Improving Accuracy in Coronary Lumen Segmentation via Explicit Calcium Exclusion, Learning-based Ray Detection and Surface Optimization
Since the diagnostic value of non-invasive procedures for diagnosing CAD relies on an accurate extraction of the lumen, a precise segmentation of the coronary arteries is crucial. As manual segmentation is tedious, time-consuming and subjective, automatic procedures are desirable. We present a novel fully-automatic method to accurately segment the lumen of coronary arteries in the presence of calcified and non-calcified plaque. Our segmentation framework is based on three main steps: boundary detection, calcium exclusion and surface optimization. A learning-based boundary detector enables a robust lumen contour detection via dense ray-casting. The exclusion of calcified plaque is assured through a novel calcium exclusion technique which allows us to accurately capture stenoses of diseased arteries. The boundary detection results are then incorporated into a closed set formulation whose minimization yields an optimized lumen surface. On the standardized Rotterdam evaluation framework, a segmentation accuracy is achieved which is comparable to clinical experts and superior to current automatic methods. Averaged over 30 datasets, we obtain a DICE overlap of 74 (73)%, an MSD of 0.35 (0.55) mm and MAXSD of 2.99 (3.73) mm on diseased (healthy) vessel segments as compared to three medical experts.
Detection confusion tables
|Calc. cat.||QCA (per segment)||CTA (per lesion)|
The results of this method are based on the following centerlines: own or none.
Detection (QCA per segment / CTA per lesion)
| ||%||rank||%||rank||%||rank||%||rank|| |
|0 (0 - 0.1)||60.0||4.0||30.0||4.0||57.1||5.0||33.3||6.0||4.8|
|1 (0.1 - 10)||100.0||1.0||25.0||5.0||40.0||11.0||28.6||10.0||6.8|
|2 (11 - 100)||42.9||11.0||30.0||6.0||27.3||14.0||21.4||10.0||10.2|
|3 (101 - 400)||80.0||3.0||25.8||8.0||57.9||4.0||29.7||9.0||6.0|
These results are based on 30 datasets and 19 submissions.
Avg. Abs. diff.
| ||%||rank||%||rank||Κ||rank|| |
|0 (0 - 0.1)||42.6||10.0||48.7||10.0||0.28||6.0||8.0|
|1 (0.1 - 10)||37.2||11.0||40.7||11.0||0.26||7.0||9.0|
|2 (11 - 100)||46.4||10.0||53.7||11.0||0.30||7.0||8.8|
|3 (101 - 400)||47.5||10.0||52.8||10.0||0.32||6.0||8.0|