Related Experiment Video
Updated: Oct 10, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Heart Region Segmentation using Dense VNet from Multimodality Images
Insights
This study introduces Dense VNet for segmenting heart substructures from CT and MRI scans, improving diagnostic accuracy for cardiovascular diseases (CVD). The method enhances patient-specific digital heart modeling and outperforms existing techniques.
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.
Abstract:
Cardiovascular diseases (CVD) have been identified as one of the most common causes of death in the world. Advanced development of imaging techniques is allowing timely detection of CVD and helping physicians in providing correct treatment plans in saving lives. Segmentation and Identification of various substructures of the heart are very important in modeling a digital twin of the patient-specific heart. Manual delineation of various substructures of the heart is tedious and time-consuming. Here we have implemented Dense VNet for detecting substructures of the heart from both CT and MRI multimodality data. Due to the limited availability of data we have implemented an on-the-fly elastic deformation data augmentation technique. The result of the proposed has been shown to outperform other methods reported in the literature on both CT and MRI datasets.
