Related Experiment Video
Updated: Jul 23, 2025
Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging
Published on: May 24, 2021
Deep Learning for Discrimination of Hypertrophic Cardiomyopathy and Hypertensive Heart Disease on MRI Native T1 Maps
Zi-Chen Wang1, Zhang-Zhengyi Fan1, Xi-Yuan Liu1
1Ottawa-Shanghai Joint School of Medicine, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
Insights
Deep learning (DL) effectively differentiates hypertrophic cardiomyopathy (HCM) from hypertensive heart disease (HHD) using T1 mapping images. This automated DL approach shows superior diagnostic performance compared to native T1 and radiomics methods.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Distinguishing hypertrophic cardiomyopathy (HCM) from hypertensive heart disease (HHD) is clinically important.
- Previous methods like native T1 and radiomics have limitations in differentiating these conditions.
- Deep learning (DL) has shown promise in medical image analysis but its application in HCM vs. HHD differentiation is unexplored.
Purpose of the Study:
- To investigate the feasibility of using DL for differentiating HCM and HHD based on T1 mapping images.
- To compare the diagnostic performance of DL models against conventional methods (native T1 and radiomics).
Main Methods:
- A retrospective study involving 128 HCM and 59 HHD patients.
- Utilized 3.0T MRI with native T1 mapping sequences.
- Developed and tested DL models (ResNet32) using different input strategies (myocardial ring, bounding box, surrounding tissue).
- Compared DL performance with native T1 values and radiomics features extracted using Extra Trees Classifier.
Main Results:
- DL models achieved Area Under the Curve (AUC) values ranging from 0.766 to 0.830 in the testing set.
- The DL-myo model demonstrated the highest AUC of 0.830.
- Conventional native T1 analysis yielded an AUC of 0.545, while radiomics achieved an AUC of 0.800.
- DL models outperformed native T1 and showed comparable or superior performance to radiomics.
Conclusions:
- DL models based on T1 mapping images show capability in differentiating HCM and HHD.
- The DL approach offers superior diagnostic performance compared to native T1 analysis.
- DL provides an advantage over radiomics due to its automated nature and high specificity.
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.
Related Concept Videos
01:24Magnetic Resonance Imaging
01:21Imaging Studies for Cardiovascular System IV: CMRI
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy