1
|
Patel NM, Bartusiak ER, Rothenberger SM, Schwichtenberg AJ, Delp EJ, Rayz VL. Super-Resolving and Denoising 4D flow MRI of Neurofluids Using Physics-Guided Neural Networks. Ann Biomed Eng 2024:10.1007/s10439-024-03606-w. [PMID: 39223318 DOI: 10.1007/s10439-024-03606-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2024] [Accepted: 08/18/2024] [Indexed: 09/04/2024]
Abstract
PURPOSE To obtain high-resolution velocity fields of cerebrospinal fluid (CSF) and cerebral blood flow by applying a physics-guided neural network (div-mDCSRN-Flow) to 4D flow MRI. METHODS The div-mDCSRN-Flow network was developed to improve spatial resolution and denoise 4D flow MRI. The network was trained with patches of paired high-resolution and low-resolution synthetic 4D flow MRI data derived from computational fluid dynamic simulations of CSF flow within the cerebral ventricles of five healthy cases and five Alzheimer's disease cases. The loss function combined mean squared error with a binary cross-entropy term for segmentation and a divergence-based regularization term for the conservation of mass. Performance was assessed using synthetic 4D flow MRI in one healthy and one Alzheimer' disease cases, an in vitro study of healthy cerebral ventricles, and in vivo 4D flow imaging of CSF as well as flow in arterial and venous blood vessels. Comparison was performed to trilinear interpolation, divergence-free radial basis functions, divergence-free wavelets, 4DFlowNet, and our network without divergence constraints. RESULTS The proposed network div-mDCSRN-Flow outperformed other methods in reconstructing high-resolution velocity fields from synthetic 4D flow MRI in healthy and AD cases. The div-mDCSRN-Flow network reduced error by 22.5% relative to linear interpolation for in vitro core voxels and by 49.5% in edge voxels. CONCLUSION The results demonstrate generalizability of our 4D flow MRI super-resolution and denoising approach due to network training using flow patches and physics-based constraints. The mDCSRN-Flow network can facilitate MRI studies involving CSF flow measurements in cerebral ventricles and association of MRI-based flow metrics with cerebrovascular health.
Collapse
Affiliation(s)
- Neal M Patel
- Biomedical Engineering, Purdue University, West Lafayette, IN, USA
| | - Emily R Bartusiak
- Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
| | | | | | - Edward J Delp
- Biomedical Engineering, Purdue University, West Lafayette, IN, USA
- Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
- Psychological Sciences, Purdue University, West Lafayette, IN, USA
| | - Vitaliy L Rayz
- Biomedical Engineering, Purdue University, West Lafayette, IN, USA.
- Mechanical Engineering, Purdue University, West Lafayette, IN, USA.
| |
Collapse
|
2
|
Sautory T, Shadden SC. Unsupervised Denoising and Super-Resolution of Vascular Flow Data by Physics-Informed Machine Learning. J Biomech Eng 2024; 146:091006. [PMID: 38529728 DOI: 10.1115/1.4065165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2023] [Accepted: 03/18/2024] [Indexed: 03/27/2024]
Abstract
We present an unsupervised deep learning method to perform flow denoising and super-resolution without high-resolution labels. We demonstrate the ability of a single model to reconstruct three-dimensional stenosis and aneurysm flows, with varying geometries, orientations, and boundary conditions. Ground truth data was generated using computational fluid dynamics, and then corrupted with multiplicative Gaussian noise. Auto-encoders were used to compress the representations of the flow domain geometry and the (possibly noisy and low-resolution) flow field. These representations were used to condition a physics-informed neural network. A physics-based loss was implemented to train the model to recover lost information from the noisy input by transforming the flow to a solution of the Navier-Stokes equations. Our experiments achieved mean squared errors in the true flow reconstruction of O(1.0 × 10-4), and root mean squared residuals of O(1.0 × 10-2) for the momentum and continuity equations. Our method yielded correlation coefficients of 0.971 for the hidden pressure field and 0.82 for the derived wall shear stress field. By performing point-wise predictions of the flow, the model was able to robustly denoise and super-resolve the field to 20× the input resolution.
Collapse
Affiliation(s)
- Théophile Sautory
- Department of Mechanical Engineering, University of California, Berkeley, CA 94501
- University of California, Berkeley
| | - Shawn C Shadden
- Department of Mechanical Engineering, University of California, Berkeley, CA 94501
| |
Collapse
|
3
|
Csala H, Amili O, D'Souza RM, Arzani A. A comparison of machine learning methods for recovering noisy and missing 4D flow MRI data. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2024:e3858. [PMID: 39196308 DOI: 10.1002/cnm.3858] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Revised: 05/27/2024] [Accepted: 07/20/2024] [Indexed: 08/29/2024]
Abstract
Experimental blood flow measurement techniques are invaluable for a better understanding of cardiovascular disease formation, progression, and treatment. One of the emerging methods is time-resolved three-dimensional phase-contrast magnetic resonance imaging (4D flow MRI), which enables noninvasive time-dependent velocity measurements within large vessels. However, several limitations hinder the usability of 4D flow MRI and other experimental methods for quantitative hemodynamics analysis. These mainly include measurement noise, corrupt or missing data, low spatiotemporal resolution, and other artifacts. Traditional filtering is routinely applied for denoising experimental blood flow data without any detailed discussion on why it is preferred over other methods. In this study, filtering is compared to different singular value decomposition (SVD)-based machine learning and autoencoder-type deep learning methods for denoising and filling in missing data (imputation). An artificially corrupted and voxelized computational fluid dynamics (CFD) simulation as well as in vitro 4D flow MRI data are used to test the methods. SVD-based algorithms achieve excellent results for the idealized case but severely struggle when applied to in vitro data. The autoencoders are shown to be versatile and applicable to all investigated cases. For denoising, the in vitro 4D flow MRI data, the denoising autoencoder (DAE), and the Noise2Noise (N2N) autoencoder produced better reconstructions than filtering both qualitatively and quantitatively. Deep learning methods such as N2N can result in noise-free velocity fields even though they did not use clean data during training. This work presents one of the first comprehensive assessments and comparisons of various classical and modern machine-learning methods for enhancing corrupt cardiovascular flow data in diseased arteries for both synthetic and experimental test cases.
Collapse
Affiliation(s)
- Hunor Csala
- Department of Mechanical Engineering, University of Utah, Salt Lake City, Utah, USA
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah, USA
| | - Omid Amili
- Department of Mechanical, Industrial and Manufacturing Engineering, University of Toledo, Toledo, Ohio, USA
| | - Roshan M D'Souza
- Department of Mechanical Engineering, University of Wisconsin-Milwaukee, Milwaukee, Wisconsin, USA
| | - Amirhossein Arzani
- Department of Mechanical Engineering, University of Utah, Salt Lake City, Utah, USA
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah, USA
| |
Collapse
|
4
|
Garay J, Dunstan J, Uribe S, Sahli Costabal F. Physics-informed neural networks for parameter estimation in blood flow models. Comput Biol Med 2024; 178:108706. [PMID: 38879935 DOI: 10.1016/j.compbiomed.2024.108706] [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: 11/07/2023] [Revised: 05/31/2024] [Accepted: 06/03/2024] [Indexed: 06/18/2024]
Abstract
BACKGROUND Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving inverse problems, especially in cases where no complete information about the system is known and scatter measurements are available. This is especially useful in hemodynamics since the boundary information is often difficult to model, and high-quality blood flow measurements are generally hard to obtain. METHODS In this work, we use the PINNs methodology for estimating reduced-order model parameters and the full velocity field from scatter 2D noisy measurements in the aorta. Two different flow regimes, stationary and transient were studied. RESULTS We show robust and relatively accurate parameter estimations when using the method with simulated data, while the velocity reconstruction accuracy shows dependence on the measurement quality and the flow pattern complexity. Comparison with a Kalman filter approach shows similar results when the number of parameters to be estimated is low to medium. For a higher number of parameters, only PINNs were capable of achieving good results. CONCLUSION The method opens a door to deep-learning-driven methods in the simulations of complex coupled physical systems.
