Bettina Baeßler1, Manoj Mannil2, David Maintz3, Hatem Alkadhi4, Robert Manka5. 1. 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. 2. Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland. Electronic address: Manoj.Mannil@usz.ch. 3. Department of Radiology, University Hospital of Cologne, Kerpener Str. 62, D-50937, Cologne, Germany. Electronic address: david.maintz@uk-koeln.de. 4. Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland. Electronic address: Hatem.Alkadhi@usz.ch. 5. Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Raemistrasse 100, CH-8091, Zurich, Switzerland. Electronic address: Robert.Manka@usz.ch.
Abstract
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.
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.