LAUSR

BACKGROUND Intracranial aneurysms are life-threatening disease. Their rupture can lead to hemorrhagic stroke. Most studies applying deep learning for detection of aneurysms are based on angiographic images. However, critical diagnostic information such as morphology and aneurysm location are not captured by deep learning algorithms and still require manual assessments. PURPOSE Digital subtraction angiography (DSA) is the gold standard for aneurysm diagnosis. To facilitate fully automatic diagnosis of aneurysms, we proposed a comprehensive system for the detection, morphology measurement and location classification of aneurysms on 3-Dimensional DSA images, allowing automatic diagnosis without further human input. METHODS The system was comprised of three neural networks: a network for aneurysm detection, a network for morphology measurement and a network for aneurysm location identification. A cross-scale dual-path transformer module was proposed to effectively fuse local and global information to capture aneurysms of varying size. A multitask learning approach was also proposed to allow accurate localization of aneurysm neck for morphology measurement. RESULTS The cross-scale dual-path transformer module was shown to outperform other state-of-the-art network architectures, improving segmentation and classification accuracy. The detection network in our system achieved an F2 score of 0.946 (recall 93%, precision 100%), better than the winning team in the Cerebral Aneurysm Detection and Analysis (CADA) challenge. The measurement network achieved a relative error of less than 10% for morphology measurement, at the same level as human operators. Perfect accuracy (100%) was achieved on aneurysm location classification. CONCLUSIONS We have demonstrated that a comprehensive system can automatically detect, measure morphology and report aneurysm location of aneurysms without human intervention. This can be a potential tool for the diagnosis of intracranial aneurysms, improving radiologists' performance and reducing their workload. This article is protected by copyright. All rights reserved.