您的检索：
学者姓名：刘有军
精炼检索结果：
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 ：
The underuse of invasive fractional flow reserve (FFR) in clinical practice has motivated research towards noninvasive prediction of FFR. Although the non-invasive derivation of FFR (FFRCT) using computational fluid dynamics (CFD) principles has become a common practice, its clinical application has been limited due to the considerable time required for computation of resulting changes in haemodynamic conditions. An alternative to CFD technology is incorporating a neural network into the computational process to reduce the time necessary for running an effective model. In this study we propose a cascade of data -driven and physic -based neural networks (DP -NN) for predicting FFR (DL-FFRCT). The first network of cascade network DP -NN includes geometric features, and the second network includes physical features. We compare the differences between data -driven neural network (D -NN) and DP -NN for predicting FFR. The training and testing datasets were obtained by solving the three-dimensional incompressible Navier-Stokes equations. Coronary flow and geometric features were used as inputs to train D NN. In DP -NN the training process involves first training a D -NN to output resting Delta P as one input feature to the DP -NN. Secondly, the physics -based microcirculatory resistance as another input feature to the DP -NN. Using clinically measured FFR as the "gold standard", we validated the computational accuracy of DL-FFRCT in 77 patients. Compared to D -NN, DP -NN improved the prediction of Delta P (R2 = 0.87 vs. R2 = 0.92). Statistical analysis demonstrated that the diagnostic accuracy of DL-FFRCT was not inferior to FFRCT (85.71 % vs. 88.3 %) and the computational time was reduced by a factor of approximately 3000 (4.26 s vs. 3.5 h). DP -NN represents a near real-time, interpretable, and highly accurate deep -learning network, which contributes to the development of high-performance computational methods for haemodynamics. We anticipate that DP -NN will enable near real-time prediction of DL-FFRCT in personalized narrow blood vessels and provide guidance for cardiovascular disease treatments.
关键词 ：
Deep learning Deep learning Computational FFR Computational FFR Coronary artery disease Coronary artery disease Cascade neural networks Cascade neural networks
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liu, Jincheng , Li, Bao , Yang, Yang et al. A comprehensive approach to prediction of fractional flow reserve from deep-learning-augmented model [J]. | COMPUTERS IN BIOLOGY AND MEDICINE , 2024 , 169 . |
| MLA | Liu, Jincheng et al. "A comprehensive approach to prediction of fractional flow reserve from deep-learning-augmented model" . | COMPUTERS IN BIOLOGY AND MEDICINE 169 (2024) . |
| APA | Liu, Jincheng , Li, Bao , Yang, Yang , Huang, Suqin , Sun, Hao , Liu, Jian et al. A comprehensive approach to prediction of fractional flow reserve from deep-learning-augmented model . | COMPUTERS IN BIOLOGY AND MEDICINE , 2024 , 169 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开了一种磷酸盐介导的矿化胶原及其自组装方法和应用，具体涉及生物医用材料技术领域。所述方法包括在弱碱性条件下，利用可溶性多聚磷酸盐改性胶原纤维，得改性胶原纤维溶液；再在改性胶原纤维溶液中加入钙盐继续反应，得初始胶原纤维溶液；接着在初始胶原纤维溶液中加入碱性磷酸酶，控制pH，利用碱性磷酸酶调控胶原纤维的矿化，得矿化骨基质溶液；最后矿化骨基质溶液经清洗、离心、浓缩和冷冻干燥得磷酸盐介导的矿化胶原。本发明充分考虑了离子来源、化学反应平衡及化学因素添加顺序在矿化中的影响，构建了多因素协同调控体系，更好的模拟了体内复杂的骨基质矿化组装过程。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 杜田明 , 乔爱科 , 杨海胜 et al. 一种磷酸盐介导的矿化胶原及其自组装方法和应用 : CN202310744975.4[P]. | 2023-06-21 . |
