Differential Diagnosis of Thick Myocardium according to Histologic Features Revealed by Multiparametric Cardiac Magnetic Resonance Imaging

Deep Learning for Discrimination of Hypertrophic Cardiomyopathy and Hypertensive Heart Disease on MRI Native T1 Maps

BACKGROUND

Native T1 and radiomics were used for hypertrophic cardiomyopathy (HCM) and hypertensive heart disease (HHD) differentiation previously. The current problem is that global native T1 remains modest discrimination performance and radiomics requires feature extraction beforehand. Deep learning (DL) is a promising technique in differential diagnosis. However, its feasibility for discriminating HCM and HHD has not been investigated.

PURPOSE

To examine the feasibility of DL in differentiating HCM and HHD based on T1 images and compare its diagnostic performance with other methods.

STUDY TYPE

Retrospective.

POPULATION

128 HCM patients (men, 75; age, 50 years ± 16) and 59 HHD patients (men, 40; age, 45 years ± 17).

FIELD STRENGTH/SEQUENCE

3.0T; Balanced steady-state free precession, phase-sensitive inversion recovery (PSIR) and multislice native T1 mapping.

ASSESSMENT

Compare HCM and HHD patients baseline data. Myocardial T1 values were extracted from native T1 images. Radiomics was implemented through feature extraction and Extra Trees Classifier. The DL network is ResNet32. Different input including myocardial ring (DL-myo), myocardial ring bounding box (DL-box) and the surrounding tissue without myocardial ring (DL-nomyo) were tested. We evaluate diagnostic performance through AUC of ROC curve.

STATISTICAL TESTS

Accuracy, sensitivity, specificity, ROC, and AUC were calculated. Independent t test, Mann-Whitney U-test and Chi-square test were adopted for HCM and HHD comparison. P < 0.05 was considered statistically significant.

RESULTS

DL-myo, DL-box, and DL-nomyo models showed an AUC (95% confidential interval) of 0.830 (0.702-0.959), 0.766 (0.617-0.915), 0.795 (0.654-0.936) in the testing set. AUC of native T1 and radiomics were 0.545 (0.352-0.738) and 0.800 (0.655-0.944) in the testing set.

DATA CONCLUSION

The DL method based on T1 mapping seems capable of discriminating HCM and HHD. Considering diagnostic performance, the DL network outperformed the native T1 method. Compared with radiomics, DL won an advantage for its high specificity and automated working mode.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 2.

Utilities and Limitations of Cardiac Magnetic Resonance Imaging in Dilated Cardiomyopathy

Dilated cardiomyopathy (DCM) is one of the most common types of non-ischemic cardiomyopathy. DCM is characterized by left ventricle (LV) dilatation and systolic dysfunction without coronary artery disease or abnormal loading conditions. DCM is not a single disease entity and has a complex historical background of revisions and updates to its definition because of its diverse etiology and clinical manifestations. In cases of LV dilatation and dysfunction, conditions with phenotypic overlap should be excluded before establishing a DCM diagnosis. The differential diagnoses of DCM include ischemic cardiomyopathy, valvular heart disease, burned-out hypertrophic cardiomyopathy, arrhythmogenic cardiomyopathy, and non-compaction. Cardiac magnetic resonance (CMR) imaging is helpful for evaluating DCM because it provides precise measurements of cardiac size, function, mass, and tissue characterization. Comprehensive analyses using various sequences, including cine imaging, late gadolinium enhancement imaging, and T1 and T2 mapping, may help establish differential diagnoses, etiological work-up, disease stratification, prognostic determination, and follow-up procedures in patients with DCM phenotypes. This article aimed to review the utilities and limitations of CMR in the diagnosis and assessment of DCM.

Mitochondrial Cardiomyopathy: Molecular Epidemiology, Diagnosis, Models, and Therapeutic Management

Mitochondrial cardiomyopathy (MCM) is characterized by abnormal heart-muscle structure and function, caused by mutations in the nuclear genome or mitochondrial DNA. The heterogeneity of gene mutations and various clinical presentations in patients with cardiomyopathy make its diagnosis, molecular mechanism, and therapeutics great challenges. This review describes the molecular epidemiology of MCM and its clinical features, reviews the promising diagnostic tests applied for mitochondrial diseases and cardiomyopathies, and details the animal and cellular models used for modeling cardiomyopathy and to investigate disease pathogenesis in a controlled in vitro environment. It also discusses the emerging therapeutics tested in pre-clinical and clinical studies of cardiac regeneration.