Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping

Khalid Youssef; Xinheng Zhang; Ghazal Yoosefian; Yinyin Chen; Shing Fai Chan; Hsin-Jung Yang; Keyur Vora; Andrew Howarth; Andreas Kumar; Behzad Sharif; Rohan Dharmakumar

doi:10.1148/ryct.230338

Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping

Radiol Cardiothorac Imaging. 2024 Aug;6(4):e230338. doi: 10.1148/ryct.230338.

Authors

Affiliation

¹ From the Krannert Cardiovascular Research Center, Indiana University School of Medicine, IU Health Cardiovascular Institute, 1700 N Capitol Ave, E316, Indianapolis, IN 46202-1228 (K.Y., X.Z., G.Y., S.F.C., K.V., B.S., R.D.); University of California Los Angeles, Los Angeles, Calif (X.Z.); Zhongshan Hospital, Fudan University, Shanghai, China (Y.C.); Cedars-Sinai Medical Center, Los Angeles, Calif (H.J.Y.); Libin Cardiovascular Institute of Alberta, University of Calgary, Alberta, Canada (A.H.); and Northern Ontario School of Medicine University, Sudbury, Canada (A.K.).

Abstract

Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and t-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as data-driven native mapping (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; P < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; P = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (R² = 0.71 for native T1 maps vs LGE; R² = 0.85 for DNM vs LGE; P < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. Keywords: Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping Supplemental material is available for this article. © RSNA, 2024.

Keywords: Cardiac MRI; Chronic Myocardial Infarction; Data-Driven Native Contrast Mapping.

MeSH terms

Algorithms
Animals
Chronic Disease
Contrast Media*
Disease Models, Animal
Dogs
Female
Magnetic Resonance Imaging / methods
Male
Myocardial Infarction* / diagnostic imaging
Myocardial Infarction* / pathology
Reproducibility of Results

Substances

Contrast Media

Abstract

MeSH terms

Substances

Grants and funding