Top

European Radiology

Published in:

Open Access 01-05-2019 | Cardiac

Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis

Authors: Robbert W. van Hamersvelt, Majd Zreik, Michiel Voskuil, Max A. Viergever, Ivana Išgum, Tim Leiner

Published in: European Radiology | Issue 5/2019

Abstract

Objectives

To evaluate the added value of deep learning (DL) analysis of the left ventricular myocardium (LVM) in resting coronary CT angiography (CCTA) over determination of coronary degree of stenosis (DS), for identification of patients with functionally significant coronary artery stenosis.

Methods

Patients who underwent CCTA prior to an invasive fractional flow reserve (FFR) measurement were retrospectively selected. Highest DS from CCTA was used to classify patients as having non-significant (≤ 24% DS), intermediate (25–69% DS), or significant stenosis (≥ 70% DS). Patients with intermediate stenosis were referred for fully automatic DL analysis of the LVM. The DL algorithm characterized the LVM, and likely encoded information regarding shape, texture, contrast enhancement, and more. Based on these encodings, features were extracted and patients classified as having a non-significant or significant stenosis. Diagnostic performance of the combined method was evaluated and compared to DS evaluation only. Functionally significant stenosis was defined as FFR ≤ 0.8 or presence of angiographic high-grade stenosis (≥ 90% DS).

Results

The final study population consisted of 126 patients (77% male, 59 ± 9 years). Eighty-one patients (64%) had a functionally significant stenosis. The proposed method resulted in improved discrimination (AUC = 0.76) compared to classification based on DS only (AUC = 0.68). Sensitivity and specificity were 92.6% and 31.1% for DS only (≥ 50% indicating functionally significant stenosis), and 84.6% and 48.4% for the proposed method.

Conclusion

The combination of DS with DL analysis of the LVM in intermediate-degree coronary stenosis may result in improved diagnostic performance for identification of patients with functionally significant coronary artery stenosis.

Key Points

• Assessment of degree of coronary stenosis on CCTA has consistently high sensitivity and negative predictive value, but has limited specificity for identifying the functional significance of a stenosis.

• Deep learning algorithms are able to learn complex patterns and relationships directly from the images without prior specification of which image features represent presence of disease, and thereby may be more sensitive to subtle changes in the LVM caused by functionally significant stenosis.

• Addition of deep learning analysis of the left ventricular myocardium to the evaluation of degree of coronary artery stenosis improves diagnostic performance and increases specificity of resting CCTA. This could potentially decrease the number of patients undergoing invasive coronary angiography.

Available only for authorised users

Budoff MJ, Dowe D, Jollis JG et al (2008) Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease. J Am Coll Cardiol 52:1724–1732. https://doi.org/10.1016/j.jacc.2008.07.031 CrossRefPubMed

Meijboom WB, Van Mieghem CA, van Pelt N et al (2008) Comprehensive assessment of coronary artery stenoses: computed tomography coronary angiography versus conventional coronary angiography and correlation with fractional flow reserve in patients with stable angina. J Am Coll Cardiol 52:636–643. https://doi.org/10.1016/j.jacc.2008.05.024

Ko BS, Wong DT, Cameron JD et al (2014) 320-row CT coronary angiography predicts freedom from revascularisation and acts as a gatekeeper to defer invasive angiography in stable coronary artery disease: a fractional flow reserve-correlated study. Eur Radiol 24:738–747. https://doi.org/10.1007/s00330-013-3059-8 CrossRefPubMed

Tonino PA, De Bruyne B, Pijls NH et al (2009) Fractional flow reserve versus angiography for guiding percutaneous coronary intervention. N Engl J Med 360:213–224. https://doi.org/10.1056/NEJMoa0807611 CrossRef

Tesche C, De Cecco CN, Albrecht MH et al (2017) Coronary CT angiography–derived fractional flow reserve. Radiology 285:17–33. https://doi.org/10.1148/radiol.2017162641 CrossRefPubMed

Nørgaard BL, Leipsic J, Gaur S et al (2014) 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). J Am Coll Cardiol 63:1145–1155. https://doi.org/10.1016/J.Jacc.2013.11.043 CrossRefPubMed

Koo BK, Erglis A, Doh JH et al (2011) Diagnosis of ischemia-causing coronary stenoses by noninvasive fractional flow reserve computed from coronary computed tomographic angiograms. Results from the prospective multicenter DISCOVER-FLOW (Diagnosis of Ischemia-Causing Stenoses Obtained Via Noninvasive Fractional Flow Reserve) study. J Am Coll Cardiol 58:1989–1997. https://doi.org/10.1016/j.jacc.2011.06.066 CrossRefPubMed

Xiong G, Kola D, Heo R, Elmore K, Cho I, Min JK (2015) Myocardial perfusion analysis in cardiac computed tomography angiographic images at rest. Med Image Anal 24:77–89. https://doi.org/10.1016/j.media.2015.05.010

Han D, Lee JH, Rizvi A, et al (2017) Incremental role of resting myocardial computed tomography perfusion for predicting physiologically significant coronary artery disease: a machine learning approach. J Nucl Cardiol 25:223–233. https://doi.org/10.1007/s12350-017-0834-y

10.

Osawa K, Miyoshi T, Miki T et al (2016) Diagnostic performance of first-pass myocardial perfusion imaging without stress with computed tomography (CT) compared with coronary CT angiography alone, with fractional flow reserve as the reference standard. PLoS One 11:e0149170. https://doi.org/10.1371/journal.pone.0149170 CrossRefPubMedPubMedCentral

11.

Branch KR, Busey J, Mitsumori LM et al (2013) Diagnostic performance of resting CT myocardial perfusion in patients with possible acute coronary syndrome. AJR Am J Roentgenol 200:W450–W457. https://doi.org/10.2214/AJR.12.8934 CrossRefPubMedPubMedCentral

12.

Pursnani A, Lee AM, Mayrhofer T et al (2015) Early resting myocardial computed tomography perfusion for the detection of acute coronary syndrome in patients with coronary artery disease. Circ Cardiovasc Imaging 8:e002404–e002404. https://doi.org/10.1161/CIRCIMAGING.114.002404 CrossRefPubMedPubMedCentral

13.

Zreik M, Lessmann N, van Hamersvelt RW et al (2018) Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis. Med Image Anal 44:72–85. https://doi.org/10.1016/j.media.2017.11.008 CrossRefPubMed

14.

Mannil M, von Spiczak J, Manka R, Alkadhi H (2018) Texture analysis and machine learning for detecting myocardial infarction in noncontrast low-dose computed tomography. Invest Radiol 53:338–343. https://doi.org/10.1097/RLI.0000000000000448 CrossRefPubMed

15.

Ruzsics B, Lee H, Zwerner PL, Gebregziabher M, Costello P, Schoepf UJ (2008) Dual-energy CT of the heart for diagnosing coronary artery stenosis and myocardial ischemia-initial experience. Eur Radiol 18:2414–2424. https://doi.org/10.1007/s00330-008-1022-x

16.

Wang R, Yu W, Wang Y et al (2011) Incremental value of dual-energy CT to coronary CT angiography for the detection of significant coronary stenosis: comparison with quantitative coronary angiography and single photon emission computed tomography. Int J Cardiovasc Imaging 27:647–656. https://doi.org/10.1007/s10554-011-9881-7 CrossRefPubMed

17.

Ko BS, Cameron JD, Meredith IT et al (2012) Computed tomography stress myocardial perfusion imaging in patients considered for revascularization: a comparison with fractional flow reserve. Eur Heart J 33:67–77. https://doi.org/10.1093/eurheartj/ehr268 CrossRefPubMed

18.

Ko BS, Cameron JD, Leung M et al (2012) Combined CT coronary angiography and stress myocardial perfusion imaging for hemodynamically significant stenoses in patients with suspected coronary artery disease. JACC Cardiovasc Imaging 5:1097–1111. https://doi.org/10.1016/j.jcmg.2012.09.004 CrossRefPubMed

19.

Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248. https://doi.org/10.1146/annurev-bioeng-071516-044442 CrossRefPubMedPubMedCentral

20.

