Ultrasound Computed Tomography

Ultrasound computed tomography (USCT) aims to create high-resolution 3D ultrasound images by leveraging the full waveform information of ultrasound signals, surpassing the capabilities of conventional ultrasound. Current research focuses on accelerating USCT image reconstruction, primarily by employing deep learning techniques such as neural networks (including encoder-decoder architectures and neural operators) to improve speed and efficiency, even with limited data acquisition. These advancements address the current limitations of USCT, such as long scan times and high computational costs, making it a more viable and potentially transformative tool for medical imaging, particularly in applications like breast cancer detection.