum Likelihood Estimator (MLE). This framework combines the advantages of both data-driven and model-based methods, and, we hypothesize, is a promising tool for QMRI. Previously, RIMs were used to solve linear inverse reconstruction problems. Here, we show that they can also be used to optimize non-linear problems and estimate relaxometry maps with high precision and accuracy. The developed RIM framework is evaluated in terms of accuracy and precision and compared to an MLE method and an implementation of the Residual Neural Network (ResNet). The results show that the RIM improves the quality of estimates compared to the other techniques in Monte Carlo experiments with simulated data, test-retest analysis of a system phantom, and in-vivo scans. Additionally, inference with the RIM is 150 times faster than the MLE, and robustness to (slight) variations of scanning parameters is demonstrated. Hence, the RIM is a promising and flexible method for QMRI. Coupled with an open-source training data generation tool, it presents a compelling alternative to previous methods.
Collapse
Affiliation(s)
- E R Sabidussi
- Erasmus MC University Medical Center, Department of Radiology and Nuclear Medicine, Rotterdam, the Netherlands.
| | - S Klein
- Erasmus MC University Medical Center, Department of Radiology and Nuclear Medicine, Rotterdam, the Netherlands
| | - M W A Caan
- Amsterdam UMC, Biomedical Engineering and Physics, University of Amsterdam, Amsterdam, the Netherlands
| | - S Bazrafkan
- imec-Vision Lab, Department of Physics, University of Antwerp, Antwerp, Belgium
| | - A J den Dekker
- imec-Vision Lab, Department of Physics, University of Antwerp, Antwerp, Belgium
| | - J Sijbers
- imec-Vision Lab, Department of Physics, University of Antwerp, Antwerp, Belgium; µ NEURO Research Centre of Excellence, University of Antwerp, Antwerp, Belgium
| | - W J Niessen
- Erasmus MC University Medical Center, Department of Radiology and Nuclear Medicine, Rotterdam, the Netherlands; Delft University of Technology, Delft, the Netherlands
| | - D H J Poot
- Erasmus MC University Medical Center, Department of Radiology and Nuclear Medicine, Rotterdam, the Netherlands
| |
Collapse
|
19
|
Takeshima H. Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview. Magn Reson Med Sci 2021; 21:553-568. [PMID: 34544924 DOI: 10.2463/mrms.rev.2021-0040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022] Open
Abstract
This article presents an overview of deep learning (DL) and its applications to function approximation for MR in medicine. The aim of this article is to help readers develop various applications of DL. DL has made a large impact on the literature of many medical sciences, including MR. However, its technical details are not easily understandable for non-experts of machine learning (ML).The first part of this article presents an overview of DL and its related technologies, such as artificial intelligence (AI) and ML. AI is explained as a function that can receive many inputs and produce many outputs. ML is a process of fitting the function to training data. DL is a kind of ML, which uses a composite of many functions to approximate the function of interest. This composite function is called a deep neural network (DNN), and the functions composited into a DNN are called layers. This first part also covers the underlying technologies required for DL, such as loss functions, optimization, initialization, linear layers, non-linearities, normalization, recurrent neural networks, regularization, data augmentation, residual connections, autoencoders, generative adversarial networks, model and data sizes, and complex-valued neural networks.The second part of this article presents an overview of the applications of DL in MR and explains how functions represented as DNNs are applied to various applications, such as RF pulse, pulse sequence, reconstruction, motion correction, spectroscopy, parameter mapping, image synthesis, and segmentation.
Collapse
Affiliation(s)
- Hidenori Takeshima
- Advanced Technology Research Department, Research and Development Center, Canon Medical Systems Corporation
| |
Collapse
|
20
|
Li Y, Wang Y, Qi H, Hu Z, Chen Z, Yang R, Qiao H, Sun J, Wang T, Zhao X, Guo H, Chen H. Deep learning-enhanced T 1 mapping with spatial-temporal and physical constraint. Magn Reson Med 2021; 86:1647-1661. [PMID: 33821529 DOI: 10.1002/mrm.28793] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2020] [Revised: 03/07/2021] [Accepted: 03/15/2021] [Indexed: 12/20/2022]
Abstract
PURPOSE To propose a reconstruction framework to generate accurate T1 maps for a fast MR T1 mapping sequence. METHODS A deep learning-enhanced T1 mapping method with spatial-temporal and physical constraint (DAINTY) was proposed. This method explicitly imposed low-rank and sparsity constraints on the multiframe T1 -weighted images to exploit the spatial-temporal correlation. A deep neural network was used to efficiently perform T1 mapping as well as denoise and reduce undersampling artifacts. Additionally, the physical constraint was used to build a bridge between low-rank and sparsity constraint and deep learning prior, so the benefits of constrained reconstruction and deep learning can be both available. The DAINTY method was trained on simulated brain data sets, but tested on real acquired phantom, 6 healthy volunteers, and 7 atherosclerosis patients, compared with the narrow-band k-space-weighted image contrast filter conjugate-gradient SENSE (NK-CS) method, kt-sparse-SENSE (kt-SS) method, and low-rank plus sparsity (L+S) method with least-squares T1 fitting and direct deep learning mapping. RESULTS The DAINTY method can generate more accurate T1 maps and higher-quality T1 -weighted images compared with other methods. For atherosclerosis patients, the intraplaque hemorrhage can be successfully detected. The computation speed of DAINTY was 10 times faster than traditional methods. Meanwhile, DAINTY can reconstruct images with comparable quality using only 50% of k-space data. CONCLUSION The proposed method can provide accurate T1 maps and good-quality T1 -weighted images with high efficiency.