Collapse
Affiliation(s)
- Jeremías Garay
- Department of Mechanical and Metallurgical Engineering, Pontificia Universidad Católica de Chile, Chile; Center of Biomedical Imaging, Pontificia Universidad Católica de Chile, Chile; Millennium Institute for Intelligent Healthcare Engineering (iHealth), Chile
| | - Jocelyn Dunstan
- Department of Computer Science, Pontificia Universidad Católica de Chile, Chile; Institute for Mathematical and Computational Engineering, Pontificia Universidad Católica de Chile, Chile; Millennium Institute for Foundational Research on Data (IMFD), Chile
| | - Sergio Uribe
- Center of Biomedical Imaging, Pontificia Universidad Católica de Chile, Chile; Millennium Institute for Intelligent Healthcare Engineering (iHealth), Chile; Department of Medical Imaging and Radiation Sciences, Monash University, Australia; Department of Radiology, Pontificia Universidad Católica de Chile, Chile
| | - Francisco Sahli Costabal
- Department of Mechanical and Metallurgical Engineering, Pontificia Universidad Católica de Chile, Chile; Millennium Institute for Intelligent Healthcare Engineering (iHealth), Chile; Institute for Biological and Medical Engineering, Pontificia Universidad Católica de Chile, Chile.
| |
Collapse
|
5
|
Maidu B, Martinez-Legazpi P, Guerrero-Hurtado M, Nguyen CM, Gonzalo A, Kahn AM, Bermejo J, Flores O, Del Alamo JC. Super-resolution Left Ventricular Flow and Pressure Mapping by Navier-Stokes-Informed Neural Networks. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.04.12.589319. [PMID: 38659851 PMCID: PMC11042210 DOI: 10.1101/2024.04.12.589319] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/26/2024]
Abstract
Intraventricular vector flow mapping (VFM) is a growingly adopted echocardiographic modality that derives time-resolved two-dimensional flow maps in the left ventricle (LV) from color-Doppler sequences. Current VFM models rely on kinematic constraints arising from planar flow incompressibility. However, these models are not informed by crucial information about flow physics; most notably the pressure and shear forces within the fluid and the resulting accelerations. This limitation has rendered VFM unable to combine information from different time frames in an acquisition sequence or derive fluctuating pressure maps. In this study, we leveraged recent advances in artificial intelligence (AI) to develop AI-VFM, a vector flow mapping modality that uses physics-informed neural networks (PINNs) encoding mass conservation and momentum balance inside the LV, and no-slip boundary conditions at the LV endocardium. AI-VFM recovers the flow and pressure fields in the LV from standard echocardiographic scans. It performs phase unwrapping and recovers flow data in areas without input color-Doppler data. AI-VFM also recovers complete flow maps at time points without color-Doppler input data, producing super-resolution flow maps. We show that informing the PINNs with momentum balance is essential to achieving temporal super-resolution and significantly increases the accuracy of AI-VFM compared to informing the PINNs only with mass conservation. AI-VFM is solely informed by each patient's flow physics; it does not utilize explicit smoothness constraints or incorporate data from other patients or flow models. AI-VFM takes 15 minutes to run in off-the-shelf graphics processing units and its underlying PINN framework could be extended to map other flow-associated metrics like blood residence time or the concentration of coagulation species.
Collapse
Affiliation(s)
- Bahetihazi Maidu
- Dept. of Mechanical Engineering, University of Washington, Seattle, WA, USA
| | - Pablo Martinez-Legazpi
- Dept. of Mathematical Physics and Fluids. Universidad Nacional de Educación a Distancia & CIBERCV, Madrid, Spain
| | - Manuel Guerrero-Hurtado
- Dept. of Aerospace Engineering and Bioengineering, Universidad Carlos III De Madrid, Leganes, Spain
| | - Cathleen M Nguyen
- Dept. of Mechanical Engineering, University of Washington, Seattle, WA, USA
| | - Alejandro Gonzalo
- Dept. of Mechanical Engineering, University of Washington, Seattle, WA, USA
| | - Andrew M Kahn
- Division of Cardiovascular Medicine., University of California San Diego, La Jolla, CA, USA
| | - Javier Bermejo
- Dept. of Cardiology, Hospital General Universitario Gregorio Marañon & CIBERCV, Madrid, Spain
| | - Oscar Flores
- Dept. of Aerospace Engineering and Bioengineering, Universidad Carlos III De Madrid, Leganes, Spain
| | - Juan C Del Alamo
- Dept. of Mechanical Engineering, University of Washington, Seattle, WA, USA
- Center for Cardiovascular Biology, University of Washington School of Medicine, Seattle, WA, USA
- Division of Cardiology, University of Washington School of Medicine, Seattle, WA, USA
| |
Collapse
|
6
|
Saitta S, Carioni M, Mukherjee S, Schönlieb CB, Redaelli A. Implicit neural representations for unsupervised super-resolution and denoising of 4D flow MRI. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 246:108057. [PMID: 38335865 DOI: 10.1016/j.cmpb.2024.108057] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Revised: 02/02/2024] [Accepted: 02/02/2024] [Indexed: 02/12/2024]
Abstract
BACKGROUND AND OBJECTIVE 4D flow magnetic resonance imaging provides time-resolved blood flow velocity measurements, but suffers from limitations in spatio-temporal resolution and noise. In this study, we investigated the use of sinusoidal representation networks (SIRENs) to improve denoising and super-resolution of velocity fields measured by 4D flow MRI in the thoracic aorta. METHODS Efficient training of SIRENs in 4D was achieved by sampling voxel coordinates and enforcing the no-slip condition at the vessel wall. A set of synthetic measurements were generated from computational fluid dynamics simulations, reproducing different noise levels. The influence of SIREN architecture was systematically investigated, and the performance of our method was compared to existing approaches for 4D flow denoising and super-resolution. RESULTS Compared to existing techniques, a SIREN with 300 neurons per layer and 20 layers achieved lower errors (up to 50% lower vector normalized root mean square error, 42% lower magnitude normalized root mean square error, and 15% lower direction error) in velocity and wall shear stress fields. Applied to real 4D flow velocity measurements in a patient-specific aortic aneurysm, our method produced denoised and super-resolved velocity fields while maintaining accurate macroscopic flow measurements. CONCLUSIONS This study demonstrates the feasibility of using SIRENs for complex blood flow velocity representation from clinical 4D flow, with quick execution and straightforward implementation.
Collapse
Affiliation(s)
- Simone Saitta
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
| | - Marcello Carioni
- Department of Applied Mathematics, University of Twente, 7500AE Enschede, the Netherlands
| | - Subhadip Mukherjee
- Department of Electronics & Electrical Communication Engineering, Indian Institute of Technology (IIT) Kharagpur, India
| | - Carola-Bibiane Schönlieb
- Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK
| | - Alberto Redaelli
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy
| |
Collapse
|
7
|
MacRaild M, Sarrami-Foroushani A, Lassila T, Frangi AF. Accelerated simulation methodologies for computational vascular flow modelling. J R Soc Interface 2024; 21:20230565. [PMID: 38350616 PMCID: PMC10864099 DOI: 10.1098/rsif.2023.0565] [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: 09/26/2023] [Accepted: 01/12/2024] [Indexed: 02/15/2024] Open
Abstract
Vascular flow modelling can improve our understanding of vascular pathologies and aid in developing safe and effective medical devices. Vascular flow models typically involve solving the nonlinear Navier-Stokes equations in complex anatomies and using physiological boundary conditions, often presenting a multi-physics and multi-scale computational problem to be solved. This leads to highly complex and expensive models that require excessive computational time. This review explores accelerated simulation methodologies, specifically focusing on computational vascular flow modelling. We review reduced order modelling (ROM) techniques like zero-/one-dimensional and modal decomposition-based ROMs and machine learning (ML) methods including ML-augmented ROMs, ML-based ROMs and physics-informed ML models. We discuss the applicability of each method to vascular flow acceleration and the effectiveness of the method in addressing domain-specific challenges. When available, we provide statistics on accuracy and speed-up factors for various applications related to vascular flow simulation acceleration. Our findings indicate that each type of model has strengths and limitations depending on the context. To accelerate real-world vascular flow problems, we propose future research on developing multi-scale acceleration methods capable of handling the significant geometric variability inherent to such problems.
Collapse
Affiliation(s)
- Michael MacRaild
- Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Leeds, Leeds, UK
- EPSRC Centre for Doctoral Training in Fluid Dynamics, University of Leeds, Leeds, UK
| | - Ali Sarrami-Foroushani
- Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Leeds, Leeds, UK
- School of Health Science, University of Manchester, Manchester, UK
| | - Toni Lassila
- Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Leeds, Leeds, UK
- School of Computing, University of Leeds, Leeds, UK
| | - Alejandro F. Frangi
- Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Leeds, Leeds, UK
- School of Computer Science, University of Manchester, Manchester, UK
- School of Health Science, University of Manchester, Manchester, UK
- Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium
- Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium
| |
Collapse
|
8
|
Liao J, Misaki K, Uno T, Nambu I, Kamide T, Chen Z, Nakada M, Sakamoto J. Fluid dynamic analysis in predicting the recanalization of intracranial aneurysms after coil embolization - A study of spatiotemporal characteristics. Heliyon 2024; 10:e22801. [PMID: 38226254 PMCID: PMC10788401 DOI: 10.1016/j.heliyon.2023.e22801] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 10/09/2023] [Accepted: 11/20/2023] [Indexed: 01/17/2024] Open
Abstract
Purpose Hemodynamics play a key role in the management of cerebral aneurysm recanalization after coil embolization; however, the most reliable hemodynamic parameter remains unknown. Previous studies have explored the use of both spatiotemporally averaged and maximal definitions for hemodynamic parameters, based on computational fluid dynamics (CFD) analysis, to build predictive models for aneurysmal recanalization. In this study, we aimed to assess the influence of different spatiotemporal characteristics of hemodynamic parameters on predictive performance. Methods Hemodynamics were simulated using CFD for 66 cerebral aneurysms from 65 patients. We evaluated 14 types of spatiotemporal definitions for two hemodynamic parameters in the pre-coiling model and five in virtual post-coiling model (VM) created by cutting the aneurysm from the pre-coiling model. A total of 91 spatiotemporal hemodynamic features were derived and utilized to develop univariate predictor (UP) and multivariate logistic regression (LR) models. The model's performance was assessed using two metrics: the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Results Different spatiotemporal hemodynamic features exhibited a wide range of AUROC values ranging from 0.224 to 0.747, with 22 feature pairs showing a significant difference in AUROC value (P-value <0.05), despite being derived from the same hemodynamic parameter. PDave,q1 was identified as the strongest UP with AUROC/AUPRC values of 0.747/0.385, yielding sensitivity and specificity value of 0.889 and 0.614 at the optimal cut-off value, respectively. The LR model further improved the prediction performance, having AUROC/AUPRC values of 0.890/0.903. At the optimal cut-off value, the LR model achieved a specificity of 0.877, sensitivity of 0.719, outperforming the UP model. Conclusion Our research indicated that the characteristics of hemodynamic parameters in terms of space and time had a significant impact on the development of predictive model. Our findings suggest that LR model based on spatiotemporal hemodynamic features could be clinically useful in predicting recanalization after coil embolization in patients, without the need for invasive procedures.
