1
|
Feng Y, Fu R, Sun H, Wang X, Yang Y, Wen C, Hao Y, Sun Y, Li B, Li N, Yang H, Feng Q, Liu J, Liu Z, Zhang L, Liu Y. Non-invasive fractional flow reserve derived from reduced-order coronary model and machine learning prediction of stenosis flow resistance. Artif Intell Med 2024; 147:102744. [PMID: 38184351 DOI: 10.1016/j.artmed.2023.102744] [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: 10/05/2022] [Revised: 11/29/2023] [Accepted: 11/29/2023] [Indexed: 01/08/2024]
Abstract
BACKGROUND AND OBJECTIVE Recently, computational fluid dynamics enables the non-invasive calculation of fractional flow reserve (FFR) based on 3D coronary model, but it is time-consuming. Currently, machine learning technique has emerged as an efficient and reliable approach for prediction, which allows saving a lot of analysis time. This study aimed at developing a simplified FFR prediction model for rapid and accurate assessment of functional significance of stenosis. METHODS A reduced-order lumped parameter model (LPM) of coronary system and cardiovascular system was constructed for rapidly simulating coronary flow, in which a machine learning model was embedded for accurately predicting stenosis flow resistance at a given flow from anatomical features of stenosis. Importantly, the LPM was personalized in both structures and parameters according to coronary geometries from computed tomography angiography and physiological measurements such as blood pressure and cardiac output for personalized simulations of coronary pressure and flow. Coronary lesions with invasive FFR ≤ 0.80 were defined as hemodynamically significant. RESULTS A total of 91 patients (93 lesions) who underwent invasive FFR were involved in FFR derived from machine learning (FFRML) calculation. Of the 93 lesions, 27 lesions (29.0%) showed lesion-specific ischemia. The average time of FFRML simulation was about 10 min. On a per-vessel basis, the FFRML and FFR were significantly correlated (r = 0.86, p < 0.001). The diagnostic accuracy, sensitivity, specificity, positive predictive value and negative predictive value were 91.4%, 92.6%, 90.9%, 80.6% and 96.8%, respectively. The area under the receiver-operating characteristic curve of FFRML was 0.984. CONCLUSION In this selected cohort of patients, the FFRML improves the computational efficiency and ensures the accuracy. The favorable performance of FFRML approach greatly facilitates its potential application in detecting hemodynamically significant coronary stenosis in future routine clinical practice.
Collapse
Affiliation(s)
- Yili Feng
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Ruisen Fu
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Hao Sun
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Xue Wang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China; Department of Equipment and Materials, Tianjin First Central Hospital, Tianjin, China
| | - Yang Yang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Chuanqi Wen
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Yaodong Hao
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Yutong Sun
- Department of Cardiology, Peking University People's Hospital, Beijing, China
| | - Bao Li
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Na Li
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China; School of Radiology, Shandong First Medical University & Shandong Academy of Medical Sciences, Tai'an, Shandong 271016, China
| | - Haisheng Yang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Quansheng Feng
- Department of Cardiology, The First People's Hospital of Guangshui, Hubei 432700, China
| | - Jian Liu
- Department of Cardiology, Peking University People's Hospital, Beijing, China
| | - Zhuo Liu
- Department of Radiology, Peking University People's Hospital, Beijing, China
| | - Liyuan Zhang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China.
| | - Youjun Liu
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China.
| |
Collapse
|
2
|
Hu X, Liu X, Wang H, Xu L, Wu P, Zhang W, Niu Z, Zhang L, Gao Q. A novel physics-based model for fast computation of blood flow in coronary arteries. Biomed Eng Online 2023; 22:56. [PMID: 37303051 DOI: 10.1186/s12938-023-01121-y] [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: 12/15/2022] [Accepted: 05/28/2023] [Indexed: 06/13/2023] Open
Abstract
Blood flow and pressure calculated using the currently available methods have shown the potential to predict the progression of pathology, guide treatment strategies and help with postoperative recovery. However, the conspicuous disadvantage of these methods might be the time-consuming nature due to the simulation of virtual interventional treatment. The purpose of this study is to propose a fast novel physics-based model, called FAST, for the prediction of blood flow and pressure. More specifically, blood flow in a vessel is discretized into a number of micro-flow elements along the centerline of the artery, so that when using the equation of viscous fluid motion, the complex blood flow in the artery is simplified into a one-dimensional (1D) steady-state flow. We demonstrate that this method can compute the fractional flow reserve (FFR) derived from coronary computed tomography angiography (CCTA). 345 patients with 402 lesions are used to evaluate the feasibility of the FAST simulation through a comparison with three-dimensional (3D) computational fluid dynamics (CFD) simulation. Invasive FFR is also introduced to validate the diagnostic performance of the FAST method as a reference standard. The performance of the FAST method is comparable with the 3D CFD method. Compared with invasive FFR, the accuracy, sensitivity and specificity of FAST is 88.6%, 83.2% and 91.3%, respectively. The AUC of FFRFAST is 0.906. This demonstrates that the FAST algorithm and 3D CFD method show high consistency in predicting steady-state blood flow and pressure. Meanwhile, the FAST method also shows the potential in detecting lesion-specific ischemia.
