Related Experiment Video
Updated: Apr 24, 2026
08:12
A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage
Published on: July 28, 2018
9.4K
A system to detect cerebral aneurysms in multimodality angiographic data sets.
Clemens M Hentschke1, Oliver Beuing2, Harald Paukisch2
1Department of Simulation and Graphics, University of Magdeburg, 39106 Magdeburg, Germany.
Medical Physics
|September 5, 2014
Summary
An automated system effectively detects cerebral aneurysms in 3D angiographic data across multiple modalities. This computer-aided detection tool aids radiologists by achieving high sensitivity and finding small aneurysms.
Area of Science:
- Medical Imaging
- Radiology
- Computer-Aided Diagnosis
Background:
- Early detection of cerebral aneurysms is crucial for preventing subarachnoid hemorrhage.
- Multimodal 3D angiographic data (CE-MRA, TOF-MRA, CTA) are used for aneurysm visualization.
Purpose of the Study:
- To develop and evaluate an automated system for detecting cerebral aneurysms in multimodal 3D angiographic datasets.
- To assess the system's performance across different imaging modalities and compare expert vs. trained parametrization.
Main Methods:
- A multiscale sphere-enhancing filter identifies initial volumes of interest.
- A linear discriminant function (LDF) combines shape, spatial, and probability features to differentiate true aneurysms from false positives.
- Vessel segmentation is intentionally omitted to avoid influencing the detection algorithm.
Main Results:
- The system achieved 95% sensitivity across CE-MRA, TOF-MRA, and CTA modalities, with varying false positive rates (8.2, 11.3, and 22.8 FPDS, respectively).
- Expert parametrization yielded results comparable or superior to trained parametrization, negating the need for training.
- 93% of aneurysms smaller than 5 mm were detected, and the algorithm identified aneurysms missed by radiologists.
Conclusions:
- The developed automatic system serves as a valuable computer-aided detection tool for cerebral aneurysms.
- The system demonstrates suitability for assisting radiologists in the early and accurate identification of cerebral aneurysms.