| MLA | 杜田明 et al. "一种磷酸盐介导的矿化胶原及其自组装方法和应用" : CN202310744975.4. | 2023-06-21 . |
| APA | 杜田明 , 乔爱科 , 杨海胜 , 刘有军 . 一种磷酸盐介导的矿化胶原及其自组装方法和应用 : CN202310744975.4. | 2023-06-21 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
一种基于集中参数模型计算冠状动脉FFR并三维可视化的方法属于数值模拟领域，该方法包括以下步骤：基于患者真实冠脉CT图像进行三维建模，并对三维模型进行平滑、切割等一系列处理；基于最大内切球法的中心线提取算法对该模型进行中心线提取，得到其几何拓扑结构，同时得到血管几何参数(管腔半径、长度、狭窄入口面积、狭窄长度等)；基于集中参数模型，结合深度学习预测得到的冠状动脉狭窄阻力，进行个性化数值计算，得到该冠脉的FFR值；基于纹理映射等计算机图形学方法，把FFR值以彩色可视化的方式显示到冠脉三维模型上。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 刘有军 , 郝耀东 , 李鲍 et al. 一种基于集中参数模型计算冠状动脉FFR并三维可视化的方法 : CN202310880011.2[P]. | 2023-07-18 . |
| MLA | 刘有军 et al. "一种基于集中参数模型计算冠状动脉FFR并三维可视化的方法" : CN202310880011.2. | 2023-07-18 . |
| APA | 刘有军 , 郝耀东 , 李鲍 , 冯懿俐 . 一种基于集中参数模型计算冠状动脉FFR并三维可视化的方法 : CN202310880011.2. | 2023-07-18 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本申请公开了一种基于神经血管耦合脑血流量预测系统，包括：结构连接矩阵生成模块，根据弥散张量成像数据得到结构连接矩阵；重新构建局部场电位模块，根据磁共振成像数据和头皮脑电数据建立局部场电位；功能连接矩阵生成模块，根据局部场电位生成功能连接矩阵；脑网络融合矩阵生成模块，将结构连接矩阵和功能矩阵融合生成脑网络融合矩阵；全脑逆向神经质量模型网络生成模块，建立单个逆向神经质量模型并形成全脑逆向神经质量模型网络；神经活动获取模块，根据逆向神经质量模型和局部场电位获取神经活动；脑血流量计算模块，神经活动输入到神经调控血流动力学系统得到脑血流量。通过本申请，提高脑血流量预测准确性，不会对检测对象造成伤害。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 张丽媛 , 王同娜 , 刘有军 et al. 一种基于神经血管耦合脑血流量的预测系统 : CN202310580124.0[P]. | 2023-05-22 . |
| MLA | 张丽媛 et al. "一种基于神经血管耦合脑血流量的预测系统" : CN202310580124.0. | 2023-05-22 . |
| APA | 张丽媛 , 王同娜 , 刘有军 , 李鲍 . 一种基于神经血管耦合脑血流量的预测系统 : CN202310580124.0. | 2023-05-22 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Background and objective: The functional assessment of the severity of coronary stenosis from coronary computed tomography angiography (CCTA)-derived fractional flow reserve (FFR) has recently attracted interest. However, existing algorithms run at high computational cost. Therefore, this study proposes a fast calculation method of FFR for the diagnosis of ischemia-causing coronary stenosis.Methods: We combined CCTA and machine learning to develop a simplified single-vessel coronary model for rapid calculation of FFR. First, a zero-dimensional model of single-vessel coronary was established based on CCTA, and microcirculation resistance was determined through the relationship between coronary pressure and flow. In addition, a coronary stenosis model based on machine learning was introduced to determine stenosis resistance. Computational FFR (cFFR) was then obtained by combining the zero-dimensional model and the stenosis model with inlet boundary conditions for resting (cFFRr) and hyperemic (cFFRh) aortic pressure, respectively. We retrospectively analyzed 75 patients who underwent clinically invasive FFR (iFFR), and verified the model accuracy by comparison of cFFR with iFFR.Results: The average computing time of cFFR was less than 2 s. The correlations between cFFRr and cFFRh with iFFR were r = 0.89 (p < 0.001) and r = 0.90 (p < 0.001), respectively. Diagnostic accuracy, sensitivity, speci-ficity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio for cFFRr and cFFRh were 90.7%, 95.0%, 89.1%, 76.0%, 98.0%, 8.7, 0.1 and 92.0%, 95.0%, 90.9%, 79.2%, 98.0%, 10.5, 0.1, respectively.Conclusions: The proposed model enables rapid prediction of cFFR and exhibits high diagnostic performance in selected patient cohorts. The model thus provides an accurate and time-efficient computational tool to detect ischemia-causing stenosis and assist with clinical decision-making.
