1
|
Borja MG, Martinez-Legazpi P, Nguyen C, Flores O, Kahn AM, Bermejo J, Del Álamo JC. Deriving phenotype-representative left ventricular flow patterns by reduced-order modeling and classification. Comput Biol Med 2024; 179:108760. [PMID: 38944903 DOI: 10.1016/j.compbiomed.2024.108760] [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: 12/06/2023] [Revised: 06/12/2024] [Accepted: 06/13/2024] [Indexed: 07/02/2024]
Abstract
BACKGROUND Extracting phenotype-representative flow patterns and their associated numerical metrics is a bottleneck in the clinical translation of advanced cardiac flow imaging modalities. We hypothesized that reduced-order models (ROMs) are a suitable strategy for deriving simple and interpretable clinical metrics of intraventricular flow suitable for further assessments. Combined with machine learning (ML) flow-based ROMs could provide new insight to help diagnose and risk-stratify patients. METHODS We analyzed 2D color-Doppler echocardiograms of 81 non-ischemic dilated cardiomyopathy (DCM) patients, 51 hypertrophic cardiomyopathy (HCM) patients, and 77 normal volunteers (Control). We applied proper orthogonal decomposition (POD) to build patient-specific and cohort-specific ROMs of LV flow. Each ROM aggregates a low number of components representing a spatially dependent velocity map modulated along the cardiac cycle by a time-dependent coefficient. We tested three classifiers using deliberately simple ML analyses of these ROMs with varying supervision levels. In supervised models, hyperparameter grid search was used to derive the ROMs that maximize classification power. The classifiers were blinded to LV chamber geometry and function. We ran vector flow mapping on the color-Doppler sequences to help visualize flow patterns and interpret the ML results. RESULTS POD-based ROMs stably represented each cohort through 10-fold cross-validation. The principal POD mode captured >80 % of the flow kinetic energy (KE) in all cohorts and represented the LV filling/emptying jets. Mode 2 represented the diastolic vortex and its KE contribution ranged from <1 % (HCM) to 13 % (DCM). Semi-unsupervised classification using patient-specific ROMs revealed that the KE ratio of these two principal modes, the vortex-to-jet (V2J) energy ratio, is a simple, interpretable metric that discriminates DCM, HCM, and Control patients. Receiver operating characteristic curves using V2J as classifier had areas under the curve of 0.81, 0.91, and 0.95 for distinguishing HCM vs. Control, DCM vs. Control, and DCM vs. HCM, respectively. CONCLUSIONS Modal decomposition of cardiac flow can be used to create ROMs of normal and pathological flow patterns, uncovering simple interpretable flow metrics with power to discriminate disease states, and particularly suitable for further processing using ML.
Collapse
Affiliation(s)
- María Guadalupe Borja
- Department of Mechanical and Aerospace Engineering, University of California San Diego, La Jolla, CA, USA
| | - Pablo Martinez-Legazpi
- Department of Mathematical Physics and Fluids, Facultad de Ciencias, Universidad Nacional de Educación a Distancia, UNED and CIBERCV, Madrid, Spain
| | - Cathleen Nguyen
- Department of Mechanical Engineering, University of Washington, Seattle, WA, USA
| | - Oscar Flores
- Department of Aerospace Engineering, Universidad Carlos III de Madrid, Leganés, Spain
| | - Andrew M Kahn
- Division of Cardiovascular Medicine, University of California San Diego, La Jolla, CA, USA
| | - Javier Bermejo
- Department of Cardiology, Hospital General Universitario Gregorio Marañón, Facultad de Medicina, Universidad Complutense de Madrid, Instituto de Investigación Sanitaria Gregorio Marañón and CIBERCV, Madrid, Spain
| | - Juan C Del Álamo
- Department of Mechanical and Aerospace Engineering, University of California San Diego, La Jolla, CA, USA; Department of Mechanical Engineering, University of Washington, Seattle, WA, USA; Center for Cardiovascular Biology, University of Washington, Seattle, WA, USA; Division of Cardiology, University of Washington, Seattle, WA, USA.
| |
Collapse
|
2
|
Cheng L, de Groot J, Xie K, Si Y, Han X. Camera-Based Dynamic Vibration Analysis Using Transformer-Based Model CoTracker and Dynamic Mode Decomposition. SENSORS (BASEL, SWITZERLAND) 2024; 24:3541. [PMID: 38894329 PMCID: PMC11175193 DOI: 10.3390/s24113541] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/10/2024] [Revised: 05/28/2024] [Accepted: 05/30/2024] [Indexed: 06/21/2024]
Abstract
Accelerometers are commonly used to measure vibrations for condition monitoring in mechanical and civil structures; however, their high cost and point-based measurement approach present practical limitations. With rapid advancements in computer vision and deep learning, research into tracking the motion of individual pixels with vision cameras has increased. The recently developed CoTracker, a transformer-based model, has demonstrated excellence in motion tracking, yet its performance in measuring structural vibrations has not been fully explored. This paper investigates the efficacy of the CoTracker model in extracting full-field structural vibrations using cameras. It is initially applied to capture the dense point movements in video sequences of a cantilever beam recorded using a high-speed camera. Subsequently, modal analysis using delay-embedding dynamic mode decomposition (DMD) is conducted to extract modal parameters including natural frequencies, damping ratios, and mode shapes. The results, benchmarked against those from a reference accelerometer and the Finite Element Method (FEM) result, demonstrate CoTracker's high potential for general applicability in structural vibration measurements.
