scispace - formally typeset
Search or ask a question
Author

Lucian Mihai Itu

Bio: Lucian Mihai Itu is an academic researcher from Siemens. The author has contributed to research in topics: Fractional flow reserve & Deep learning. The author has an hindex of 19, co-authored 97 publications receiving 1383 citations. Previous affiliations of Lucian Mihai Itu include Transilvania University of Brașov & Princeton University.


Papers
More filters
Journal ArticleDOI
TL;DR: A machine-learning-based model for predicting FFR is presented as an alternative to physics-based approaches, and average execution time was reduced by more than 80 times, leading to near real-time assessment of FFR.
Abstract: Fractional flow reserve (FFR) is a functional index quantifying the severity of coronary artery lesions and is clinically obtained using an invasive, catheter-based measurement. Recently, physics-based models have shown great promise in being able to noninvasively estimate FFR from patient-specific anatomical information, e.g., obtained from computed tomography scans of the heart and the coronary arteries. However, these models have high computational demand, limiting their clinical adoption. In this paper, we present a machine-learning-based model for predicting FFR as an alternative to physics-based approaches. The model is trained on a large database of synthetically generated coronary anatomies, where the target values are computed using the physics-based model. The trained model predicts FFR at each point along the centerline of the coronary tree, and its performance was assessed by comparing the predictions against physics-based computations and against invasively measured FFR for 87 patients and 125 lesions in total. Correlation between machine-learning and physics-based predictions was excellent (0.9994, P < 0.001), and no systematic bias was found in Bland-Altman analysis: mean difference was -0.00081 ± 0.0039. Invasive FFR ≤ 0.80 was found in 38 lesions out of 125 and was predicted by the machine-learning algorithm with a sensitivity of 81.6%, a specificity of 83.9%, and an accuracy of 83.2%. The correlation was 0.729 (P < 0.001). Compared with the physics-based computation, average execution time was reduced by more than 80 times, leading to near real-time assessment of FFR. Average execution time went down from 196.3 ± 78.5 s for the CFD model to ∼2.4 ± 0.44 s for the machine-learning model on a workstation with 3.4-GHz Intel i7 8-core processor.

300 citations

Journal ArticleDOI
TL;DR: The FFRML algorithm performs equally in detecting lesion-specific ischemia when compared with the FFRCFD approach, and both methods outperform accuracy of coronary CT angiography and QCA in the detection of flow-limiting stenosis.
Abstract: The results demonstrate that coronary CT angiography–derived fractional flow reserve using machine learning performs equally to computational fluid dynamics modeling in detecting lesion-specific ischemia; both algorithms outperform coronary CT angiography alone and quantitative coronary angiography.

156 citations

Patent
04 Nov 2013
TL;DR: In this paper, a method and system for non-invasive assessment of coronary artery stenosis is disclosed, where patient-specific anatomical measurements of the coronary arteries are extracted from medical image data of a patient acquired during rest state.
Abstract: A method and system for non-invasive assessment of coronary artery stenosis is disclosed. Patient-specific anatomical measurements of the coronary arteries are extracted from medical image data of a patient acquired during rest state. Patient-specific rest state boundary conditions of a model of coronary circulation representing the coronary arteries are calculated based on the patient-specific anatomical measurements and non-invasive clinical measurements of the patient at rest. Patient-specific rest state boundary conditions of the model of coronary circulation representing the coronary arteries are calculated based on the patient-specific anatomical measurements and non-invasive clinical measurements of the patient at rest. Hyperemic blood flow and pressure across at least one stenosis region of the coronary arteries are simulated using the model of coronary circulation and the patient-specific hyperemic boundary conditions. Fractional flow reserve (FFR) is calculated for the at least one stenosis region based on the simulated hyperemic blood flow and pressure.

96 citations

Patent
12 Nov 2012
TL;DR: In this paper, a multi-scale functional model of coronary circulation is generated based on the patient-specific anatomical model, and virtual intervention simulations are performed using the multiscale function model for decision support and intervention planning.
Abstract: A method and system for multi-scale anatomical and functional modeling of coronary circulation is disclosed. A patient-specific anatomical model of coronary arteries and the heart is generated from medical image data of a patient. A multi-scale functional model of coronary circulation is generated based on the patient-specific anatomical model. Blood flow is simulated in at least one stenosis region of at least one coronary artery using the multi-scale function model of coronary circulation. Hemodynamic quantities, such as fractional flow reserve (FFR), are computed to determine a functional assessment of the stenosis, and virtual intervention simulations are performed using the multi-scale function model of coronary circulation for decision support and intervention planning.

79 citations

Patent
21 Jul 2015
TL;DR: In this article, a machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data.
Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution. Combinations of one or more of uncertainty, use of synthetic training data, and therapy prediction may be provided.

69 citations


Cited by
More filters
Journal ArticleDOI

[...]

08 Dec 2001-BMJ
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

33,785 citations

Christopher M. Bishop1
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

10,141 citations

Journal ArticleDOI
TL;DR: Basic definitions of terms such as “machine/deep learning” are provided and the integration of AI into radiology is analyzed, which will allow radiologists to perform more value-added tasks, becoming more visible to patients and playing a vital role in multidisciplinary clinical teams.
Abstract: One of the most promising areas of health innovation is the application of artificial intelligence (AI), primarily in medical imaging. This article provides basic definitions of terms such as “machine/deep learning” and analyses the integration of AI into radiology. Publications on AI have drastically increased from about 100–150 per year in 2007–2008 to 700–800 per year in 2016–2017. Magnetic resonance imaging and computed tomography collectively account for more than 50% of current articles. Neuroradiology appears in about one-third of the papers, followed by musculoskeletal, cardiovascular, breast, urogenital, lung/thorax, and abdomen, each representing 6–9% of articles. With an irreversible increase in the amount of data and the possibility to use AI to identify findings either detectable or not by the human eye, radiology is now moving from a subjective perceptual skill to a more objective science. Radiologists, who were on the forefront of the digital era in medicine, can guide the introduction of AI into healthcare. Yet, they will not be replaced because radiology includes communication of diagnosis, consideration of patient’s values and preferences, medical judgment, quality assurance, education, policy-making, and interventional procedures. The higher efficiency provided by AI will allow radiologists to perform more value-added tasks, becoming more visible to patients and playing a vital role in multidisciplinary clinical teams.

403 citations

Patent
29 Jul 2011
TL;DR: In this article, a system for determining cardiovascular information for a patient is described, which includes at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the heart based on the patient specific data.
Abstract: Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.

394 citations