MRI iUS Registration

MRI-ultrasound (US) registration aims to precisely align images from these two modalities, improving diagnostic accuracy and treatment planning in various medical applications. Current research focuses on developing robust and accurate registration algorithms, often employing deep learning architectures like Swin UNETR and novel approaches such as dense error map estimation and graph-based methods to handle challenges like brain shift and complex anatomical structures (e.g., ribs). These advancements are crucial for improving the accuracy of image-guided interventions, particularly in neurosurgery and robotic ultrasound procedures, leading to safer and more effective treatments. The ultimate goal is to provide clinicians with reliable, automated tools for image fusion, enhancing diagnostic confidence and surgical precision.