PMID- 29685546 OWN - NLM STAT- MEDLINE DCOM- 20180827 LR - 20181202 IS - 1872-7727 (Electronic) IS - 0720-048X (Linking) VI - 102 DP - 2018 May TI - Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy-Preliminary results. PG - 61-67 LID - S0720-048X(18)30096-2 [pii] LID - 10.1016/j.ejrad.2018.03.013 [doi] AB - PURPOSE: To test in a first proof-of-concept study whether texture analysis (TA) allows for the detection of myocardial tissue alterations in hypertrophic cardiomyopathy (HCM) on non-contrast T1-weighted cardiac magnetic resonance (CMR) images using machine learning based approaches. METHODS: This retrospective, IRB-approved study included 32 patients with known HCM. Thirty patients with normal CMR served as controls. Regions-of-interest for TA encompassing the left ventricle were drawn on short-axis non-contrast T1-weighted images using a freely available software package. Step-wise dimension reduction and texture feature selection was performed for selecting features enabling the detection of myocardial tissue alterations in HCM patients on non-contrast T1-weighted CMR images. RESULTS: Comparing HCM patients and controls, four texture features were identified showing significant differences between groups (Grey-level Non-uniformity [GLevNonU]: 74 +/- 17 vs. 38 +/- 9, p < .001; Energy of wavelet coefficients in low-frequency sub-bands [WavEnLL]: 58 +/- 5 vs. 48 +/- 10, p < .001; Fraction: 0.70 +/- 0.07 vs. 0.78 +/- 0.05, p < .001; Sum Average: 16.6 +/- 0.4 vs. 17.0 +/- 0.5, p = .007). A model containing the single parameter GLevNonU proved to be the best for differentiating between HCM patients and controls with a sensitivity/specificity of 91%/93%. A cut-off of GLevNonU >/=46 allowed for distinguishing HCM patients from controls with a sensitivity/specificity of 94%/90%. Even in patients without late gadolinium enhancement (LGE), the defined cut-off led to a differentiation of LGE- patients from healthy controls with 100% sensitivity and 90% specificity. CONCLUSIONS: TA on non-contrast T1-weighted images allows for the detection of myocardial tissue alterations in the setting of HCM with excellent accuracy, delivering potential novel parameters for a non-contrast assessment of myocardial texture alterations. CI - Copyright (c) 2018 Elsevier B.V. All rights reserved. FAU - Baessler, Bettina AU - Baessler B AD - Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland; Department of Radiology, University Hospital of Cologne, Kerpener Str. 62, D-50937, Cologne, Germany. Electronic address: bettina.baessler@uk-koeln.de. FAU - Mannil, Manoj AU - Mannil M AD - Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland. Electronic address: Manoj.Mannil@usz.ch. FAU - Maintz, David AU - Maintz D AD - Department of Radiology, University Hospital of Cologne, Kerpener Str. 62, D-50937, Cologne, Germany. Electronic address: david.maintz@uk-koeln.de. FAU - Alkadhi, Hatem AU - Alkadhi H AD - Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland. Electronic address: Hatem.Alkadhi@usz.ch. FAU - Manka, Robert AU - Manka R AD - Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland. Electronic address: Robert.Manka@usz.ch. LA - eng PT - Journal Article DEP - 20180306 PL - Ireland TA - Eur J Radiol JT - European journal of radiology JID - 8106411 RN - 0 (Contrast Media) RN - 0 (Organometallic Compounds) RN - 1BJ477IO2L (gadobutrol) RN - AU0V1LM3JT (Gadolinium) SB - IM MH - Adult MH - Aged MH - Cardiomyopathy, Hypertrophic/*pathology MH - Contrast Media MH - Female MH - Fibrosis/pathology MH - Gadolinium MH - Heart Ventricles/pathology MH - Humans MH - Machine Learning MH - Magnetic Resonance Angiography/methods MH - Magnetic Resonance Imaging, Cine/methods MH - Male MH - Middle Aged MH - Myocardium/*pathology MH - Organometallic Compounds MH - Retrospective Studies MH - Sensitivity and Specificity OTO - NOTNLM OT - Cardiac magnetic resonance OT - HCM OT - Hypertrophic cardiomyopathy OT - Machine learning OT - Non-contrast imaging techniques OT - Texture analysis EDAT- 2018/04/25 06:00 MHDA- 2018/08/28 06:00 CRDT- 2018/04/25 06:00 PHST- 2017/11/06 00:00 [received] PHST- 2018/02/26 00:00 [revised] PHST- 2018/03/05 00:00 [accepted] PHST- 2018/04/25 06:00 [entrez] PHST- 2018/04/25 06:00 [pubmed] PHST- 2018/08/28 06:00 [medline] AID - S0720-048X(18)30096-2 [pii] AID - 10.1016/j.ejrad.2018.03.013 [doi] PST - ppublish SO - Eur J Radiol. 2018 May;102:61-67. doi: 10.1016/j.ejrad.2018.03.013. Epub 2018 Mar 6.