Fitting tree model with CNN and geodesics to track vesselsand application to Ultrasound Localization Microscopy data
This work addresses segmentation of vascular networks for medical imaging applications, but it is incremental as it builds on existing methods for tree-like structures.
The paper tackled the problem of segmenting tubular structures in vascular imaging by detecting landmarks with a CNN and representing vessels as edges in a minimal distance tree graph using geodesic methods. Results indicated that while scarce annotated ULM data hindered landmark localization, the Orientation Score from ULM data provided effective geodesics for tracking blood vessels.
Segmentation of tubular structures in vascular imaging is a well studied task, although it is rare that we try to infuse knowledge of the tree-like structure of the regions to be detected. Our work focuses on detecting the important landmarks in the vascular network (via CNN performing both localization and classification of the points of interest) and representing vessels as the edges in some minimal distance tree graph. We leverage geodesic methods relevant to the detection of vessels and their geometry, making use of the space of positions and orientations so that 2D vessels can be accurately represented as trees. We build our model to carry tracking on Ultrasound Localization Microscopy (ULM) data, proposing to build a good cost function for tracking on this type of data. We also test our framework on synthetic and eye fundus data. Results show that scarcity of well annotated ULM data is an obstacle to localization of vascular landmarks but the Orientation Score built from ULM data yields good geodesics for tracking blood vessels.