Collapse
Affiliation(s)
- Jing Liao
- Division of Transdisciplinary Sciences, Graduate School of Frontier Science Initiative, Kanazawa University, Ishikawa, Japan
| | - Kouichi Misaki
- Department of Neurosurgery, Kanazawa University, Ishikawa, Japan
| | - Tekehiro Uno
- Department of Neurosurgery, Kanazawa University, Ishikawa, Japan
| | - Iku Nambu
- Department of Neurosurgery, Kanazawa University, Ishikawa, Japan
| | - Tomoya Kamide
- Department of Neurosurgery, Kanazawa University, Ishikawa, Japan
| | - Zhuoqing Chen
- Department of Nuclear Medicine, Kanazawa University, Ishikawa, Japan
| | | | - Jiro Sakamoto
- Division of Mechanical Science and Engineering, Graduate School of Natural Science and Technology, Kanazawa University, Kanazawa, Ishikawa, Japan
| |
Collapse
|
9
|
Aggarwal K, Manso Jimeno M, Ravi KS, Gonzalez G, Geethanath S. Developing and deploying deep learning models in brain magnetic resonance imaging: A review. NMR IN BIOMEDICINE 2023; 36:e5014. [PMID: 37539775 DOI: 10.1002/nbm.5014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/04/2023] [Revised: 07/12/2023] [Accepted: 07/13/2023] [Indexed: 08/05/2023]
Abstract
Magnetic resonance imaging (MRI) of the brain has benefited from deep learning (DL) to alleviate the burden on radiologists and MR technologists, and improve throughput. The easy accessibility of DL tools has resulted in a rapid increase of DL models and subsequent peer-reviewed publications. However, the rate of deployment in clinical settings is low. Therefore, this review attempts to bring together the ideas from data collection to deployment in the clinic, building on the guidelines and principles that accreditation agencies have espoused. We introduce the need for and the role of DL to deliver accessible MRI. This is followed by a brief review of DL examples in the context of neuropathologies. Based on these studies and others, we collate the prerequisites to develop and deploy DL models for brain MRI. We then delve into the guiding principles to develop good machine learning practices in the context of neuroimaging, with a focus on explainability. A checklist based on the United States Food and Drug Administration's good machine learning practices is provided as a summary of these guidelines. Finally, we review the current challenges and future opportunities in DL for brain MRI.
Collapse
Affiliation(s)
- Kunal Aggarwal
- Accessible MR Laboratory, Biomedical Engineering and Imaging Institute, Department of Diagnostic, Molecular and Interventional Radiology, Mount Sinai Hospital, New York, USA
- Department of Electrical and Computer Engineering, Technical University Munich, Munich, Germany
| | - Marina Manso Jimeno
- Department of Biomedical Engineering, Columbia University in the City of New York, New York, New York, USA
- Columbia Magnetic Resonance Research Center, Columbia University in the City of New York, New York, New York, USA
| | - Keerthi Sravan Ravi
- Department of Biomedical Engineering, Columbia University in the City of New York, New York, New York, USA
- Columbia Magnetic Resonance Research Center, Columbia University in the City of New York, New York, New York, USA
| | - Gilberto Gonzalez
- Division of Neuroradiology, Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Sairam Geethanath
- Accessible MR Laboratory, Biomedical Engineering and Imaging Institute, Department of Diagnostic, Molecular and Interventional Radiology, Mount Sinai Hospital, New York, USA
| |
Collapse
|
10
|
Bissell MM, Raimondi F, Ait Ali L, Allen BD, Barker AJ, Bolger A, Burris N, Carhäll CJ, Collins JD, Ebbers T, Francois CJ, Frydrychowicz A, Garg P, Geiger J, Ha H, Hennemuth A, Hope MD, Hsiao A, Johnson K, Kozerke S, Ma LE, Markl M, Martins D, Messina M, Oechtering TH, van Ooij P, Rigsby C, Rodriguez-Palomares J, Roest AAW, Roldán-Alzate A, Schnell S, Sotelo J, Stuber M, Syed AB, Töger J, van der Geest R, Westenberg J, Zhong L, Zhong Y, Wieben O, Dyverfeldt P. 4D Flow cardiovascular magnetic resonance consensus statement: 2023 update. J Cardiovasc Magn Reson 2023; 25:40. [PMID: 37474977 PMCID: PMC10357639 DOI: 10.1186/s12968-023-00942-z] [Citation(s) in RCA: 42] [Impact Index Per Article: 42.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Accepted: 05/30/2023] [Indexed: 07/22/2023] Open
Abstract
Hemodynamic assessment is an integral part of the diagnosis and management of cardiovascular disease. Four-dimensional cardiovascular magnetic resonance flow imaging (4D Flow CMR) allows comprehensive and accurate assessment of flow in a single acquisition. This consensus paper is an update from the 2015 '4D Flow CMR Consensus Statement'. We elaborate on 4D Flow CMR sequence options and imaging considerations. The document aims to assist centers starting out with 4D Flow CMR of the heart and great vessels with advice on acquisition parameters, post-processing workflows and integration into clinical practice. Furthermore, we define minimum quality assurance and validation standards for clinical centers. We also address the challenges faced in quality assurance and validation in the research setting. We also include a checklist for recommended publication standards, specifically for 4D Flow CMR. Finally, we discuss the current limitations and the future of 4D Flow CMR. This updated consensus paper will further facilitate widespread adoption of 4D Flow CMR in the clinical workflow across the globe and aid consistently high-quality publication standards.
Collapse
Affiliation(s)
- Malenka M Bissell
- Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine (LICAMM), LIGHT Laboratories, Clarendon Way, University of Leeds, Leeds, LS2 9NL, UK.