关键词 ：
Machine learning Machine learning Coronary zero-dimensional model Coronary zero-dimensional model Coronary stenosis model Coronary stenosis model Fractional flow reserve Fractional flow reserve Coronary computed tomography angiography Coronary computed tomography angiography
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Feng, Yili , Li, Bao , Fu, Ruisen et al. A simplified coronary model for diagnosis of ischemia-causing coronary stenosis [J]. | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE , 2023 , 242 . |
| MLA | Feng, Yili et al. "A simplified coronary model for diagnosis of ischemia-causing coronary stenosis" . | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 242 (2023) . |
| APA | Feng, Yili , Li, Bao , Fu, Ruisen , Hao, Yaodong , Wang, Tongna , Guo, Huanmei et al. A simplified coronary model for diagnosis of ischemia-causing coronary stenosis . | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE , 2023 , 242 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Background and Objectives: Coronary computed tomography angiography (CCTA) derived fractional flow reserve (CT-FFR) requires a maximal hyperemic state to be modeled by assuming the total coronary re-sistance decreased to a constant 0.24 of that under the resting state. However, this assumption neglects the vasodilator capacity of individual patients. Herein, we proposed a high-fidelity geometric multiscale model (HFMM) to characterize coronary pressure and flow under the resting state, seeking to better pre-dict myocardial ischemia by using CCTA-derived instantaneous wave-free ratio (CT-iFR).Methods: Fifty-seven patients (62 lesions) who had undergone CCTA and were then referred to invasive FFR were prospectively enrolled. The coronary microcirculation resistance hemodynamic model (RHM) under the resting condition was established on a patient-specific basis. Coupled with a closed-loop ge-ometric multiscale model (CGM) of their individual coronary circulations, the HFMM model was estab-lished to non-invasively derive the CT-iFR from CCTA images.Results: With the invasive FFR being the reference standard, accuracy of the obtained CT-iFR in identify-ing myocardial ischemia was greater than those of the CCTA and non-invasively derived CT-FFR (90.32% vs. 79.03% vs. 84.3%). The overall computational time of CT-iFR was 61 +/- 6 min, faster than that of the CT-FFR (8 h). The sensitivity, specificity, positive predictive value, and negative predictive value of the CT-iFR in discriminating an invasive FFR > 0.8 were 78% (95% CI: 40-97%), 92% (95% CI: 82-98%), 64% (95% CI: 39-83%), and 96% (95% CI:88-99%), respectively.Conclusions: A high-fidelity geometric multiscale hemodynamic model was developed for rapid and ac-curate estimation of CT-iFR. Compared with CT-FFR, CT-iFR is of less computational cost and enables as-sessment of tandem lesions.(c) 2023 Elsevier B.V. All rights reserved.