Collapse
Affiliation(s)
- Xiuhua Hu
- Department of Radiology, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou, China
| | - Xingli Liu
- Hangzhou Shengshi Science and Technology Co., Ltd., Hangzhou, China
| | - Hongping Wang
- The State Key Laboratory of Nonlinear Mechanics, Institute of Mechanics, Chinese Academy of Sciences, Beijing, China
| | - Lei Xu
- Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, Beijing, China
| | - Peng Wu
- Biomanufacturing Research Centre, School of Mechanical and Electric Engineering, Soochow University, Suzhou, Jiangsu, China
| | - Wenbing Zhang
- Department of Cardiology, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou, China
| | - Zhaozhuo Niu
- Department of Cardiac Surgery, Qingdao Municipal Hospital, Qingdao, China
| | - Longjiang Zhang
- Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, China.
| | - Qi Gao
- Institute of Fluid Engineering, School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China.
| |
Collapse
|
3
|
Li N, Li B, Liu J, Feng Y, Zhang L, Liu J, Liu Y. The quantitative relationship between coronary microcirculatory resistance and myocardial ischemia in patients with coronary artery disease. J Biomech 2022; 140:111166. [PMID: 35671542 DOI: 10.1016/j.jbiomech.2022.111166] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Revised: 04/17/2022] [Accepted: 05/23/2022] [Indexed: 10/18/2022]
Abstract
It was hypothesized that the microcirculatory resistance of resting state (Rm-res) might be a good predictor for ischemia. In this study, the quantitative relationship between Rm-res and myocardial ischemia in different stenosed degrees was explored and verified through retrospective analysis, and the diagnostic performance was evaluated. 136 patients were screened and divided into a training set (90 patients) and a validation set (46 patients). In the training set, Rm-res was calculated, and thresholds were determined by exploring the relationship between Rm-res and myocardial ischemia in different stenosed degrees. In the validation set, the diagnostic performance of the thresholds was verified. It was found that the 90 data mean difference (95%CI) of Rm-res between the ischemic group and the non-ischemic group was 63.03 (95 %CI: 25.72-100.34), p < 0.05. In the training set with stenosed degree 41-60%, 61-70%, 71-80%, and >81%, the average of Rm-res in the ischemic and non-ischemic groups were (80.79, 136.87), (96.41, 172.62), (128.99, 198.94) and (175.95, 310.79) mmHg/s/ml. The Rm-res thresholds were 87.18, 118.96, 142.35, and 177.39 mmHg/s/ml. In the validation set, the overall sensitivity, specificity, PPV, NPV, and accuracy were 73.3%, 77.4%, 61.1%, 85.7%, and 76.1%. In conclusion, Rm-res had a significant predictor on myocardial ischemia. As a smaller Rm-res represents greater myocardial mass perfusion, it is more likely that a stenosis will have a functional impact. Threshold analysis showed that Rm-res of different stenosed degrees was a quantitative predictor of myocardial ischemia, which could assist physicians with clinical treatment strategies.
Collapse
Affiliation(s)
- Na Li
- College of Life Science and Chemistry, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Bao Li
- College of Life Science and Chemistry, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Jincheng Liu
- College of Life Science and Chemistry, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Yili Feng
- College of Life Science and Chemistry, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Liyuan Zhang
- College of Life Science and Chemistry, Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Jian Liu
- Peking University People's Hospital, Beijing, China
| | - Youjun Liu
- College of Life Science and Chemistry, Faculty of Environment and Life, Beijing University of Technology, Beijing, China.
| |
Collapse
|
4
|
Lyras KG, Lee J. An improved reduced-order model for pressure drop across arterial stenoses. PLoS One 2021; 16:e0258047. [PMID: 34597313 PMCID: PMC8486142 DOI: 10.1371/journal.pone.0258047] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2021] [Accepted: 09/16/2021] [Indexed: 11/19/2022] Open
Abstract
Quantification of pressure drop across stenotic arteries is a major element in the functional assessment of occlusive arterial disease. Accurate estimation of the pressure drop with a numerical model allows the calculation of Fractional Flow Reserve (FFR), which is a haemodynamic index employed for guiding coronary revascularisation. Its non-invasive evaluation would contribute to safer and cost-effective diseases management. In this work, we propose a new formulation of a reduced-order model of trans-stenotic pressure drop, based on a consistent theoretical analysis of the Navier-Stokes equation. The new formulation features a novel term that characterises the contribution of turbulence effect to pressure loss. Results from three-dimensional computational fluid dynamics (CFD) showed that the proposed model produces predictions that are significantly more accurate than the existing reduced-order models, for large and small symmetric and eccentric stenoses, covering mild to severe area reductions. FFR calculations based on the proposed model produced zero classification error for three classes comprising positive (≤ 0.75), negative (≥ 0.8) and intermediate (0.75 − 0.8) classes.
Collapse
Affiliation(s)
- Konstantinos G. Lyras
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom
- * E-mail: (KGL); (JL)
| | - Jack Lee
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom
- * E-mail: (KGL); (JL)
| |
Collapse
|