Collapse
Affiliation(s)
- Yuze Li
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Yajie Wang
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Haikun Qi
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| | - Zhangxuan Hu
- GE Healthcare, MR Research China, Beijing, China
| | - Zhensen Chen
- Vascular Imaging Lab and BioMolecular Imaging Center, Department of Radiology, University of Washington, Seattle, Washington, USA
| | - Runyu Yang
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Huiyu Qiao
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Jie Sun
- GE Healthcare, MR Research China, Beijing, China
| | - Tao Wang
- Department of Neurology, Peking University Third Hospital, Beijing, China
| | - Xihai Zhao
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Hua Guo
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Huijun Chen
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| |
Collapse
|
21
|
Nezafat M, El-Rewaidy H, Kucukseymen S, Hauser TH, Fahmy AS. Deep convolution neural networks based artifact suppression in under-sampled radial acquisitions of myocardial T 1 mapping images. Phys Med Biol 2020; 65:225024. [PMID: 33045693 DOI: 10.1088/1361-6560/abc04f] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
We developed a deep convolutional neural network (CNN) based method to remove streaking artefact from accelerated radial acquisitions of myocardial T 1-mapping images. A deep CNN based on a modified U-Net architecture was developed and trained to remove the streaking artefacts from under-sampled T 1 mapping images. A total of 2090 T 1-weighted images for 33 patients (55 ± 15 years, 19 males) and five healthy subjects (30 ± 14 years, 2 males) were used for training and testing the network. The images were acquired using radial slice interleaved T 1 mapping sequence (STONE) and retrospectively under-sampled to achieve acceleration rate of 4 (corresponding to 48 spokes). The dataset was split into training and testing subsets with 23 subjects (60%) and 15 subjects (40%), respectively. For generating voxel-wise T 1 maps, a two-parameter fitting model was used. Network performance was evaluated using normalized mean square error (NMSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) metrics. The proposed network allowed fast (<0.3 s/image) removal of the artefact from all T 1-weighted testing images and the corresponding T 1 maps with PSNR = 64.3 ± 1.02, NMSE = 0.2 ± 0.09 and SSIM = 0.9 ± 0.3 × 10-4. There was no statistically significant difference between the measured T 1 maps for both per-subject (reference: 1085 ± 37 ms, CNN: 1088 ± 37 ms, p = 0.4) and per-segment (reference: 1084 ± 48 ms, CNN: 1083 ± 58 ms, p = 0.9) analyses. In summary, deep CNN allows fast and reliable removal of streaking artefact from under-sampled radial T 1 mapping images. Our results show that the highly non-linear operations of deep CNN processing of T 1 mapping images do not impact accurate reconstruction of myocardial T 1 maps.
Collapse
Affiliation(s)
- Maryam Nezafat
- Department of Medicine, Beth Israel Deaconess Medical Centre and Harvard Medical School, 330 Brookline Ave, Boston, MA 02215, United States of America
| | | | | | | | | |
Collapse
|
22
|
Shao J, Ghodrati V, Nguyen K, Hu P. Fast and accurate calculation of myocardial T 1 and T 2 values using deep learning Bloch equation simulations (DeepBLESS). Magn Reson Med 2020; 84:2831-2845. [PMID: 32416010 PMCID: PMC7402013 DOI: 10.1002/mrm.28321] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2019] [Revised: 04/22/2020] [Accepted: 04/23/2020] [Indexed: 12/15/2022]
Abstract
PURPOSE To propose and evaluate a deep learning model for rapid and accurate calculation of myocardial T1 /T2 values based on a previously proposed Bloch equation simulation with slice profile correction (BLESSPC) method. METHODS Deep learning Bloch equation simulations (DeepBLESS) models are proposed for rapid and accurate T1 estimation for the MOLLI T1 mapping sequence with balanced SSFP readouts and T1 /T2 estimation for a radial simultaneous T1 and T2 mapping (radial T1 -T2 ) sequence. The DeepBLESS models were trained separately based on simulated radial T1 -T2 and MOLLI data, respectively. The DeepBLESS T1 -T2 estimation accuracy was evaluated based on simulated data with different noise levels. The DeepBLESS model was compared with BLESSPC in simulation, phantom, and in vivo studies for the MOLLI sequence at 1.5 T and radial T1 -T2 sequence at 3 T. RESULTS After DeepBLESS was trained, in phantom studies, DeepBLESS and BLESSPC achieved similar accuracy and precision in T1 -T2 estimations for both MOLLI and radial T1 -T2 (P > .05). For in vivo, DeepBLESS and BLESSPC generated similar myocardial T1 /T2 values for radial T1 -T2 at 3 T (T1 : 1366 ± 31 ms for both methods, P > .05; T2 : 37.4 ms ± 0.9 ms for both methods, P > .05), and similar myocardial T1 values for the MOLLI sequence at 1.5 T (1044 ± 20 ms for both methods, P > .05). DeepBLESS generated a T1 /T2 map in less than 1 second. CONCLUSION The DeepBLESS model offers an almost instantaneous approach for estimating accurate T1 /T2 values, replacing BLESSPC for both MOLLI and radial T1 -T2 sequences, and is promising for multiparametric mapping in cardiac MRI.
Collapse
Affiliation(s)
- Jiaxin Shao
- Department of Radiological SciencesDavid Geffen School of MedicineUniversity of CaliforniaLos AngelesCaliforniaUSA
| | - Vahid Ghodrati
- Department of Radiological SciencesDavid Geffen School of MedicineUniversity of CaliforniaLos AngelesCaliforniaUSA
| | - Kim‐Lien Nguyen
- Department of MedicineDivision of CardiologyDavid Geffen School of MedicineUniversity of CaliforniaLos AngelesCaliforniaUSA
- Division of CardiologyVeterans Affairs Greater Los Angeles Healthcare SystemLos AngelesCaliforniaUSA
| | - Peng Hu
- Department of Radiological SciencesDavid Geffen School of MedicineUniversity of CaliforniaLos AngelesCaliforniaUSA
- Biomedical Physics Inter‐Departmental Graduate ProgramUniversity of CaliforniaLos AngelesCaliforniaUSA
| |
Collapse
|
23
|
Hamilton JI, Currey D, Rajagopalan S, Seiberlich N. Deep learning reconstruction for cardiac magnetic resonance fingerprinting T 1 and T 2 mapping. Magn Reson Med 2020; 85:2127-2135. [PMID: 33107162 DOI: 10.1002/mrm.28568] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2020] [Revised: 09/30/2020] [Accepted: 10/02/2020] [Indexed: 02/01/2023]
Abstract
PURPOSE To develop a deep learning method for rapidly reconstructing T1 and T2 maps from undersampled electrocardiogram (ECG) triggered cardiac magnetic resonance fingerprinting (cMRF) images. METHODS A neural network was developed that outputs T1 and T2 values when given a measured cMRF signal time course and cardiac RR interval times recorded by an ECG. Over 8 million cMRF signals, corresponding to 4000 random cardiac rhythms, were simulated for training. The training signals were corrupted by simulated k-space undersampling artifacts and random phase shifts to promote robust learning. The deep learning reconstruction was evaluated in Monte Carlo simulations for a variety of cardiac rhythms and compared with dictionary-based pattern matching in 58 healthy subjects at 1.5T. RESULTS In simulations, the normalized root-mean-square error (nRMSE) for T1 was below 1% in myocardium, blood, and liver for all tested heart rates. For T2 , the nRMSE was below 4% for myocardium and liver and below 6% for blood for all heart rates. The difference in the mean myocardial T1 or T2 observed in vivo between dictionary matching and deep learning was 3.6 ms for T1 and -0.2 ms for T2 . Whereas dictionary generation and pattern matching required more than 4 min per slice, the deep learning reconstruction only required 336 ms. CONCLUSION A neural network is introduced for reconstructing cMRF T1 and T2 maps directly from undersampled spiral images in under 400 ms and is robust to arbitrary cardiac rhythms, which paves the way for rapid online display of cMRF maps.
Collapse
Affiliation(s)
- Jesse I Hamilton
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Danielle Currey
- Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA
| | - Sanjay Rajagopalan
- Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA.,Division of Cardiovascular Medicine, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Nicole Seiberlich
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| |
Collapse
|