Related Experiment Video
Updated: Jun 29, 2026
Cardiac Magnetic Resonance for the Evaluation of Suspected Cardiac Thrombus: Conventional and Emerging Techniques
Published on: June 11, 2019
CardioRadNet: Cardiac mass diagnosis through integrated segmentation and radiomic analysis
Meri Ferretti1, Michele Pagliaccia2, Andrea Baggiano3
1Cardio Tech-Lab, Centro Cardiologico Monzino IRCCS, Via Carlo Parea 4, Milan 20138, Italy; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Via Golgi 39, Milan 20133, Italy.
Insights
CardioRadNet accurately classifies cardiac masses using contrast-free MRI and deep learning segmentation. This novel approach aids in distinguishing benign from malignant lesions, improving patient management.
Area of Science:
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
- Oncology
Background:
- Cardiac masses (CMs) encompass diverse benign and malignant lesions requiring tailored treatments.
- Previous studies often focus on limited classifications and manual segmentation, hindering comprehensive analysis.
- A need exists for advanced tools to accurately differentiate CM types using non-invasive imaging.
Purpose of the Study:
- Introduce CardioRadNet, an integrated framework for CM classification.
- Utilize deep learning segmentation and radiomics on contrast-free T1-weighted cardiac MRI.
- Differentiate benign from malignant cardiac masses effectively.
Main Methods:
- Developed a segmentation network with point-based guidance for mass delineation.
- Extracted radiomic features from manual and semiautomated segmented volumes.
- Optimized feature selection and classifier performance using 5-fold cross-validation.
Main Results:
- Achieved a Dice score of 0.78 for the segmentation network.
- Demonstrated good reproducibility (ICC > 0.6) for 88% of semiautomated radiomic features.
- Both classification models achieved a balanced accuracy of 0.85, with the semiautomated model reducing false negatives.
Conclusions:
- CardioRadNet provides an accurate, contrast-free method for comprehensive CM classification.
- The framework incorporates a full spectrum of CMs and uses semiautomated segmentation for clinical utility.
- This approach can be integrated into routine workflows as a decision-support tool for risk stratification and patient management.
Background And Objective:
Cardiac masses (CMs), though rare, include a wide spectrum of benign and malignant lesions that require distinct therapeutic strategies. Prior studies typically address narrow classification tasks (e.g., thrombus vs tumor) and rely on manually delineated regions. Building on these gaps, we introduce CardioRadNet: the first integrated framework combining deep learning segmentation and radiomics-based classification on contrast-free T1-weighted cardiac MR, designed to differentiate benign from malignant CMs.
Methods:
A total of 127 patients with pathologically confirmed CMs (62 malignant, 65 benign) were included. A segmentation network incorporating point-based guidance was developed for mass delineation. Radiomic features were extracted from both manually and semiautomatically segmented volumes, and two separate radiomics-based classification models were developed accordingly. Feature selection and classifier performance were optimized using a 5-fold cross-validation.
Results:
The segmentation network achieved a Dice score of 0.78, with 88% of the radiomic features extracted from the semiautomatic ROIs showing good reproducibility (ICC > 0.6) when compared with those derived from manual ROIs. The two models achieved identical balanced accuracy (0.85) and the same number of misclassifications (both used 10 features). Notably, the semiautomated ROI model yielded one fewer false negative, thereby reducing missed malignant cases.
Conclusion:
CardioRadNet offers a novel, accurate and contrast-free solution for comprehensive CM classification. Unlike prior studies, it includes the full spectrum of CMs and uses semiautomated segmentation for broader clinical applicability. Overall, this approach supports scalable integration into routine CMR workflows as a decision-support tool for early risk stratification and, in turn, improved patient management.