关键词 ：
Instantaneous wave-free ratio (iFR) Instantaneous wave-free ratio (iFR) Coronary pre-arterioles compensation Coronary pre-arterioles compensation Computational fluid dynamics (CFD) Computational fluid dynamics (CFD) Coronary artery disease Coronary artery disease
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liu, Jincheng , Li, Bao , Zhang, Yanping et al. A high-fidelity geometric multiscale hemodynamic model for predicting myocardial ischemia [J]. | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE , 2023 , 233 . |
| MLA | Liu, Jincheng et al. "A high-fidelity geometric multiscale hemodynamic model for predicting myocardial ischemia" . | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 233 (2023) . |
| APA | Liu, Jincheng , Li, Bao , Zhang, Yanping , Zhang, Liyuan , Huang, Suqin , Sun, Hao et al. A high-fidelity geometric multiscale hemodynamic model for predicting myocardial ischemia . | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE , 2023 , 233 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Background and Objectives: Clinical diagnosis of ischemic stroke commonly relies on examining cerebral perfusion changes by using computed tomography perfusion (CTP) techniques. However, the radiation dose in CTP is quite higher in comparison to computed tomography angiography (CTA), with associated costs and time. Methods: Hence, this study established a lumped-parameter model (LPM) of brain tissue microcirculation (BTM) based on CTA, aiming to achieve real-time calculation of cerebral perfusion. After validation of calculated flow results with clinical data, the BTM-LPM model was used to examine the changes in cerebral perfusion following ischemic stroke, in which the effects of nine anatomical structures of the Circle of Willis (CoW) together with various distribution patterns of stenosis in the feeding arteries were considered. Results: When compared the calculated flow results from BTM-LPM with the clinically measured data of litera-ture, the mean squared error (MSE) value for the feeding arteries was 3.9 % and its total value for microcir-culatory flow in each region was 0.1 %. Notably, the calculation time was 35.6 s. In the case of the CoW missing the left and right posterior communicating artery, a 60 % stenosis of the basilar artery is likely to cause ischemic damage to some temporal and occipital lobes of the right and left hemispheres. While in the case of the CoW missing the anterior communicating artery and the left posterior communicating artery, ischemic damage to the entire frontal lobe and parts of the temporal and parietal lobes of the left hemisphere was found when 80 % stenosis occurred in the left internal carotid artery. Conclusions: The BTM-LPM proposed in this study could accurately calculate cerebral perfusion in real time and demonstrated the importance of CoW anatomy in different ischemic injuries to cerebral tissue. The calculated cerebral perfusion would be a reference value for early diagnosis and preoperative planning of different ischemic injuries to cerebral tissue, thereby the BTM-LPM holds great promising for replacing CTP examination.
关键词 ：
Ischemic stroke Ischemic stroke Lumped-parameter model Lumped-parameter model Cerebral perfusion Cerebral perfusion
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Sun, Hao , Li, Bao , Liu, Jincheng et al. Real-time model-based cerebral perfusion calculation for ischemic stroke [J]. | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE , 2023 , 243 . |
| MLA | Sun, Hao et al. "Real-time model-based cerebral perfusion calculation for ischemic stroke" . | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 243 (2023) . |
| APA | Sun, Hao , Li, Bao , Liu, Jincheng , Xi, Xiaolu , Zhang, Liyuan , Zhang, Yanping et al. Real-time model-based cerebral perfusion calculation for ischemic stroke . | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE , 2023 , 243 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Difficulty in knowledge validation is a significant hindrance to knowledge discovery via data mining, especially automatic validation without artificial participation. In the field of medical research, medical knowledge discovery from electronic medical records is a common medical data mining method, but it is difficult to validate the discovered medical knowledge without the participation of medical experts. In this article, we propose a data-driven medical knowledge discovery closed-loop pipeline based on interpretable machine learning and deep learning; the components of the pipeline include Data Generator, Medical Knowledge Mining, Medical Knowledge Evaluation, and Medical Knowledge Application. In addition to completing the discovery of medical knowledge, the pipeline can also automatically validate the knowledge. We apply our pipeline's discovered medical knowledge to a traditional prognostic predictive model of heart failure in a real-world study, demonstrating that the incorporation of medical knowledge can effectively improve the performance of the traditional model. We also construct a scale model based on the discovered medical knowledge and demonstrate that it achieves good performance. To guarantee its medical effectiveness, every process of our pipeline involves the participation of medical experts.
关键词 ：
Heart Failure Heart Failure Electronic Medical Records Electronic Medical Records Machine Learning Machine Learning Medical Knowledge Discovery Medical Knowledge Discovery
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang, Shaobo , Du, Xinhui , Liu, Guangliang et al. An Interpretable Data-Driven Medical Knowledge Discovery Pipeline Based on Artificial Intelligence [J]. | IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS , 2023 , 27 (10) : 5099-5109 . |
| MLA | Wang, Shaobo et al. "An Interpretable Data-Driven Medical Knowledge Discovery Pipeline Based on Artificial Intelligence" . | IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 27 . 10 (2023) : 5099-5109 . |
| APA | Wang, Shaobo , Du, Xinhui , Liu, Guangliang , Xing, Hang , Jiao, Zengtao , Yan, Jun et al. An Interpretable Data-Driven Medical Knowledge Discovery Pipeline Based on Artificial Intelligence . | IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS , 2023 , 27 (10) , 5099-5109 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
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.
关键词 ：
Fractional flow reserve Fractional flow reserve Numerical simulation Numerical simulation Reduced-order model Reduced-order model Stenotic flow resistance Stenotic flow resistance Machine learning Machine learning
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Feng, Yili , Fu, Ruisen , Sun, Hao et al. Non-invasive fractional flow reserve derived from reduced-order coronary model and machine learning prediction of stenosis flow resistance [J]. | ARTIFICIAL INTELLIGENCE IN MEDICINE , 2023 , 147 . |
| MLA | Feng, Yili et al. "Non-invasive fractional flow reserve derived from reduced-order coronary model and machine learning prediction of stenosis flow resistance" . | ARTIFICIAL INTELLIGENCE IN MEDICINE 147 (2023) . |
| APA | Feng, Yili , Fu, Ruisen , Sun, Hao , Wang, Xue , Yang, Yang , Wen, Chuanqi et al. Non-invasive fractional flow reserve derived from reduced-order coronary model and machine learning prediction of stenosis flow resistance . | ARTIFICIAL INTELLIGENCE IN MEDICINE , 2023 , 147 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Sigmoid sinus wall dehiscence (SSWD) is a common pathophysiology of patients with pulsatile tinnitus (PT). However, the pathological mechanism of SSWD is unclear. This study aimed to investigate the relationship between the position of the SSWD and blood flow pattern of the transverse sinus and sigmoid sinus (TS-SS) junction. The impact of the blood flow was hypothesized to be the pathological mechanism of SSWD. Twenty patients and two healthy volunteers were analyzed retrospectively, and transient computer fluid dynamics was used to verify this hypothesis. A 4D flow magnetic resonance imaging experiment was performed to validate the numerical simulation. The position of high-velocity blood flow impacting the vessel wall (17/20) was consistent with SSWD. In healthy volunteers, the temporal bone was thin where the blood flow impacted the blood vessel wall. The average wall shear stress (20/20) and pressure (18/20) of the SSWD area (peak) were higher than those of sigmoid sinus wall anomalies (the contact area between the vessel wall and the temporal bone at the TS-SS junction). The average wall pressure percentage differences of 16/20, 11/20, and 4/20 patients were more than 5%, 10%, and 20%, respectively. The average wall shear stress percentage differences of 20/20, 18/20, and 16/ 20 patients were more than 5%, 10%, and 20%, respectively. In brief, the blood flow of the TS-SS junction impacted the vessel wall and increased wall pressure, which might be an important pathological mechanism of SSWD. This study could serve as a basis for the diagnosis and SSWD resurfacing surgery of patients with PT induced by SSWD.
关键词 ：
Computational fluid dynamics Computational fluid dynamics Transverse sinus and sigmoid sinus junction Transverse sinus and sigmoid sinus junction Pulsatile tinnitus Pulsatile tinnitus 4D flow MRI 4D flow MRI Sigmoid sinus wall dehiscence Sigmoid sinus wall dehiscence
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Mu, Zhenxia , Li, Xiaoshuai , Zhao, Dawei et al. Hemodynamics study on the relationship between the sigmoid sinus wall dehiscence and the blood flow pattern of the transverse sinus and sigmoid sinus junction [J]. | JOURNAL OF BIOMECHANICS , 2022 , 135 . |
| MLA | Mu, Zhenxia et al. "Hemodynamics study on the relationship between the sigmoid sinus wall dehiscence and the blood flow pattern of the transverse sinus and sigmoid sinus junction" . | JOURNAL OF BIOMECHANICS 135 (2022) . |
| APA | Mu, Zhenxia , Li, Xiaoshuai , Zhao, Dawei , Qiu, Xiaoyu , Dai, Chihang , Meng, Xuxu et al. Hemodynamics study on the relationship between the sigmoid sinus wall dehiscence and the blood flow pattern of the transverse sinus and sigmoid sinus junction . | JOURNAL OF BIOMECHANICS , 2022 , 135 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
