Improving vessel graph matching in longitudinal angiographic images
Temporally Consistent Graph Extraction and Matching for Longitudinal Angiographic Images
Computer Vision and Pattern Recognition
Summary
Images of blood vessels help doctors see how vessels change over time, but tiny differences in image processing can make it hard to match the same vessels in different pictures. The authors propose a new method that matches vessel graphs early, before cleaning them up, using information from both images together. This approach better matches large vessel areas without breaking the graphs into pieces. They tested their method on detailed eye vessel images and found it works better than previous ways.
What this means in practice
- •For medical imaging teams: Enhance tracking of vascular changes in longitudinal angiographic images by improving vessel graph alignment and reducing segmentation artifacts.
- •For ophthalmology software developers: Develop retinal image analysis tools that better match blood vessel structures over time to assist in disease monitoring.
Authors
Linus Kreitner, Laurin Lux, Carmen Baumann, Daniel Rueckert, Martin J. Menten
Abstract
Recent advances in angiographic imaging have enabled longitudinal visualization of the microvasculature. Image processing pipelines based on vessel graphs are able to resolve subtle temporal changes at the level of individual blood vessels. However, current strategies for graph extraction, refinement, and matching are highly sensitive, with even minuscule differences in the underlying segmentation map resulting in substantially different vessel graphs. These artifacts severely inhibit the ability to accurately match sequential vessel graphs of the same subject over time. To address this problem, we propose a strategy that matches graphs before jointly refining them. Specifically, we perform an early matching after basic graph extraction before removing spurious bulges and merging junctions in both graphs using joint information. In experiments with complex retinal vessel graphs, we demonstrate that this strategy results in a higher matched area without graph fragmentation compared to separate or no refinement, respectively.