Heart Region Segmentation using Dense VNet from Multimodality Images.

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Cardiovascular Research

Background:

• Cardiovascular diseases (CVD) are a leading global cause of mortality.
• Advanced medical imaging aids in early CVD detection and treatment planning.
• Accurate segmentation of heart substructures is crucial for patient-specific digital heart modeling.

Purpose of the Study:

• To implement Dense VNet for automated segmentation of heart substructures.
• To process multimodality data from CT and MRI.
• To address data scarcity using elastic deformation data augmentation.

Main Methods:

• Utilized Dense VNet architecture for image segmentation.
• Applied on-the-fly elastic deformation for data augmentation.
• Validated the approach on both CT and MRI datasets.

Main Results:

• Achieved superior performance in heart substructure detection compared to existing methods.
• Demonstrated the effectiveness of Dense VNet on multimodality imaging data.
• Showcased the utility of data augmentation in limited-data scenarios.

Conclusions:

• Dense VNet offers an efficient and accurate solution for heart substructure segmentation.
• The proposed method aids in creating patient-specific digital heart models.
• This approach has the potential to improve cardiovascular disease diagnosis and treatment.