Cerebral Aneurysm Detection and Analysis Challenge 2020 (CADA)

Abstract

Rupture of an intracranial aneurysm often results in subarachnoid hemorrhage, a life-threatening condition with high mortality and morbidity. The Cerebral Aneurysm Detection and Analysis (CADA) competition was organized to support the development and benchmarking of algorithms for the detection, analysis, 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. Segmentation quality was measured using Jaccard and a combination of different surface distance measurements. 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 CADAchallenge. The detection solutions presented by the community are mostly accurate (F2 score 0.92) with a small number of missed aneurysms with diameters of 3.5 mm. In addition, the delineation of these structures is very good with a Jaccard score of 0.915. The rupture risk estimation methods achieved an F2 score of 0.7. The performance of the detection and segmentation solutions is equivalent to that of human experts. In rupture risk estimation, the best results are obtained by combining different image-based, morphological and computational fluid dynamic parameters using machine learning methods.

High-throughput 3DRA segmentation of brain vasculature and aneurysms using deep learning

“…Table 6). Our segmentation method yielded results close to the championship method [27]. For in silico clinical trials, the accuracy of aneurysm localization is as important as Dice and Surface-to-surface error.…”

“…The test sets in different cross-validation experiments traverse the entire data set. We also trained and evaluated our approach on a publicly available dataset, CADA [27], which comprises computerized tomography (CT) images of patients with cerebral aneurysms. These images were acquired as part of the Cerebral Aneurysm Detection and Analysis challenge, hosted at the international conference on medical image computing and computer-assisted interventions in 2020.…”

“…We comprehensively evaluated the proposed approach across two 3DRA datasets: an in-house multi-center @neurIS dataset [26] and a publicly available cerebral aneurysm detection and analysis dataset (CADA) [27].…”

Segmentation Method of Cerebral Aneurysms Based on Entropy Selection Strategy

“…The MICCAI 2020 CADA challenge provided 109 cases. Image data of patients with cerebral aneurysms without vasospasm were collected for the purpose of assisting diagnosis and treatment [ 32 ]. The image data were acquired utilizing the digital subtraction AXIOM Artis C-arm system.…”