Improved centerline tree detection of diseased peripheral arteries with a cascading algorithm for vascular segmentation
Kristína Lidayová1, Hans Frimmel2, Ewert Bengtsson1
1Uppsala University, Centre for Image Analysis, Division of Visual Information and Interaction, Uppsala, Sweden.
Insights
A new cascading algorithm accurately detects vascular centerlines in diseased peripheral arteries, aiding in peripheral arterial disease assessment. This method improves segmentation for challenging cases like stenosis and occlusion.
Area of Science:
- Medical Imaging
- Radiology
- Computer-Aided Diagnosis
Background:
- Vascular segmentation is crucial for diagnosing peripheral arterial disease (PAD).
- Segmentation is particularly difficult in cases of severe arterial stenosis or occlusion.
- Accurate centerline detection is essential for facilitating vascular segmentation.
Purpose of the Study:
- To present a novel cascading algorithm for vascular centerline tree detection.
- To specialize the algorithm for detecting centerlines in diseased peripheral arteries, including those with stenosis and occlusion.
- To improve the accuracy and efficiency of vascular segmentation in PAD assessment.
Main Methods:
- A four-level cascading algorithm was developed for vascular centerline tree detection.
- Two levels target healthy arteries of varying sizes, while two address pathologies like calcification and occlusion.
- Key steps include automatic parameter selection, voxel detection, connectivity analysis, and centerline tree correction.
Main Results:
- The algorithm achieved an average overlap rate of 89% and a detection rate of 82% on 25 lower limb CTA scans.
- Average execution time was 70 seconds using four CPU cores.
- The method successfully detected very distal artery branches, including those in the foot.
Conclusions:
- The proposed cascading algorithm effectively detects vascular centerlines in diseased peripheral arteries.
- This technique enhances the acceleration and facilitation of vascular segmentation for PAD assessment.
- The algorithm demonstrates high accuracy and efficiency, even in complex pathological cases.
Abstract:
Vascular segmentation plays an important role in the assessment of peripheral arterial disease. The segmentation is very challenging especially for arteries with severe stenosis or complete occlusion. We present a cascading algorithm for vascular centerline tree detection specializing in detecting centerlines in diseased peripheral arteries. It takes a three-dimensional computed tomography angiography (CTA) volume and returns a vascular centerline tree, which can be used for accelerating and facilitating the vascular segmentation. The algorithm consists of four levels, two of which detect healthy arteries of varying sizes and two that specialize in different types of vascular pathology: severe calcification and occlusion. We perform four main steps at each level: appropriate parameters for each level are selected automatically, a set of centrally located voxels is detected, these voxels are connected together based on the connection criteria, and the resulting centerline tree is corrected from spurious branches. The proposed method was tested on 25 CTA scans of the lower limbs, achieving an average overlap rate of 89% and an average detection rate of 82%. The average execution time using four CPU cores was 70 s, and the technique was successful also in detecting very distal artery branches, e.g., in the foot.
More Related Videos
Related Concept Videos
01:21Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation
01:19Imaging Studies VII: Vascular Imaging