Collapse
Affiliation(s)
- Liangliang Cheng
- Dynamics and Vibration Group, Engineering and Technology Institute Groningen, Faculty of Science and Engineering, University of Groningen, 9712 CP Groningen, The Netherlands; (J.d.G.); (K.X.); (Y.S.); (X.H.)
| | | | | | | | | |
Collapse
|
3
|
Borja MG, Martinez-Legazpi P, Nguyen C, Flores O, Kahn AM, Bermejo J, del Álamo JC. Deriving Explainable Metrics of Left Ventricular Flow by Reduced-Order Modeling and Classification. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.10.03.23296524. [PMID: 37873442 PMCID: PMC10593009 DOI: 10.1101/2023.10.03.23296524] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/25/2023]
Abstract
Background Extracting explainable flow metrics is a bottleneck to the clinical translation of advanced cardiac flow imaging modalities. We hypothesized that reduced-order models (ROMs) of intraventricular flow are a suitable strategy for deriving simple and interpretable clinical metrics suitable for further assessments. Combined with machine learning (ML) flow-based ROMs could provide new insight to help diagnose and risk-stratify patients. Methods We analyzed 2D color-Doppler echocardiograms of 81 non-ischemic dilated cardiomyopathy (DCM) patients, 51 hypertrophic cardiomyopathy (HCM) patients, and 77 normal volunteers (Control). We applied proper orthogonal decomposition (POD) to build patient-specific and cohort-specific ROMs of LV flow. Each ROM aggregates a low number of components representing a spatially dependent velocity map modulated along the cardiac cycle by a time-dependent coefficient. We tested three classifiers using deliberately simple ML analyses of these ROMs with varying supervision levels. In supervised models, hyperparameter gridsearch was used to derive the ROMs that maximize classification power. The classifiers were blinded to LV chamber geometry and function. We ran vector flow mapping on the color-Doppler sequences to help visualize flow patterns and interpret the ML results. Results POD-based ROMs stably represented each cohort through 10-fold cross-validation. The principal POD mode captured >80% of the flow kinetic energy (KE) in all cohorts and represented the LV filling/emptying jets. Mode 2 represented the diastolic vortex and its KE contribution ranged from <1% (HCM) to 13% (DCM). Semi-unsupervised classification using patient-specific ROMs revealed that the KE ratio of these two principal modes, the vortex-to-jet (V2J) energy ratio, is a simple, interpretable metric that discriminates DCM, HCM, and Control patients. Receiver operating characteristic curves using V2J as classifier had areas under the curve of 0.81, 0.91, and 0.95 for distinguishing HCM vs. Control, DCM vs. Control, and DCM vs. HCM, respectively. Conclusions Modal decomposition of cardiac flow can be used to create ROMs of normal and pathological flow patterns, uncovering simple interpretable flow metrics with power to discriminate disease states, and particularly suitable for further processing using ML.
