Deep learning model for cardiac right ventricular volume quantification
This technology is an attention-based deep learning for cardiac right ventricular volume quantification using 2D echocardiography.
Unmet Need: Low-cost, widely available tools for measurements of ventricle volume
To diagnose cardiac diseases, doctors often need accurate measurements of the ventricular structure of the heart. However, the gold standard for ventricle quantification, cardiovascular magnetic resonance imaging (CMRI), has limited availability, while alternative imaging techniques, such as two-dimensional transthoracic echocardiography (2DE), are typically inaccurate due to the complex geometry of the ventricles.
The Technology: Deep learning model for accurate right ventricular volume quantification
This technology describes a deep learning method, namely an attention-based deep learning network, capable of interpreting two-dimensional transthoracic echocardiography for quantification of right ventricular structure. This enables the use of this 2D echocardiography for accurate prediction of ventricular volume, even when compared to cardiovascular magnetic resonance imaging (CMRI). This, in turn, can improve the availability of cardiac imaging by increasing the effectiveness of widely available echocardiography as a technique.
This technology has been tested with a retrospective study of 50 patients.
Applications:
- Clinical tools to diagnose cardiac ventricular abnormalities, specifically the right ventricle
- Research tool for studying cardiac abnormalities, specifically the right ventricle
- Training tool for clinicians learning echocardiography
Advantages:
- Based on widely used technology, two-dimensional transthoracic echocardiography (2DE)
- Cheaper technology with improved accuracy
- Easy workflow integration
Lead Inventor:
Polydoros Kampaktsis, M.D., Ph.D.
Patent Information:
Patent Pending (WO/2024/249863)
Related Publications:
Tech Ventures Reference:
IR CU23237
Licensing Contact: Joan Martinez