| | | | - Lamia Ait Ali
- Institute of Clinical Physiology CNR, Massa, Italy
- Foundation CNR Tuscany Region G. Monasterio, Massa, Italy
| | - Bradley D Allen
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
| | - Alex J Barker
- Department of Radiology, Children's Hospital Colorado, University of Colorado Anschutz Medical Center, Aurora, USA
| | - Ann Bolger
- Department of Medicine, University of California, San Francisco, CA, USA
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | - Nicholas Burris
- Department of Radiology, University of Michigan, Ann Arbor, USA
| | - Carl-Johan Carhäll
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | | | - Tino Ebbers
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | | | - Alex Frydrychowicz
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein, Campus Lübeck and Universität Zu Lübeck, Lübeck, Germany
| | - Pankaj Garg
- Norwich Medical School, University of East Anglia, Norwich, UK
| | - Julia Geiger
- Department of Diagnostic Imaging, University Children's Hospital, Zurich, Switzerland
- Children's Research Center, University Children's Hospital Zurich, Zurich, Switzerland
| | - Hojin Ha
- Department of Mechanical and Biomedical Engineering, Kangwon National University, Chuncheon, South Korea
| | - Anja Hennemuth
- Institute of Computer-Assisted Cardiovascular Medicine, Charité - Universitätsmedizin, Berlin, Germany
- German Center for Cardiovascular Research (DZHK), Partner Site, Berlin, Germany
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Michael D Hope
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA
| | - Albert Hsiao
- Department of Radiology, University of California, San Diego, CA, USA
| | - Kevin Johnson
- Departments of Radiology and Medical Physics, University of Wisconsin, Madison, WI, USA
| | - Sebastian Kozerke
- Institute for Biomedical Engineering, University and ETH Zurich, Zurich, Switzerland
| | - Liliana E Ma
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
| | - Michael Markl
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
| | - Duarte Martins
- Department of Pediatric Cardiology, Hospital de Santa Cruz, Centro Hospitalar Lisboa Ocidental, Lisbon, Portugal
| | - Marci Messina
- Department of Radiology, Northwestern Medicine, Chicago, IL, USA
| | - Thekla H Oechtering
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein, Campus Lübeck and Universität Zu Lübeck, Lübeck, Germany
- Departments of Radiology and Medical Physics, University of Wisconsin, Madison, WI, USA
| | - Pim van Ooij
- Department of Radiology & Nuclear Medicine, Amsterdam Cardiovascular Sciences, Amsterdam Movement Sciences, Amsterdam University Medical Centers, Location AMC, Amsterdam, The Netherlands
- Department of Pediatric Cardiology, Division of Pediatrics, Wilhelmina Children's Hospital, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Cynthia Rigsby
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
- Department of Medical Imaging, Ann & Robert H Lurie Children's Hospital of Chicago, Chicago, IL, USA
| | - Jose Rodriguez-Palomares
- Department of Cardiology, Hospital Universitari Vall d´Hebron,Vall d'Hebron Institut de Recerca (VHIR), Universitat Autònoma de Barcelona, Barcelona, Spain
- Centro de Investigación Biomédica en Red-CV, CIBER CV, Madrid, Spain
| | - Arno A W Roest
- Department of Pediatric Cardiology, Willem-Alexander's Children Hospital, Leiden University Medical Center and Center for Congenital Heart Defects Amsterdam-Leiden, Leiden, The Netherlands
| | | | - Susanne Schnell
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
- Department of Medical Physics, Institute of Physics, University of Greifswald, Greifswald, Germany
| | - Julio Sotelo
- School of Biomedical Engineering, Universidad de Valparaíso, Valparaíso, Chile
- Biomedical Imaging Center, Pontificia Universidad Catolica de Chile, Santiago, Chile
- Millennium Institute for Intelligent Healthcare Engineering - iHEALTH, Santiago, Chile
| | - Matthias Stuber
- Département de Radiologie Médicale, Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland
| | - Ali B Syed
- Department of Radiology, Stanford University, Stanford, CA, USA
| | - Johannes Töger
- Clinical Physiology, Department of Clinical Sciences Lund, Lund University, Skåne University Hospital, Lund, Sweden
| | - Rob van der Geest
- Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Jos Westenberg
- CardioVascular Imaging Group (CVIG), Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Liang Zhong
- National Heart Centre Singapore, Duke-NUS Medical School, National University of Singapore, Singapore, Singapore
| | - Yumin Zhong
- Department of Radiology, School of Medicine, Shanghai Children's Medical Center Affiliated With Shanghai Jiao Tong University, Shanghai, People's Republic of China
| | - Oliver Wieben
- Departments of Radiology and Medical Physics, University of Wisconsin, Madison, WI, USA
| | - Petter Dyverfeldt
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| |
Collapse
|
11
|
Ferdian E, Marlevi D, Schollenberger J, Aristova M, Edelman ER, Schnell S, Figueroa CA, Nordsletten DA, Young AA. Cerebrovascular super-resolution 4D Flow MRI - Sequential combination of resolution enhancement by deep learning and physics-informed image processing to non-invasively quantify intracranial velocity, flow, and relative pressure. Med Image Anal 2023; 88:102831. [PMID: 37244143 DOI: 10.1016/j.media.2023.102831] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2021] [Revised: 04/04/2023] [Accepted: 04/20/2023] [Indexed: 05/29/2023]
Abstract
The development of cerebrovascular disease is tightly coupled to regional changes in intracranial flow and relative pressure. Image-based assessment using phase contrast magnetic resonance imaging has particular promise for non-invasive full-field mapping of cerebrovascular hemodynamics. However, estimations are complicated by the narrow and tortuous intracranial vasculature, with accurate image-based quantification directly dependent on sufficient spatial resolution. Further, extended scan times are required for high-resolution acquisitions, and most clinical acquisitions are performed at comparably low resolution (>1 mm) where biases have been observed with regard to the quantification of both flow and relative pressure. The aim of our study was to develop an approach for quantitative intracranial super-resolution 4D Flow MRI, with effective resolution enhancement achieved by a dedicated deep residual network, and with accurate quantification of functional relative pressures achieved by subsequent physics-informed image processing. To achieve this, our two-step approach was trained and validated in a patient-specific in-silico cohort, showing good accuracy in estimating velocity (relative error: 15.0 ± 0.1%, mean absolute error (MAE): 0.07 ± 0.06 m/s, and cosine similarity: 0.99 ± 0.06 at peak velocity) and flow (relative error: 6.6 ± 4.7%, root mean square error (RMSE): 0.56 mL/s at peak flow), and with the coupled physics-informed image analysis allowing for maintained recovery of functional relative pressure throughout the circle of Willis (relative error: 11.0 ± 7.3%, RMSE: 0.3 ± 0.2 mmHg). Furthermore, the quantitative super-resolution approach is applied to an in-vivo volunteer cohort, effectively generating intracranial flow images at <0.5 mm resolution and showing reduced low-resolution bias in relative pressure estimation. Our work thus presents a promising two-step approach to non-invasively quantify cerebrovascular hemodynamics, being applicable to dedicated clinical cohorts in the future.
Collapse
Affiliation(s)
- E Ferdian
- University of Auckland, Auckland 1142 New Zealand
| | - D Marlevi
- Massachusetts Institute of Technology, Cambridge, MA 02139 USA
| | | | - M Aristova
- Northwestern University, Chicago, IL 60611, USA
| | - E R Edelman
- Massachusetts Institute of Technology, Cambridge, MA 02139 USA
| | - S Schnell
- Northwestern University, Chicago, IL 60611, USA; University of Greifswald, Greifswald 17489, Germany
| | - C A Figueroa
- University of Michigan, Ann Arbor, MI 48109, USA
| | - D A Nordsletten
- University of Michigan, Ann Arbor, MI 48109, USA; King's College London, London, SE1 7EH, UK
| | - A A Young
- University of Auckland, Auckland 1142 New Zealand; King's College London, London, SE1 7EH, UK
| |
Collapse
|
12
|
Tripura T, Awasthi A, Roy S, Chakraborty S. A wavelet neural operator based elastography for localization and quantification of tumors. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 232:107436. [PMID: 36870167 DOI: 10.1016/j.cmpb.2023.107436] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/07/2022] [Revised: 01/19/2023] [Accepted: 02/18/2023] [Indexed: 06/18/2023]
Abstract
BACKGROUND AND OBJECTIVES The application of intelligent imaging techniques and deep learning in the field of computer-aided diagnosis and medical imaging have improved and accelerated the early diagnosis of many diseases. Elastography is an imaging modality where an inverse problem is solved to extract the elastic properties of tissues and subsequently mapped to anatomical images for diagnostic purposes. In the present work, we propose a wavelet neural operator-based approach for correctly learning the non-linear mapping of elastic properties directly from measured displacement field data. METHODS The proposed framework learns the underlying operator behind the elastic mapping and thus can map any displacement data from a family to the elastic properties. The displacement fields are first uplifted to a high-dimensional space using a fully connected neural network. On the lifted data, certain iterations are performed using wavelet neural blocks. In each wavelet neural block, the lifted data are decomposed into low, and high-frequency components using wavelet decomposition. To learn the most relevant patterns and structural information from the input, the neural network kernels are directly convoluted with the outputs of the wavelet decomposition. Thereafter the elasticity field is reconstructed from the outputs from convolution. The mapping between the displacement and the elasticity using wavelets is unique and remains stable during training. RESULTS The proposed framework is tested on several artificially fabricated numerical examples, including a benign-cum-malignant tumor prediction problem. The trained model was also tested on real Ultrasound-based elastography data to demonstrate the applicability of the proposed scheme in clinical usage. The proposed framework reproduces the highly accurate elasticity field directly from the displacement inputs. CONCLUSIONS The proposed framework circumvents different data pre-processing and intermediate steps utilized in traditional methods, hence providing an accurate elasticity map. The computationally efficient framework requires fewer epochs for training, which bodes well for its clinical usability for real-time predictions. The weights and biases from pre-trained models can also be employed for transfer learning, which reduces the effective training time with random initialization.
