医学
线性判别分析
心脏淀粉样变性
磁共振成像
淀粉样变性
心脏磁共振
心脏病学
心肌病
内科学
病理
放射科
心力衰竭
人工智能
计算机科学
作者
Brendan L. Eck,Nicole Seiberlich,Scott D. Flamm,Jesse Hamilton,Abhilash Suresh,Yash Kumar,Mazen Hanna,Angel Houston,Derrek Tew,W.H. Wilson Tang,Deborah Kwon
标识
DOI:10.1016/j.ijcard.2021.12.038
摘要
Background Cardiac amyloidosis (CA) is an infiltrative cardiomyopathy with poor prognosis absent appropriate treatment. Elevated native myocardial T1 and T2 have been reported for CA, and tissue characterization by cardiac MRI may expedite diagnosis and treatment. Cardiac Magnetic Resonance Fingerprinting (cMRF) has the potential to enable tissue characterization for CA through rapid, simultaneous T1 and T2 mapping. Furthermore, cMRF signal timecourses may provide additional information beyond myocardial T1 and T2. Methods Nine CA patients and five controls were scanned at 3 T using a prospectively gated cMRF acquisition. Two cMRF-based analysis approaches were examined: (1) relaxometric-based linear discriminant analysis (LDA) using native T1 and T2, and (2) signal timecourse-based LDA. The Fisher coefficient was used to compare the separability of patient and control groups from both approaches. Leave-two-out cross-validation was employed to evaluate the classification error rates of both approaches. Results Elevated myocardial T1 and T2 was observed in patients vs controls (T1: 1395 ± 121 vs 1240 ± 36.4 ms, p < 0.05; T2: 36.8 ± 3.3 vs 31.8 ± 2.6 ms, p < 0.05). LDA scores were elevated in patients for relaxometric-based LDA (0.56 ± 0.28 vs 0.18 ± 0.13, p < 0.05) and timecourse-based LDA (0.97 ± 0.02 vs 0.02 ± 0.02, p < 0.05). The Fisher coefficient was greater for timecourse-based LDA (60.8) vs relaxometric-based LDA (1.6). Classification error rates were lower for timecourse-based LDA vs relaxometric-based LDA (12.6 ± 24.3 vs 22.5 ± 30.1%, p < 0.05). Conclusions These findings suggest that cMRF may be a valuable technique for the detection and characterization of CA. Analysis of cMRF signal timecourse data may improve tissue characterization as compared to analysis of native T1 and T2 alone.
科研通智能强力驱动
Strongly Powered by AbleSci AI