arXiv (Cornell University) · 2018 · 12 citations · 11 references
ComputingComputer ScienceRadiologyComputer VisionDiagnostic ImagingInterventional RadiologyDeep LearningImage SegmentationMedical Image AnalysisMedical ImagingOptical FlowSemantic SegmentationBinary SegmentationDeep Learning In RadiologyReal-time SegmentationReal-time Semantic SegmentationSegmentationSiamese NetworksVascular SegmentationVideo Semantic Segmentation
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.
11
Carsten Rother, Vladimir Kolmogorov, Andrew Blake · ACM Transactions on Graphics · 2004 · 5.8K citations · Full text
Shai Avidan · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2004 · 1.1K citations