Collapse
Affiliation(s)
- María Guadalupe Borja
- Department of Mechanical and Aerospace Engineering, University of California San Diego, La Jolla, CA
| | - Pablo Martinez-Legazpi
- Department of Mathematical Physics and Fluids, Facultad de Ciencias, Universidad Nacional de Educación a Distancia, UNED and CIBERCV, Madrid, Spain
| | - Cathleen Nguyen
- Mechanical Engineering Department; University of Washington, Seattle, WA
| | - Oscar Flores
- Department of Aerospace Engineering, Universidad Carlos III de Madrid, Leganés, Spain
| | - Andrew M. Kahn
- Division of Cardiovascular Medicine, University of California San Diego, La Jolla, CA
| | - Javier Bermejo
- Department of Cardiology, Hospital General Universitario Gregorio Marañón; Facultad de Medicina, Universidad Complutense de Madrid, Instituto de Investigación Sanitaria Gregorio Marañón and CIBERCV, Madrid, Spain
| | - Juan C. del Álamo
- Department of Mechanical and Aerospace Engineering, University of California San Diego, La Jolla, CA
- Mechanical Engineering Department; University of Washington, Seattle, WA
- Center for Cardiovascular Biology; University of Washington, Seattle, WA
- Division of Cardiology, University of Washington, Seattle, WA
| |
Collapse
|
4
|
Ilicak E, Ozdemir S, Zapp J, Schad LR, Zöllner FG. Dynamic mode decomposition of dynamic MRI for assessment of pulmonary ventilation and perfusion. Magn Reson Med 2023; 90:761-769. [PMID: 36989180 DOI: 10.1002/mrm.29656] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 03/03/2023] [Accepted: 03/15/2023] [Indexed: 03/30/2023]
Abstract
PURPOSE To introduce dynamic mode decomposition (DMD) as a robust alternative for the assessment of pulmonary functional information from dynamic non-contrast-enhanced acquisitions. METHODS Pulmonary fractional ventilation and normalized perfusion maps were obtained using DMD from simulated phantoms as well as in vivo dynamic acquisitions of healthy volunteers at 1.5T. The performance of DMD was compared with conventional Fourier decomposition (FD) and matrix pencil (MP) methods in estimating functional map values. The proposed method was evaluated based on estimated signal amplitude in functional maps across varying number of measurements. RESULTS Quantitative assessments performed on phantoms and in vivo measurements indicate that DMD is capable of successfully obtaining pulmonary functional maps. Specifically, compared to FD and MP methods, DMD is able to reduce variations in estimated amplitudes across different number of measurements. This improvement is evident in the fractional ventilation and normalized perfusion maps obtain from phantom simulations with frequency variations and noise, as well as in the maps obtained from in vivo measurements. CONCLUSIONS A robust method for accurately estimating pulmonary ventilation and perfusion related signal changes in dynamic acquisitions is presented. The proposed method uses DMD to obtain functional maps reliably, while reducing amplitude variations caused by differences in number of measurements.
Collapse
Affiliation(s)
- Efe Ilicak
- Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Safa Ozdemir
- Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Jascha Zapp
- Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Lothar R Schad
- Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Frank G Zöllner
- Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| |
Collapse
|
5
|
Groun N, Villalba-Orero M, Lara-Pezzi E, Valero E, Garicano-Mena J, Le Clainche S. A novel data-driven method for the analysis and reconstruction of cardiac cine MRI. Comput Biol Med 2022; 151:106317. [PMID: 36442273 DOI: 10.1016/j.compbiomed.2022.106317] [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: 05/24/2022] [Revised: 11/08/2022] [Accepted: 11/13/2022] [Indexed: 11/17/2022]
Abstract
Cardiac cine magnetic resonance imaging (MRI) can be considered the optimal criterion for measuring cardiac function. This imaging technique can provide us with detailed information about cardiac structure, tissue composition and even blood flow, which makes it highly used in medical science. But due to the image time acquisition and several other factors the MRI sequences can easily get corrupted, causing radiologists to misdiagnose 40 million people worldwide each and every single year. Hence, the urge to decrease these numbers, researchers from different fields have been introducing novel tools and methods in the medical field. Aiming to the same target, we consider in this work the application of the higher order dynamic mode decomposition (HODMD) technique. The HODMD algorithm is a linear method, which was originally introduced in the fluid dynamics domain, for the analysis of complex systems. Nevertheless, the proposed method has extended its applicability to numerous domains, including medicine. In this work, HODMD in used to analyze sets of MR images of a heart, with the ultimate goal of identifying the main patterns and frequencies driving the heart dynamics. Furthermore, a novel interpolation algorithm based on singular value decomposition combined with HODMD is introduced, providing a three-dimensional reconstruction of the heart. This algorithm is applied (i) to reconstruct corrupted or missing images, and (ii) to build a reduced order model of the heart dynamics.
Collapse
Affiliation(s)
- Nourelhouda Groun
- ETSI Aeronáutica y del Espacio and ETSI Telecomunicación - Universidad Politécnica de Madrid, 28040 Madrid, Spain.
| | - María Villalba-Orero
- Centro Nacional de Investigaciones Cardiovasculares (CNIC), C. de Melchor Fernández Almagro, 3, 28029 Madrid, Spain; Departamento de Medicina y Cirugía Animal, Facultad de Veterinaria, Universidad Complutense de Madrid, 28040 Madrid, Spain
| | - Enrique Lara-Pezzi
- Centro Nacional de Investigaciones Cardiovasculares (CNIC), C. de Melchor Fernández Almagro, 3, 28029 Madrid, Spain
| | - Eusebio Valero
- ETSI Aeronáutica y del Espacio - Universidad Politécnica de Madrid, 28040 Madrid, Spain; Center for Computational Simulation (CCS), 28660 Boadilla del Monte, Spain
| | - Jesús Garicano-Mena
- ETSI Aeronáutica y del Espacio - Universidad Politécnica de Madrid, 28040 Madrid, Spain; Center for Computational Simulation (CCS), 28660 Boadilla del Monte, Spain
| | - Soledad Le Clainche
- ETSI Aeronáutica y del Espacio - Universidad Politécnica de Madrid, 28040 Madrid, Spain; Center for Computational Simulation (CCS), 28660 Boadilla del Monte, Spain.
| |
Collapse
|