Shah SJ, Katz DH, Selvaraj S et al (2015) Phenomapping for novel classification of heart failure with preserved ejection fraction. Circulation 131:269–279. https://doi.org/10.1161/CIRCULATIONAHA.114.010637 CrossRefPubMed

21.

Abadi S, Roguin A, Engel A, Lessick J (2010) Feasibility of automatic assessment of four-chamber cardiac function with MDCT: initial clinical application and validation. Eur J Radiol 74:175–181. https://doi.org/10.1016/j.ejrad.2009.01.035 CrossRefPubMed

22.

Abbara S, Blanke P, Maroules CD et al (2016) SCCT guidelines for the performance and acquisition of coronary computed tomographic angiography: a report of the society of Cardiovascular Computed Tomography Guidelines Committee: endorsed by the North American Society for Cardiovascular Imaging (NASCI). J Cardiovasc Comput Tomogr 10:435–449. https://doi.org/10.1016/j.jcct.2016.10.002 CrossRef

23.

Leipsic J, Abbara S, Achenbach S et al (2014) SCCT guidelines for the interpretation and reporting of coronary CT angiography: a report of the Society of Cardiovascular Computed Tomography Guidelines Committee. J Cardiovasc Comput Tomogr 8:342–358. https://doi.org/10.1016/j.jcct.2014.07.003 CrossRef

24.

Cury RC, Abbara S, Achenbach S et al (2016) CAD-RADS^TM Coronary Artery Disease – Reporting and Data System. An expert consensus document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Radiology (ACR) and the North American Society for Cardiovascular Imaging (NASCI). Endorsed by the American College of Cardiology. J Cardiovasc Comput Tomogr 10:269–281. https://doi.org/10.1016/j.jcct.2016.04.005

25.

Windecker S, Kolh P, Alfonso F et al (2014) 2014 ESC/EACTS guidelines on myocardial revascularization. Eur Heart J 35:2541–2619. https://doi.org/10.1093/eurheartj/ehu278

26.

Takx RA, Blomberg BA, El Aidi H et al (2015) Diagnostic accuracy of stress myocardial perfusion imaging compared to invasive coronary angiography with fractional flow reserve meta-analysis. Circ Cardiovasc Imaging 8:e002666–e002666. https://doi.org/10.1161/CIRCIMAGING.114.002666

27.

Cook CM, Petraco R, Shun-Shin MJ et al (2017) Diagnostic accuracy of computed tomography–derived fractional flow reserve: a systematic review. JAMA Cardiol 2:803–810. https://doi.org/10.1001/jamacardio.2017.1314

28.

Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Comput. Vis. -- ECCV 2014 13th Eur. Conf. Zurich, Switzerland, Sept. 6–12, 2014, Proceedings, Part I. Springer International Publishing, Cham, pp 818–833

29.

Sarwar A, Rieber J, Mooyaart EA et al (2008) Calcified plaque: measurement of area at thin-section flat-panel CT and 64-section multidetector CT and comparison with histopathologic findings. Radiology 249:301–306. https://doi.org/10.1148/radiol.2483072003

Title: Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis
Authors: Robbert W. van Hamersvelt
Majd Zreik
Michiel Voskuil
Max A. Viergever
Ivana Išgum
Tim Leiner
Publication date: 01-05-2019
Publisher: Springer Berlin Heidelberg
Published in: European Radiology / Issue 5/2019
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-018-5822-3

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis

Abstract

Objectives

Methods

Results

Conclusion

Key Points

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusion

Key Points

Please log in to get access to this content

Other articles of this Issue 5/2019

Evaluation of elevated left ventricular end diastolic pressure in patients with preserved ejection fraction using cardiac magnetic resonance

Multicenter validation of the magnetic resonance T2* technique for quantification of pancreatic iron

Prognosis-based definition of left ventricular remodeling after ST-elevation myocardial infarction

Transhepatic forceps biopsy combined with biliary drainage in obstructive jaundice: safety and accuracy

Diabetes risk assessment with imaging: a radiomics study of abdominal CT

Multidetector CT findings differ between surgical grades of pancreatic fistula after pancreaticoduodenectomy