Journal
MEDICAL IMAGE ANALYSIS
Volume 77, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.media.2021.102333
Keywords
Intracranial aneurysms; Aneurysm detection; Aneurysm segmentation; Subarachnoid hemorrhage; X-ray rotational angiography; Machine learning; Rupture risk; Deep learning; CFD
Categories
Funding
- NVIDIA
- Deutsche Forschungsgemeinschaft (DFG) [DFG HA 5399/5-1, HE 7312/4-1, HE 1875/29-1]
- German Ministry for Education and Research (BMBF) [FKZ: 01IS18037E]
Ask authors/readers for more resources
The CADA challenge aimed to support the development and benchmarking of algorithms for detecting, analyzing, and assessing the risk of cerebral aneurysms in 3DRA images. Participants presented U-Net-based detection solutions with similar accuracy to experts and excellent delineation of these structures. The rupture risk estimation methods achieved good results. The best method pipeline showed comparable performance to the ground-truth delineation.
The Cerebral Aneurysm Detection and Analysis (CADA) challenge was organized to support the development and benchmarking of algorithms for detecting, analyzing, and risk assessment of cerebral aneurysms in X-ray rotational angiography (3DRA) images. 109 anonymized 3DRA datasets were provided for training, and 22 additional datasets were used to test the algorithmic solutions. Cerebral aneurysm detection was assessed using the F2 score based on recall and precision, and the fit of the delivered bounding box was assessed using the distance to the aneurysm. The segmentation quality was measured using the Jaccard index and a combination of different surface distance measures. Systematic errors were analyzed using volume correlation and bias. Rupture risk assessment was evaluated using the F2 score. 158 participants from 22 countries registered for the CADA challenge. The U-Net-based detection solutions presented by the community show similar accuracy compared to experts (F2 score 0.92), with a small number of missed aneurysms with diameters smaller than 3.5 mm. In addition, the delineation of these structures, based on U-Net variations, is excellent, with a Jaccard score of 0.92. The rupture risk estimation methods achieved an F2 score of 0.71. The performance of the detection and segmentation solutions is equivalent to that of human experts. The best results are obtained in rupture risk estimation by combining different image-based, morphological, and computational fluid dynamic parameters using machine learning methods. Furthermore, we evaluated the best methods pipeline, from detecting and delineating the vessel dilations to estimating the risk of rupture. The chain of these methods achieves an F2-score of 0.70, which is comparable to applying the risk prediction to the ground-truth delineation (0.71). (C) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available