Collapse
Affiliation(s)
- Tapas Tripura
- Department of Applied Mechanics, Indian Institute of Technology Delhi, Hauz Khas, Delhi, 110016, India.
| | - Abhilash Awasthi
- Department of Applied Mechanics, Indian Institute of Technology Delhi, Hauz Khas, Delhi, 110016, India.
| | - Sitikantha Roy
- Department of Applied Mechanics, Indian Institute of Technology Delhi, Hauz Khas, Delhi, 110016, India; Yardi School of Artificial Intelligence (ScAI), Indian Institute of Technology Delhi, Hauz Khas, Delhi, 110016, India.
| | - Souvik Chakraborty
- Department of Applied Mechanics, Indian Institute of Technology Delhi, Hauz Khas, Delhi, 110016, India; Yardi School of Artificial Intelligence (ScAI), Indian Institute of Technology Delhi, Hauz Khas, Delhi, 110016, India.
| |
Collapse
|
13
|
Chen Z, Pawar K, Ekanayake M, Pain C, Zhong S, Egan GF. Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges. J Digit Imaging 2023; 36:204-230. [PMID: 36323914 PMCID: PMC9984670 DOI: 10.1007/s10278-022-00721-9] [Citation(s) in RCA: 18] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Revised: 09/09/2022] [Accepted: 10/17/2022] [Indexed: 11/06/2022] Open
Abstract
Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.
Collapse
Affiliation(s)
- Zhaolin Chen
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia.
- Department of Data Science and AI, Monash University, Melbourne, VIC, Australia.
| | - Kamlesh Pawar
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
| | - Mevan Ekanayake
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, VIC, Australia
| | - Cameron Pain
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, VIC, Australia
| | - Shenjun Zhong
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- National Imaging Facility, Brisbane, QLD, Australia
| | - Gary F Egan
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- Turner Institute for Brain and Mental Health, Monash University, Melbourne, VIC, Australia
| |
Collapse
|
14
|
Kim D, Jen ML, Eisenmenger LB, Johnson KM. Accelerated 4D-flow MRI with 3-point encoding enabled by machine learning. Magn Reson Med 2023; 89:800-811. [PMID: 36198027 PMCID: PMC9712238 DOI: 10.1002/mrm.29469] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2022] [Revised: 08/22/2022] [Accepted: 09/06/2022] [Indexed: 01/25/2023]
Abstract
PURPOSE To investigate the acceleration of 4D-flow MRI using a convolutional neural network (CNN) that produces three directional velocities from three flow encodings, without requiring a fourth reference scan measuring background phase. METHODS A fully 3D CNN using a U-net architecture was trained in a block-wise fashion to take complex images from three flow encodings and to produce three real-valued images for each velocity component. Using neurovascular 4D-flow scans (n = 144), the CNN was trained to predict velocities computed from four flow encodings by standard reconstruction including correction for residual background phase offsets. Methods to optimize loss functions were investigated, including magnitude, complex difference, and uniform velocity weightings. Subsequently, 3-point encoding was evaluated using cross validation of pixelwise correlation, flow measurements in major arteries, and in experiments with data at differing acceleration rates than the training data. RESULTS The CNN-produced 3-point velocities showed excellent agreements with the 4-point velocities, both qualitatively in velocity images, in flow rate measures, and quantitatively in regression analysis (slope = 0.96, R2 = 0.992). Optimizing the training to focus on vessel velocities rather than the global velocity error and improved the correlation of velocity within vessels themselves. The lowest error was observed when the loss function used uniform velocity weighting, in which the magnitude-weighted inverse of the velocity frequency uniformly distributed weighting across all velocity ranges. When applied to highly accelerated data, the 3-point network maintained a high correlation with ground truth data and demonstrated a denoising effect. CONCLUSION The 4D-flow MRI can be accelerated using machine learning requiring only three flow encodings to produce three-directional velocity maps with small errors.
Collapse
Affiliation(s)
- Dahan Kim
- Department of Physics, University of Wisconsin, Madison, Wisconsin, USA,Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
| | - Mu-Lan Jen
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
| | - Laura B. Eisenmenger
- Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
| | - Kevin M. Johnson
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA,Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
| |
Collapse
|
15
|
Moradi H, Al-Hourani A, Concilia G, Khoshmanesh F, Nezami FR, Needham S, Baratchi S, Khoshmanesh K. Recent developments in modeling, imaging, and monitoring of cardiovascular diseases using machine learning. Biophys Rev 2023; 15:19-33. [PMID: 36909958 PMCID: PMC9995635 DOI: 10.1007/s12551-022-01040-7] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2022] [Accepted: 12/21/2022] [Indexed: 01/12/2023] Open
Abstract
Cardiovascular diseases are the leading cause of mortality, morbidity, and hospitalization around the world. Recent technological advances have facilitated analyzing, visualizing, and monitoring cardiovascular diseases using emerging computational fluid dynamics, blood flow imaging, and wearable sensing technologies. Yet, computational cost, limited spatiotemporal resolution, and obstacles for thorough data analysis have hindered the utility of such techniques to curb cardiovascular diseases. We herein discuss how leveraging machine learning techniques, and in particular deep learning methods, could overcome these limitations and offer promise for translation. We discuss the remarkable capacity of recently developed machine learning techniques to accelerate flow modeling, enhance the resolution while reduce the noise and scanning time of current blood flow imaging techniques, and accurate detection of cardiovascular diseases using a plethora of data collected by wearable sensors.
Collapse
Affiliation(s)
- Hamed Moradi
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
| | - Akram Al-Hourani
- School of Engineering, RMIT University, Melbourne, Victoria Australia
| | | | - Farnaz Khoshmanesh
- School of Allied Health, Human Services & Sport, La Trobe University, Melbourne, Victoria Australia
| | - Farhad R. Nezami
- Division of Thoracic and Cardiac Surgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA USA
| | - Scott Needham
- Leading Technology Group, Melbourne, Victoria Australia
| | - Sara Baratchi
- School of Health and Biomedical Sciences, RMIT University, Melbourne, Victoria Australia
| | | |
Collapse
|
16
|
Thewlis J, Stevens D, Power H, Giddings D, Gowland P, Vloeberghs M. 4-dimensional local radial basis function interpolation of large, uniformly spaced datasets. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 228:107235. [PMID: 36413829 DOI: 10.1016/j.cmpb.2022.107235] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Revised: 10/30/2022] [Accepted: 11/05/2022] [Indexed: 06/16/2023]
Abstract
BACKGROUND AND OBJECTIVE Large, uniformly spaced, complex and time varying datasets derived from high resolution medical image velocimetry can provide a wealth of information regarding small-scale transient physiological flow phenomena and pulsation of anatomical boundaries. However, there remains a need for interpolation techniques to effectively reconstruct a fully 4-dimensional functional relationship from this data. This paper presents a preliminary evaluation of a 4-dimensional local radial basis function (RBF) algorithm as a means of addressing this problem for laminar flows. METHODS A 4D interpolation algorithm is proposed based on a Local Hermitian Interpolation (LHI) using a combination of multi-quadric RBF with a partition of unity scheme. The domain is divided into uniform sub-systems with size restricted to immediately neighbouring points. The validity of the algorithm is first established on a known 4D analytical dataset and a CFD based laminar flow phantom. Application is then demonstrated through characterisation of a large 4D laminar flow dataset obtained from magnetic resonance imaging (MRI) measurements of cerebrospinal fluid velocities in the brain. RESULTS Performance of the algorithm is compared to that of a quad-linear interpolation, demonstrating favourable improvement in accuracy. The technique is shown to be robust, computationally efficient and capable of refined interpolation in Euclidean space and time. Application to MR velocimetry data is shown to produce promising results for the 4D reconstruction of the transient flow field and movement of the fluid boundaries at spatial and temporal locations intermediate to the original data. CONCLUSION This study has demonstrated feasibility of an accurate, stable and efficient 4-dimensional local RBF interpolation method for large, transient laminar flow velocimetry datasets. The proposed approach does not suffer from ill-conditioning or high computational cost due to domain decomposition into local stencils where the RBF is only ever applied to a limited number of points. This work offers a potential tool to assist medical diagnoses and drug delivery through better understanding of physiological flow fields such as cerebrospinal fluid. Further work will evaluate the technique on a wider range of flow fields and against CFD simulation.
