Real-time Wall Shear Stress Measurement on Chicken Embryo Heart Assisted by Automatic Localization Module and HRNet Using Spectral Domain Optical Coherence Tomography

Congenital heart disease, the most common birth defect in newborns and children, highlights the significance of understanding heart development. In the early development stage, the biomechanical environment, especially wall shear stress (WSS), plays a crucial role in heart morphogenesis. However, real-time measurement of WSS in the OFT of animal models remains challenging. Current algorithms for WSS measurement often struggle with issues such as low spatial resolution, long processing times, or limited applicability to in vivo environments. We propose a deep learning approach that combines an Automatic Localization Module with HRNet integrated with spectral domain optical coherence tomography (SD-OCT) to achieve real-time WSS calculation. Our approach accurately extracts the blood flow area from SD-OCT structure images by incorporating an automatic localization module. The proposed combination of HRNet and automatic localization allows for precise segmentation and real-time WSS measurement at 27 frames per second. Using the developed system, we successfully monitor in vivo WSS in the OFT of chicken embryos, providing valuable insights into embryonic heart development. The integration of deep learning with SD-OCT enables real-time and accurate WSS measurements, offering a powerful tool for studying congenital heart disease and heart morphogenesis.