A machine-learning approach for computation of fractional flow reserve from coronary computed tomography.
Lucian Mihai Itu,Saikiran Rapaka,Tiziano Passerini,Bogdan Georgescu,Chris Schwemmer,Max Schoebinger,Thomas Flohr,Puneet Sharma,Dorin Comaniciu +8 more
TLDR
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.read more
Citations
More filters
Journal ArticleDOI
Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine
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.
Journal ArticleDOI
Artificial Intelligence in Cardiovascular Imaging: JACC State-of-the-Art Review.
Damini Dey,Piotr J. Slomka,Paul Leeson,Dorin Comaniciu,Sirish Shrestha,Partho P. Sengupta,Thomas H. Marwick +6 more
TL;DR: Recent promising applications of AI in cardiology and cardiac imaging, which potentially add value to patient care are summarized.
Journal ArticleDOI
Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging
Subhi J. Al'Aref,Khalil Anchouche,Gurpreet Singh,Piotr J. Slomka,Kranthi K. Kolli,Amit Kumar,Mohit Pandey,Gabriel Maliakal,Alexander R. van Rosendael,Ashley Beecy,Daniel S. Berman,Jonathan Leipsic,Koen Nieman,Daniele Andreini,Gianluca Pontone,U. Joseph Schoepf,Leslee J. Shaw,Hyuk Jae Chang,Jagat Narula,Jeroen J. Bax,Yuanfang Guan,James K. Min +21 more
TL;DR: A brief overview of ML methodologies that are used for the construction of inferential and predictive data-driven models is presented, and the limitations associated with contemporary application of ML algorithms within the cardiovascular disease field are reviewed.
Journal ArticleDOI
A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis
TL;DR: This study marks, to the authors' knowledge, the first study that demonstrates the feasibility and great potential of using the DL technique as a fast and accurate surrogate of FEA for stress analysis.
Journal ArticleDOI
Diagnostic Accuracy of a Machine-Learning Approach to Coronary Computed Tomographic Angiography-Based Fractional Flow Reserve Result From the MACHINE Consortium
Adriaan Coenen,Young-Hak Y.-H. Kim,Mariusz Kruk,Christian Tesche,Jakob De Geer,Akira Kurata,Marisa Lubbers,Joost Daemen,Lucian Itu,Saikiran Rapaka,Puneet Sharma,Chris Schwemmer,Anders Persson,Joseph Schoepf,Cezary Kępka,Dong Hyun Yang,Koen Nieman +16 more
TL;DR: In this article, a new machine learning-based CT-FFR algorithm has been developed based on a deep learning model, which can be performed on a regular workstation for detection of functionally obstructive coronary artery disease.
References
More filters
Book
Pattern Recognition and Machine Learning
TL;DR: Probability Distributions, linear models for Regression, Linear Models for Classification, Neural Networks, Graphical Models, Mixture Models and EM, Sampling Methods, Continuous Latent Variables, Sequential Data are studied.
Journal ArticleDOI
Pattern Recognition and Machine Learning
TL;DR: This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
Book
Learning Deep Architectures for AI
TL;DR: The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed.
Journal ArticleDOI
Fractional flow reserve versus angiography for guiding percutaneous coronary intervention
Bernard De Bruyne,Uwe Siebert,Fumiaki Ikeno,Volker Klauss,Ganesh Manoharan,Thomas Engstrøm,Keith G. Oldroyd,Peter N. Ver Lee,Philip MacCarthy,William F. Fearon +9 more
TL;DR: Routine measurement of FFR in patients with multivessel coronary artery disease who are undergoing PCI with drug-eluting stents significantly reduces the rate of the composite end point of death, nonfatal myocardial infarction, and repeat revascularization at 1 year.
Related Papers (5)
Diagnostic performance of noninvasive fractional flow reserve derived from coronary computed tomography angiography in suspected coronary artery disease: the NXT trial (Analysis of Coronary Blood Flow Using CT Angiography: Next Steps).
Bjarne L. Nørgaard,Jonathon Leipsic,Sara Gaur,Sujith Seneviratne,Brian Ko,Hiroshi Ito,Jesper M. Jensen,Laura Mauri,Bernard De Bruyne,Hiram G. Bezerra,Kazuhiro Osawa,Mohamed Marwan,Christoph Naber,Andrejs Erglis,Seung-Jung Park,Evald Høj Christiansen,Anne Kaltoft,Jens Flensted Lassen,Hans Erik Bøtker,Stephan Achenbach +19 more
Diagnostic Accuracy of Fractional Flow Reserve From Anatomic CT Angiography
James K. Min,Jonathon Leipsic,Michael J. Pencina,Daniel S. Berman,Bon-Kwon Koo,Carlos Van Mieghem,Andrejs Erglis,Fay Y. Lin,Allison Dunning,Patricia Apruzzese,Matthew J. Budoff,Jason H. Cole,Farouc A. Jaffer,Martin B. Leon,Martin B. Leon,Jennifer Malpeso,G.B. John Mancini,Seung-Jung Park,Robert S. Schwartz,Leslee J. Shaw,Laura Mauri +20 more