Tags

Type your tag names separated by a space and hit enter

Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study.
Eur Radiol. 2018 Jun; 28(6):2655-2664.ER

Abstract

OBJECTIVES

We aimed to investigate if lesion-specific ischaemia by invasive fractional flow reserve (FFR) can be predicted by an integrated machine learning (ML) ischaemia risk score from quantitative plaque measures from coronary computed tomography angiography (CTA).

METHODS

In a multicentre trial of 254 patients, CTA and invasive coronary angiography were performed, with FFR in 484 vessels. CTA data sets were analysed by semi-automated software to quantify stenosis and non-calcified (NCP), low-density NCP (LD-NCP, < 30 HU), calcified and total plaque volumes, contrast density difference (CDD, maximum difference in luminal attenuation per unit area) and plaque length. ML integration included automated feature selection and model building from quantitative CTA with a boosted ensemble algorithm, and tenfold stratified cross-validation.

RESULTS

Eighty patients had ischaemia by FFR (FFR ≤ 0.80) in 100 vessels. Information gain for predicting ischaemia was highest for CDD (0.172), followed by LD-NCP (0.125), NCP (0.097), and total plaque volumes (0.092). ML exhibited higher area-under-the-curve (0.84) than individual CTA measures, including stenosis (0.76), LD-NCP volume (0.77), total plaque volume (0.74) and pre-test likelihood of coronary artery disease (CAD) (0.63); p < 0.006.

CONCLUSIONS

Integrated ML ischaemia risk score improved the prediction of lesion-specific ischaemia by invasive FFR, over stenosis, plaque measures and pre-test likelihood of CAD.

KEY POINTS

• Integrated ischaemia risk score improved prediction of ischaemia over quantitative plaque measures • Integrated ischaemia risk score showed higher prediction of ischaemia than standard approach • Contrast density difference had the highest information gain to identify lesion-specific ischaemia.

Authors+Show Affiliations

Biomedical Imaging Research Institute, Department of Biomedical Sciences, Cedars-Sinai Medical Center, Taper building, A238, 8700 Beverly Blvd, Los Angeles, 90048, USA. Damini.Dey@cshs.org.Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.Departments of Imaging and Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.Departments of Imaging and Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.Biomedical Imaging Research Institute, Department of Biomedical Sciences, Cedars-Sinai Medical Center, Taper building, A238, 8700 Beverly Blvd, Los Angeles, 90048, USA. Department of Cardiology, Friedrich-Alexander Universitat Erlangen-Nurnberg, Erlangen, Germany.Department of Cardiology, Friedrich-Alexander Universitat Erlangen-Nurnberg, Erlangen, Germany.Departments of Imaging and Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.Departments of Imaging and Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.Department of Cardiology, Friedrich-Alexander Universitat Erlangen-Nurnberg, Erlangen, Germany.Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.

Pub Type(s)

Clinical Trial
Journal Article
Multicenter Study

Language

eng

PubMed ID

29352380

Citation

Dey, Damini, et al. "Integrated Prediction of Lesion-specific Ischaemia From Quantitative Coronary CT Angiography Using Machine Learning: a Multicentre Study." European Radiology, vol. 28, no. 6, 2018, pp. 2655-2664.
Dey D, Gaur S, Ovrehus KA, et al. Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study. Eur Radiol. 2018;28(6):2655-2664.
Dey, D., Gaur, S., Ovrehus, K. A., Slomka, P. J., Betancur, J., Goeller, M., Hell, M. M., Gransar, H., Berman, D. S., Achenbach, S., Botker, H. E., Jensen, J. M., Lassen, J. F., & Norgaard, B. L. (2018). Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study. European Radiology, 28(6), 2655-2664. https://doi.org/10.1007/s00330-017-5223-z
Dey D, et al. Integrated Prediction of Lesion-specific Ischaemia From Quantitative Coronary CT Angiography Using Machine Learning: a Multicentre Study. Eur Radiol. 2018;28(6):2655-2664. PubMed PMID: 29352380.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study. AU - Dey,Damini, AU - Gaur,Sara, AU - Ovrehus,Kristian A, AU - Slomka,Piotr J, AU - Betancur,Julian, AU - Goeller,Markus, AU - Hell,Michaela M, AU - Gransar,Heidi, AU - Berman,Daniel S, AU - Achenbach,Stephan, AU - Botker,Hans Erik, AU - Jensen,Jesper Moller, AU - Lassen,Jens Flensted, AU - Norgaard,Bjarne Linde, Y1 - 2018/01/19/ PY - 2017/09/23/received PY - 2017/11/29/accepted PY - 2017/11/20/revised PY - 2018/1/21/pubmed PY - 2018/9/11/medline PY - 2018/1/21/entrez KW - Atherosclerotic plaque KW - Computed tomography angiography KW - Coronary stenosis KW - Ischaemia KW - Machine learning SP - 2655 EP - 2664 JF - European radiology JO - Eur Radiol VL - 28 IS - 6 N2 - OBJECTIVES: We aimed to investigate if lesion-specific ischaemia by invasive fractional flow reserve (FFR) can be predicted by an integrated machine learning (ML) ischaemia risk score from quantitative plaque measures from coronary computed tomography angiography (CTA). METHODS: In a multicentre trial of 254 patients, CTA and invasive coronary angiography were performed, with FFR in 484 vessels. CTA data sets were analysed by semi-automated software to quantify stenosis and non-calcified (NCP), low-density NCP (LD-NCP, < 30 HU), calcified and total plaque volumes, contrast density difference (CDD, maximum difference in luminal attenuation per unit area) and plaque length. ML integration included automated feature selection and model building from quantitative CTA with a boosted ensemble algorithm, and tenfold stratified cross-validation. RESULTS: Eighty patients had ischaemia by FFR (FFR ≤ 0.80) in 100 vessels. Information gain for predicting ischaemia was highest for CDD (0.172), followed by LD-NCP (0.125), NCP (0.097), and total plaque volumes (0.092). ML exhibited higher area-under-the-curve (0.84) than individual CTA measures, including stenosis (0.76), LD-NCP volume (0.77), total plaque volume (0.74) and pre-test likelihood of coronary artery disease (CAD) (0.63); p < 0.006. CONCLUSIONS: Integrated ML ischaemia risk score improved the prediction of lesion-specific ischaemia by invasive FFR, over stenosis, plaque measures and pre-test likelihood of CAD. KEY POINTS: • Integrated ischaemia risk score improved prediction of ischaemia over quantitative plaque measures • Integrated ischaemia risk score showed higher prediction of ischaemia than standard approach • Contrast density difference had the highest information gain to identify lesion-specific ischaemia. SN - 1432-1084 UR - https://www.unboundmedicine.com/medline/citation/29352380/Integrated_prediction_of_lesion_specific_ischaemia_from_quantitative_coronary_CT_angiography_using_machine_learning:_a_multicentre_study_ L2 - https://dx.doi.org/10.1007/s00330-017-5223-z DB - PRIME DP - Unbound Medicine ER -