Collapse
Affiliation(s)
- J Thewlis
- c/o Rolls-Royce plc, Registered office: Kings Place, 3rd Floor 90 York Way, London N19FX, England
| | - D Stevens
- Department of Geography, Geography and Planning Building, Winter Street, Sheffield S37ND, England
| | - H Power
- Deceased, was formerly of University of Nottingham, Faculty of Engineering, United Kingdom
| | - D Giddings
- Fluids and Thermal Engineering Research Group, Faculty of Engineering, University of Nottingham, Nottingham NG72RD, United Kingdom.
| | - P Gowland
- Sir Peter Mansfield Imaging Centre, University Park, Nottingham NG72RD, United Kingdom
| | - M Vloeberghs
- Nottingham University Hospitals NHS Trust - Queen's Medical Centre Campus, Derby Road, Nottingham, Nottinghamshire NG72UH, United Kingdom
| |
Collapse
|
17
|
Peper ES, van Ooij P, Jung B, Huber A, Gräni C, Bastiaansen JAM. Advances in machine learning applications for cardiovascular 4D flow MRI. Front Cardiovasc Med 2022; 9:1052068. [PMID: 36568555 PMCID: PMC9780299 DOI: 10.3389/fcvm.2022.1052068] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Accepted: 11/22/2022] [Indexed: 12/13/2022] Open
Abstract
Four-dimensional flow magnetic resonance imaging (MRI) has evolved as a non-invasive imaging technique to visualize and quantify blood flow in the heart and vessels. Hemodynamic parameters derived from 4D flow MRI, such as net flow and peak velocities, but also kinetic energy, turbulent kinetic energy, viscous energy loss, and wall shear stress have shown to be of diagnostic relevance for cardiovascular diseases. 4D flow MRI, however, has several limitations. Its long acquisition times and its limited spatio-temporal resolutions lead to inaccuracies in velocity measurements in small and low-flow vessels and near the vessel wall. Additionally, 4D flow MRI requires long post-processing times, since inaccuracies due to the measurement process need to be corrected for and parameter quantification requires 2D and 3D contour drawing. Several machine learning (ML) techniques have been proposed to overcome these limitations. Existing scan acceleration methods have been extended using ML for image reconstruction and ML based super-resolution methods have been used to assimilate high-resolution computational fluid dynamic simulations and 4D flow MRI, which leads to more realistic velocity results. ML efforts have also focused on the automation of other post-processing steps, by learning phase corrections and anti-aliasing. To automate contour drawing and 3D segmentation, networks such as the U-Net have been widely applied. This review summarizes the latest ML advances in 4D flow MRI with a focus on technical aspects and applications. It is divided into the current status of fast and accurate 4D flow MRI data generation, ML based post-processing tools for phase correction and vessel delineation and the statistical evaluation of blood flow.
Collapse
Affiliation(s)
- Eva S. Peper
- Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland,Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Bern, Switzerland,*Correspondence: Eva S. Peper,
| | - Pim van Ooij
- Department of Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Amsterdam, Netherlands,Department of Pediatric Cardiology, Wilhelmina Children’s Hospital, University Medical Center Utrecht, Utrecht, Netherlands
| | - Bernd Jung
- Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland,Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Bern, Switzerland
| | - Adrian Huber
- Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Christoph Gräni
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Jessica A. M. Bastiaansen
- Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland,Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Bern, Switzerland
| |
Collapse
|
18
|
Investigating molecular transport in the human brain from MRI with physics-informed neural networks. Sci Rep 2022; 12:15475. [PMID: 36104360 PMCID: PMC9474534 DOI: 10.1038/s41598-022-19157-w] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Accepted: 08/24/2022] [Indexed: 11/23/2022] Open
Abstract
In recent years, a plethora of methods combining neural networks and partial differential equations have been developed. A widely known example are physics-informed neural networks, which solve problems involving partial differential equations by training a neural network. We apply physics-informed neural networks and the finite element method to estimate the diffusion coefficient governing the long term spread of molecules in the human brain from magnetic resonance images. Synthetic testcases are created to demonstrate that the standard formulation of the physics-informed neural network faces challenges with noisy measurements in our application. Our numerical results demonstrate that the residual of the partial differential equation after training needs to be small for accurate parameter recovery. To achieve this, we tune the weights and the norms used in the loss function and use residual based adaptive refinement of training points. We find that the diffusion coefficient estimated from magnetic resonance images with physics-informed neural networks becomes consistent with results from a finite element based approach when the residuum after training becomes small. The observations presented here are an important first step towards solving inverse problems on cohorts of patients in a semi-automated fashion with physics-informed neural networks.
Collapse
|
19
|
Sarabian M, Babaee H, Laksari K. Physics-Informed Neural Networks for Brain Hemodynamic Predictions Using Medical Imaging. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:2285-2303. [PMID: 35320090 PMCID: PMC9437127 DOI: 10.1109/tmi.2022.3161653] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Determining brain hemodynamics plays a critical role in the diagnosis and treatment of various cerebrovascular diseases. In this work, we put forth a physics-informed deep learning framework that augments sparse clinical measurements with one-dimensional (1D) reduced-order model (ROM) simulations to generate physically consistent brain hemodynamic parameters with high spatiotemporal resolution. Transcranial Doppler (TCD) ultrasound is one of the most common techniques in the current clinical workflow that enables noninvasive and instantaneous evaluation of blood flow velocity within the cerebral arteries. However, it is spatially limited to only a handful of locations across the cerebrovasculature due to the constrained accessibility through the skull's acoustic windows. Our deep learning framework uses in vivo real-time TCD velocity measurements at several locations in the brain combined with baseline vessel cross-sectional areas acquired from 3D angiography images and provides high-resolution maps of velocity, area, and pressure in the entire brain vasculature. We validate the predictions of our model against in vivo velocity measurements obtained via four-dimensional (4D) flow magnetic resonance imaging (MRI) scans. We then showcase the clinical significance of this technique in diagnosing cerebral vasospasm (CVS) by successfully predicting the changes in vasospastic local vessel diameters based on corresponding sparse velocity measurements. We show this capability by generating synthetic blood flow data after cerebral vasospasm at various levels of stenosis. Here, we demonstrate that the physics-based deep learning approach can estimate and quantify the subject-specific cerebral hemodynamic variables with high accuracy despite lacking knowledge of inlet and outlet boundary conditions, which is a significant limitation for the accuracy of the conventional purely physics-based computational models.
Collapse
|
20
|
Shit S, Zimmermann J, Ezhov I, Paetzold JC, Sanches AF, Pirkl C, Menze BH. SRflow: Deep learning based super-resolution of 4D-flow MRI data. Front Artif Intell 2022; 5:928181. [PMID: 36034591 PMCID: PMC9411720 DOI: 10.3389/frai.2022.928181] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 07/11/2022] [Indexed: 11/13/2022] Open
Abstract
Exploiting 4D-flow magnetic resonance imaging (MRI) data to quantify hemodynamics requires an adequate spatio-temporal vector field resolution at a low noise level. To address this challenge, we provide a learned solution to super-resolve in vivo 4D-flow MRI data at a post-processing level. We propose a deep convolutional neural network (CNN) that learns the inter-scale relationship of the velocity vector map and leverages an efficient residual learning scheme to make it computationally feasible. A novel, direction-sensitive, and robust loss function is crucial to learning vector-field data. We present a detailed comparative study between the proposed super-resolution and the conventional cubic B-spline based vector-field super-resolution. Our method improves the peak-velocity to noise ratio of the flow field by 10 and 30% for in vivo cardiovascular and cerebrovascular data, respectively, for 4 × super-resolution over the state-of-the-art cubic B-spline. Significantly, our method offers 10x faster inference over the cubic B-spline. The proposed approach for super-resolution of 4D-flow data would potentially improve the subsequent calculation of hemodynamic quantities.
Collapse
Affiliation(s)
- Suprosanna Shit
- Department of Informatics, Technical University of Munich, Munich, Germany
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
- *Correspondence: Suprosanna Shit
| | - Judith Zimmermann
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Ivan Ezhov
- Department of Informatics, Technical University of Munich, Munich, Germany
| | | | - Augusto F. Sanches
- Institute of Neuroradiology, University Hospital LMU Munich, Munich, Germany
| | - Carolin Pirkl
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Bjoern H. Menze
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| |
Collapse
|
21
|
Nolte D, Bertoglio C. Inverse problems in blood flow modeling: A review. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2022; 38:e3613. [PMID: 35526113 PMCID: PMC9541505 DOI: 10.1002/cnm.3613] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/17/2021] [Revised: 12/29/2021] [Accepted: 03/18/2022] [Indexed: 06/14/2023]
Abstract
Mathematical and computational modeling of the cardiovascular system is increasingly providing non-invasive alternatives to traditional invasive clinical procedures. Moreover, it has the potential for generating additional diagnostic markers. In blood flow computations, the personalization of spatially distributed (i.e., 3D) models is a key step which relies on the formulation and numerical solution of inverse problems using clinical data, typically medical images for measuring both anatomy and function of the vasculature. In the last years, the development and application of inverse methods has rapidly expanded most likely due to the increased availability of data in clinical centers and the growing interest of modelers and clinicians in collaborating. Therefore, this work aims to provide a wide and comparative overview of literature within the last decade. We review the current state of the art of inverse problems in blood flows, focusing on studies considering fully dimensional fluid and fluid-solid models. The relevant physical models and hemodynamic measurement techniques are introduced, followed by a survey of mathematical data assimilation approaches used to solve different kinds of inverse problems, namely state and parameter estimation. An exhaustive discussion of the literature of the last decade is presented, structured by types of problems, models and available data.
