Tricuspid valve flow measurement using a deep learning framework for automated valve‐tracking 2D phase contrast

• Published in: Magnetic resonance in medicine Vol. 92; no. 5; pp. 1838 - 1850
• Main Authors: Lamy, Jérôme, Gonzales, Ricardo A., Xiang, Jie, Seemann, Felicia, Huber, Steffen, Steele, Jeremy, Wieben, Oliver, Heiberg, Einar, Peters, Dana C.
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.11.2024
• Subjects: Adult; Algorithms; Aorta; Automation; Bias; Blood Flow Velocity; Correlation coefficients; Deep Learning; Diastole; Echocardiography; Engineering and Technology; Female; Flow measurement; Flow velocity; Humans; Image acquisition; Image contrast; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted - methods; Magnetic Resonance Imaging, Cine - methods; Male; Measurement methods; Medical Engineering; Medical Image Processing; Medical Imaging; Medicinsk bildbehandling; Medicinsk bildvetenskap; Medicinteknik; Middle Aged; Phase contrast; Regurgitation; Reproducibility of Results; slice-following; Stroke Volume - physiology; Systole; Systole - physiology; Teknik; Tracking; Tricuspid valve; Tricuspid Valve - diagnostic imaging; Two dimensional flow; Velocity; Ventricle; deep learning; tricuspid valve; phase contrast; slice‐following; regurgitation

Tricuspid valve flow velocities are challenging to measure with cardiovascular MR, as the rapidly moving valvular plane prohibits direct flow evaluation, but they are vitally important to diastolic function evaluation. We developed an automated valve-tracking 2D method for measuring flow through the...