Deep Segmentation and Registration in X-Ray Angiography Video
This addresses the need for precise vessel and instrument localization in interventional radiology, though it appears incremental as it builds on existing U-Net methods.
The paper tackles real-time segmentation of vein structures in X-ray angiography videos to aid medical personnel, achieving a processing speed of 90fps and significantly improving state-of-the-art U-Net performance.
In interventional radiology, short video sequences of vein structure in motion are captured in order to help medical personnel identify vascular issues or plan intervention. Semantic segmentation can greatly improve the usefulness of these videos by indicating exact position of vessels and instruments, thus reducing the ambiguity. We propose a real-time segmentation method for these tasks, based on U-Net network trained in a Siamese architecture from automatically generated annotations. We make use of noisy low level binary segmentation and optical flow to generate multi class annotations that are successively improved in a multistage segmentation approach. We significantly improve the performance of a state of the art U-Net at the processing speeds of 90fps.