Spatiotemporal Attention for Realtime Segmentation of Corrupted Sequential Ultrasound Data

Laura Graf, Sven Mischkewitz, Lasse Hansen, Mattias P. Heinrich


Image-guided diagnostics with AI assistance, e.g. compression-ultrasound for detecting deep vein thrombosis, requires stable, robust and real-time capable analysis algorithms that best support the user. When using anatomical segmentations for user guidance the spatiotemporal consistency is of great importance, but point-of-care modalities deliver signal which in many frames is hard to interpret. Since 2D+t models with 3D CNNs are not applicable for many mobile end devices,we propose a newspatiotemporal attention approach that re-uses deep backbone features from previous frames to learn and optimally fuse all available image information. Proof-of-concept experiments demonstrate an improvement of over 8% for the segmentation compared to simpler 2D+t models (using several frames as multi-channel input).
Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2022 - BVM 2022
Number of pages6
Publication date01.02.2022
Publication statusPublished - 01.02.2022
EventGerman Workshop on Medical Image Computing 2022 - Heidelberg, Germany
Duration: 26.06.202228.06.2022

Research Areas and Centers

  • Centers: Center for Artificial Intelligence Luebeck (ZKIL)


Dive into the research topics of 'Spatiotemporal Attention for Realtime Segmentation of Corrupted Sequential Ultrasound Data'. Together they form a unique fingerprint.

Cite this