Related Experiment Video
Updated: Jun 20, 2026
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Knowledge-Augmented Deep Learning for Segmenting and Detecting Cerebral Aneurysms With CT Angiography: A Multicenter
Jianyong Wei1, Xinyu Song1, Xiaoer Wei1
1From the Clinical Research Center (J.W.) and Institute of Diagnostic and Interventional Radiology, Department of Radiology (X.S., X.W., L.D., Z.S., Y. Zhu, Y.L.), Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, No. 600 Yi Shan Rd, Shanghai 200233, China; School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China (J.W., M.W., Y.J.); Shukun (Beijing) Network Technology, Beijing, China (Zhiwen Yang, C.M.); Department of Radiology, The First Affiliated Hospital of Soochow University, Jiangsu, China (C.H.); Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China (X.X.); Department of Cardiology, Beijing Friendship Hospital of Capital Medical University, Beijing, China (Zhenghan Yang); Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China (Y. Zhang); Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China (F.L.); and Department of Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China (J.L.).
A new deep learning model accurately detects cerebral aneurysms on CT angiography (CTA) scans, matching radiologist performance. This AI tool could streamline diagnosis for this challenging condition.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiology
Background:
- Deep learning (DL) offers potential to improve labor-intensive cerebral aneurysm diagnosis.
- Accurate diagnosis requires large, multicenter datasets for DL model development.
- Current methods for cerebral aneurysm detection and segmentation are challenging.
Purpose of the Study:
- To develop a DL model for accurate cerebral aneurysm segmentation and detection on CT angiography (CTA) images.
- To compare the DL model's performance against radiology reports.
- To utilize a multicenter dataset for robust model construction.
Main Methods:
- Retrospective collection of head/head and neck CTA images from eight hospitals (n=6060) for model development.
- External validation using digital subtraction angiography (DSA) scans (n=118) as the reference standard.
- Performance evaluation using Dice Similarity Coefficient (DSC) for segmentation and sensitivity/AUC for detection, compared to radiologists.
Main Results:
- The DL model achieved a DSC of 0.87 for aneurysm segmentation in the internal test set.
- In external validation, the model demonstrated 85.7% sensitivity for aneurysm detection (per-vessel analysis).
- No significant difference in detection performance was found between the DL model (AUC=0.93) and radiology reports (AUC=0.91).
Conclusions:
- The developed DL model accurately segments and detects cerebral aneurysms on CTA.
- The model's diagnostic performance is comparable to that of radiology reports.
- This AI tool processes scans rapidly, potentially aiding clinical workflows.
