CardioRadNet: Cardiac mass diagnosis through integrated segmentation and radiomic analysis.

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.