Collapse
Affiliation(s)
- David Nolte
- Bernoulli InstituteUniversity of GroningenGroningenThe Netherlands
- Center for Mathematical ModelingUniversidad de ChileSantiagoChile
- Department of Fluid DynamicsTechnische Universität BerlinBerlinGermany
| | | |
Collapse
|
22
|
Shahid L, Rice J, Berhane H, Rigsby C, Robinson J, Griffin L, Markl M, Roldán-Alzate A. Enhanced 4D Flow MRI-Based CFD with Adaptive Mesh Refinement for Flow Dynamics Assessment in Coarctation of the Aorta. Ann Biomed Eng 2022; 50:1001-1016. [PMID: 35624334 PMCID: PMC11034844 DOI: 10.1007/s10439-022-02980-7] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2021] [Accepted: 05/11/2022] [Indexed: 01/28/2023]
Abstract
4D Flow MRI is a diagnostic tool that can visualize and quantify patient-specific hemodynamics and help interventionalists optimize treatment strategies for repairing coarctation of the aorta (COA). Despite recent developments in 4D Flow MRI, shortcomings include phase-offset errors, limited spatiotemporal resolution, aliasing, inaccuracies due to slow aneurysmal flows, and distortion of images due to metallic artifact from vascular stents. To address these limitations, we developed a framework utilizing Computational Fluid Dynamics (CFD) with Adaptive Mesh Refinement (AMR) that enhances 4D Flow MRI visualization/quantification. We applied this framework to five pediatric patients with COA, providing in-vivo and in-silico datasets, pre- and post-intervention. These two data sets were compared and showed that CFD flow rates were within 9.6% of 4D Flow MRI, which is within a clinically acceptable range. CFD simulated slow aneurysmal flow, which MRI failed to capture due to high relative velocity encoding (Venc). CFD successfully predicted in-stent blood flow, which was not visible in the in-vivo data due to susceptibility artifact. AMR improved spatial resolution by factors of 101 to 103 and temporal resolution four-fold. This computational framework has strong potential to optimize visualization/quantification of aneurysmal and in-stent flows, improve spatiotemporal resolution, and assess hemodynamic efficiency post-COA treatment.
Collapse
Affiliation(s)
- Labib Shahid
- Department of Mechanical Engineering, University of Wisconsin-Madison, 1111 Highland Ave, Room 2476 WIMR II, Madison, WI, 53705, USA.
| | - James Rice
- Department of Mechanical Engineering, University of Wisconsin-Madison, 1111 Highland Ave, Room 2476 WIMR II, Madison, WI, 53705, USA
| | - Haben Berhane
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
- Department of Biomedical Engineering, McCormick School of Engineering, Northwestern University, Evanston, IL, USA
| | - Cynthia Rigsby
- Department of Medical Imaging, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, IL, USA
| | - Joshua Robinson
- Department of Medical Imaging, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, IL, USA
| | - Lindsay Griffin
- Department of Medical Imaging, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, IL, USA
| | - Michael Markl
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
- Department of Biomedical Engineering, McCormick School of Engineering, Northwestern University, Evanston, IL, USA
| | - Alejandro Roldán-Alzate
- Department of Mechanical Engineering, University of Wisconsin-Madison, 1111 Highland Ave, Room 2476 WIMR II, Madison, WI, 53705, USA
- Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, USA
- Department of Radiology, University of Wisconsin-Madison, Madison, WI, USA
| |
Collapse
|
23
|
Zhu LT, Chen XZ, Ouyang B, Yan WC, Lei H, Chen Z, Luo ZH. Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors. Ind Eng Chem Res 2022. [DOI: 10.1021/acs.iecr.2c01036] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Affiliation(s)
- Li-Tao Zhu
- Department of Chemical Engineering, School of Chemistry and Chemical Engineering, State Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China
| | - Xi-Zhong Chen
- Department of Chemical and Biological Engineering, University of Sheffield, Sheffield, S1 3JD, U.K
| | - Bo Ouyang
- Department of Chemical Engineering, School of Chemistry and Chemical Engineering, State Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China
| | - Wei-Cheng Yan
- School of Chemistry and Chemical Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China
| | - He Lei
- Department of Chemical Engineering, School of Chemistry and Chemical Engineering, State Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China
| | - Zhe Chen
- Department of Chemical Engineering, School of Chemistry and Chemical Engineering, State Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China
| | - Zheng-Hong Luo
- Department of Chemical Engineering, School of Chemistry and Chemical Engineering, State Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China
| |
Collapse
|
24
|
Machine Learning for Cardiovascular Biomechanics Modeling: Challenges and Beyond. Ann Biomed Eng 2022; 50:615-627. [PMID: 35445297 DOI: 10.1007/s10439-022-02967-4] [Citation(s) in RCA: 21] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 04/07/2022] [Indexed: 12/13/2022]
Abstract
Recent progress in machine learning (ML), together with advanced computational power, have provided new research opportunities in cardiovascular modeling. While classifying patient outcomes and medical image segmentation with ML have already shown significant promising results, ML for the prediction of biomechanics such as blood flow or tissue dynamics is in its infancy. This perspective article discusses some of the challenges in using ML for replacing well-established physics-based models in cardiovascular biomechanics. Specifically, we discuss the large landscape of input features in 3D patient-specific modeling as well as the high-dimensional output space of field variables that vary in space and time. We argue that the end purpose of such ML models needs to be clearly defined and the tradeoff between the loss in accuracy and the gained speedup carefully interpreted in the context of translational modeling. We also discuss several exciting venues where ML could be strategically used to augment traditional physics-based modeling in cardiovascular biomechanics. In these applications, ML is not replacing physics-based modeling, but providing opportunities to solve ill-defined problems, improve measurement data quality, enable a solution to computationally expensive problems, and interpret complex spatiotemporal data by extracting hidden patterns. In summary, we suggest a strategic integration of ML in cardiovascular biomechanics modeling where the ML model is not the end goal but rather a tool to facilitate enhanced modeling.
Collapse
|
25
|
Zhang J, Brindise MC, Rothenberger SM, Markl M, Rayz VL, Vlachos PP. A multi-modality approach for enhancing 4D flow magnetic resonance imaging via sparse representation. J R Soc Interface 2022; 19:20210751. [PMID: 35042385 PMCID: PMC8767185 DOI: 10.1098/rsif.2021.0751] [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: 01/21/2023] Open
Abstract
This work evaluates and applies a multi-modality approach to enhance blood flow measurements and haemodynamic analysis with phase-contrast magnetic resonance imaging (4D flow MRI) in cerebral aneurysms (CAs). Using a library of high-resolution velocity fields from patient-specific computational fluid dynamic simulations and in vitro particle tracking velocimetry measurements, the flow field of 4D flow MRI data is reconstructed as the sparse representation of the library. The method was evaluated with synthetic 4D flow MRI data in two CAs. The reconstruction enhanced the spatial resolution and velocity accuracy of the synthetic MRI data, leading to reliable pressure and wall shear stress (WSS) evaluation. The method was applied on in vivo 4D flow MRI data acquired in the same CAs. The reconstruction increased the velocity and WSS by 6-13% and 39-61%, respectively, suggesting that the accuracy of these quantities was improved since the raw MRI data underestimated the velocity and WSS by 10-20% and 40-50%, respectively. The computed pressure fields from the reconstructed data were consistent with the observed flow structures. The results suggest that using the sparse representation flow reconstruction with in vivo 4D flow MRI enhances blood flow measurement and haemodynamic analysis.
Collapse
Affiliation(s)
- Jiacheng Zhang
- School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907 USA
| | - Melissa C. Brindise
- School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907 USA
| | - Sean M. Rothenberger
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN 47907 USA
| | - Michael Markl
- Feinberg School of Medicine, Northwestern University, Chicago, IL 60611, USA,McCormick School of Engineering, Northwestern University, Evanston, IL 60208, USA
| | - Vitaliy L. Rayz
- School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907 USA,Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN 47907 USA
| | - Pavlos P. Vlachos
- School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907 USA,Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN 47907 USA
| |
Collapse
|
26
|
Trenti C, Dyverfeldt P. Editorial for "Segmentation of the Aorta and Pulmonary Arteries Based on 4D Flow MRI in the Pediatric Setting Using Fully Automated Multi-Site, Multi-Vendor, and Multi-Label Dense U-Net". J Magn Reson Imaging 2021; 55:1681-1682. [PMID: 34816520 DOI: 10.1002/jmri.28005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2021] [Accepted: 11/12/2021] [Indexed: 11/09/2022] Open
Affiliation(s)
- Chiara Trenti
- Unit of Cardiovascular Sciences, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden.,Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | - Petter Dyverfeldt
- Unit of Cardiovascular Sciences, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden.,Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| |
Collapse
|
27
|
Song Z, Zhao X, Hui Y, Jiang H. Progressive back-projection network for COVID-CT super-resolution. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 208:106193. [PMID: 34107373 PMCID: PMC8142806 DOI: 10.1016/j.cmpb.2021.106193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/28/2020] [Accepted: 05/14/2021] [Indexed: 05/09/2023]
Abstract
BACKGROUND AND OBJECTIVE Recently, the COVID-19 epidemic has become more and more serious around the world, how to improve the image resolution of COVID-CT is a very important task. The network based on progressive upsampling for COVID-CT super-resolution increases the reconstruction error. This paper proposes a progressive back-projection network (PBPN) for COVID-CT super-resolution to solve this problem. METHODS In this paper, we propose a progressive back-projection network (PBPN) for COVID-CT super-resolution. PBPN is divided into two stages, and each stage consists of back-projection, deep feature extraction and upscaling. We design an up-projection and down-projection residual module to minimize the reconstruction error and construct a residual attention module to extract deep features. In each stage, firstly, PBPN performs back-projection to extract shallow features by two up-projection and down-projection residual modules; then, PBPN extracts deep features from the shallow features by two residual attention modules; finally, PBPN upsamples the deep features through sub-pixel convolution. RESULTS The proposed method achieves the improvements of about 0.14~0.47 dB/0.0012~0.0060 for × 2 scale factor, 0.02~0.08 dB/0.0024~0.0059 for × 3 scale factor, and 0.08~0.41 dB/ 0.0040~0.0147 for × 4 scale factor than state-of-the-art methods (Bicubic, SRCNN, FSRCNN, VDSR, LapSRN, DRCN and DSRN) in terms of PSNR/SSIM on benchmark datasets. CONCLUSIONS The proposed mehtod obtains better performance for COVID-CT super-resolution and reconstructs high-quality high-resolution COVID-CT images that contain more details and edges.
Collapse
Affiliation(s)
- Zhaoyang Song
- College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China.
| | - Xiaoqiang Zhao
- College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, China; National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China.
| | - Yongyong Hui
- College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, China; National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China.
| | - Hongmei Jiang
- College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, China; National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China.
| |
Collapse
|
28
|
Integrating multi-fidelity blood flow data with reduced-order data assimilation. Comput Biol Med 2021; 135:104566. [PMID: 34157468 DOI: 10.1016/j.compbiomed.2021.104566] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2021] [Revised: 05/30/2021] [Accepted: 06/08/2021] [Indexed: 11/20/2022]
Abstract
High-fidelity patient-specific modeling of cardiovascular flows and hemodynamics is challenging. Direct blood flow measurement inside the body with in-vivo measurement modalities such as 4D flow magnetic resonance imaging (4D flow MRI) suffer from low resolution and acquisition noise. In-vitro experimental modeling and patient-specific computational fluid dynamics (CFD) models are subject to uncertainty in patient-specific boundary conditions and model parameters. Furthermore, collecting blood flow data in the near-wall region (e.g., wall shear stress) with experimental measurement modalities poses additional challenges. In this study, a computationally efficient data assimilation method called reduced-order modeling Kalman filter (ROM-KF) was proposed, which combined a sequential Kalman filter with reduced-order modeling using a linear model provided by dynamic mode decomposition (DMD). The goal of ROM-KF was to overcome low resolution and noise in experimental and uncertainty in CFD modeling of cardiovascular flows. The accuracy of the method was assessed with 1D Womersley flow, 2D idealized aneurysm, and 3D patient-specific cerebral aneurysm models. Synthetic experimental data were used to enable direct quantification of errors using benchmark datasets. The accuracy of ROM-KF in reconstructing near-wall hemodynamics was assessed by applying the method to problems where near-wall blood flow data were missing in the experimental dataset. The ROM-KF method provided blood flow data that were more accurate than the computational and synthetic experimental datasets and improved near-wall hemodynamics quantification.
Collapse
|
29
|
Blood Flow Quantification in Peripheral Arterial Disease: Emerging Diagnostic Techniques in Vascular Surgery. Surg Technol Int 2021. [PMID: 33970476 DOI: 10.52198/21.sti.38.cv1410] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
The assessment of local blood flow patterns in patients with peripheral arterial disease is clinically relevant, since these patterns are related to atherosclerotic disease progression and loss of patency in stents placed in peripheral arteries, through mechanisms such as recirculating flow and low wall shear stress (WSS). However, imaging of vascular flow in these patients is technically challenging due to the often complex flow patterns that occur near atherosclerotic lesions. While several flow quantification techniques have been developed that could improve the outcomes of vascular interventions, accurate 2D or 3D blood flow quantification is not yet used in clinical practice. This article provides an overview of several important topics that concern the quantification of blood flow in patients with peripheral arterial disease. The hemodynamic mechanisms involved in the development of atherosclerosis and the current clinical practice in the diagnosis of this disease are discussed, showing the unmet need for improved and validated flow quantification techniques in daily clinical practice. This discussion is followed by a showcase of state-of-the-art blood flow quantification techniques and how these could be used before, during and after treatment of stenotic lesions to improve clinical outcomes. These techniques include novel ultrasound-based methods, Phase-Contrast Magnetic Resonance Imaging (PC-MRI) and Computational Fluid Dynamics (CFD). The last section discusses future perspectives, with advanced (hybrid) imaging techniques and artificial intelligence, including the implementation of these techniques in clinical practice.
Collapse
|
30
|
Engelhard S, van de Velde L, Jebbink E, Jain K, Westenberg J, Zeebregts C, Versluis M, Reijnen M. Blood Flow Quantification in Peripheral Arterial Disease: Emerging Diagnostic Techniques in Vascular Surgery. Surg Technol Int 2021. [DOI: https:/doi.org/10.52198/21.sti.38.cv1410] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2023]
Abstract
The assessment of local blood flow patterns in patients with peripheral arterial disease is clinically relevant, since these patterns are related to atherosclerotic disease progression and loss of patency in stents placed in peripheral arteries, through mechanisms such as recirculating flow and low wall shear stress (WSS). However, imaging of vascular flow in these patients is technically challenging due to the often complex flow patterns that occur near atherosclerotic lesions. While several flow quantification techniques have been developed that could improve the outcomes of vascular interventions, accurate 2D or 3D blood flow quantification is not yet used in clinical practice. This article provides an overview of several important topics that concern the quantification of blood flow in patients with peripheral arterial disease. The hemodynamic mechanisms involved in the development of atherosclerosis and the current clinical practice in the diagnosis of this disease are discussed, showing the unmet need for improved and validated flow quantification techniques in daily clinical practice. This discussion is followed by a showcase of state-of-the-art blood flow quantification techniques and how these could be used before, during and after treatment of stenotic lesions to improve clinical outcomes. These techniques include novel ultrasound-based methods, Phase-Contrast Magnetic Resonance Imaging (PC-MRI) and Computational Fluid Dynamics (CFD). The last section discusses future perspectives, with advanced (hybrid) imaging techniques and artificial intelligence, including the implementation of these techniques in clinical practice.
Collapse
Affiliation(s)
- Stefan Engelhard
- Department of Vascular Surgery, Rijnstate, Arnhem, The Netherlands
| | | | - Erik Jebbink
- Department of Vascular Surgery, Rijnstate, Arnhem, The Netherlands
| | - Kartik Jain
- Department of Thermal and Fluid Engineering, University of Twente, Enschede, The Netherlands
| | - Jos Westenberg
- Department of Radiology, Cardiovascular Imaging Group, Leiden University Medical Center, Leiden, The Netherlands
| | - Clark Zeebregts
- Department of Surgery (Division of Vascular Surgery), University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Michel Versluis
- Physics of Fluids Group, Technical Medical (TechMed) Centre, University of Twente, Enschede, The Netherlands
| | - Michel Reijnen
- Department of Vascular Surgery, Rijnstate, Arnhem, The Netherlands
| |
Collapse
|
31
|
Arzani A, Dawson STM. Data-driven cardiovascular flow modelling: examples and opportunities. J R Soc Interface 2021; 18:20200802. [PMID: 33561376 PMCID: PMC8086862 DOI: 10.1098/rsif.2020.0802] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2020] [Accepted: 01/18/2021] [Indexed: 12/14/2022] Open
Abstract
High-fidelity blood flow modelling is crucial for enhancing our understanding of cardiovascular disease. Despite significant advances in computational and experimental characterization of blood flow, the knowledge that we can acquire from such investigations remains limited by the presence of uncertainty in parameters, low resolution, and measurement noise. Additionally, extracting useful information from these datasets is challenging. Data-driven modelling techniques have the potential to overcome these challenges and transform cardiovascular flow modelling. Here, we review several data-driven modelling techniques, highlight the common ideas and principles that emerge across numerous such techniques, and provide illustrative examples of how they could be used in the context of cardiovascular fluid mechanics. In particular, we discuss principal component analysis (PCA), robust PCA, compressed sensing, the Kalman filter for data assimilation, low-rank data recovery, and several additional methods for reduced-order modelling of cardiovascular flows, including the dynamic mode decomposition and the sparse identification of nonlinear dynamics. All techniques are presented in the context of cardiovascular flows with simple examples. These data-driven modelling techniques have the potential to transform computational and experimental cardiovascular research, and we discuss challenges and opportunities in applying these techniques in the field, looking ultimately towards data-driven patient-specific blood flow modelling.
Collapse
Affiliation(s)
- Amirhossein Arzani
- Department of Mechanical Engineering, Northern Arizona University, Flagstaff, AZ, USA
| | - Scott T. M. Dawson
- Department of Mechanical, Materials and Aerospace Engineering, Illinois Institute of Technology, Chicago, IL, USA
| |
Collapse
|