Evaluation of an automated intracranial aneurysm detection and rupture analysis approach using cascade detection and classification networks

• Published in: Computerized medical imaging and graphics Vol. 102; p. 102126
• Main Authors: Wu, Ke, Gu, Dongdong, Qi, Peihong, Cao, Xiaohuan, Wu, Dijia, Chen, Lei, Qu, Guoxiang, Wang, Jiayu, Pan, Xianpan, Wang, Xuechun, Chen, Yuntian, Chen, Lizhou, Xue, Zhong, Lyu, Jinhao
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.12.2022
• Subjects: Aged; Aneurysm, Ruptured - diagnostic imaging; Angiography, Digital Subtraction - methods; Cascade detection model; Cerebral Angiography - methods; Feature pyramid network; Humans; Internal Medicine; Intracranial aneurysm; Intracranial Aneurysm - diagnostic imaging; Other; Rupture analysis; Sensitivity and Specificity; Cascade detection model; Feature pyramid network; Rupture analysis; Intracranial aneurysm
• ISSN: 0895-6111; 1879-0771; 1879-0771
• DOI: 10.1016/j.compmedimag.2022.102126

Intracranial aneurysm is commonly found in human brains especially for the elderly, and its rupture accounts for a high rate of subarachnoid hemorrhages. However, it is time-consuming and requires special expertise to pinpoint small aneurysms from computed tomography angiography (CTA) images. Deep learning-based detection has helped improve much efficiency but false-positives still render difficulty to be ruled out. To study the feasibility of deep learning algorithms for aneurysm analysis in clinical applications, this paper proposes a pipeline for aneurysm detection, segmentation, and rupture classification and validates its performance using CTA images of 1508 subjects. A cascade aneurysm detection model is employed by first using a fine-tuned feature pyramid network (FPN) for candidate detection and then applying a dual-channel ResNet aneurysm classifier to further reduce false positives. Detected aneurysms are then segmented by applying a traditional 3D V-Net to their image patches. Radiomics features of aneurysms are extracted after detection and segmentation. The machine-learning-based and deep learning-based rupture classification can be used to distinguish ruptured and un-ruptured ones. Experimental results show that the dual-channel ResNet aneurysm classifier utilizing image and vesselness information helps boost sensitivity of detection compared to single image channel input. Overall, the proposed pipeline can achieve a sensitivity of 90 % for 1 false positive per image, and 95 % for 2 false positives per image. For rupture classification the area under curve (AUC) of 0.906 can be achieved for the testing dataset. The results suggest feasibility of the pipeline for potential clinical use to assist radiologists in aneurysm detection and classification of ruptured and un-ruptured aneurysms. •Proposed an aneurysm detection and analysis pipeline based on a cascade model of FPN and ResNet classification with CTA images.•Taking vesselness features as additional channels to improve the performance of FPN-classification networks•Deep learning-based and machine learning-based methods are used to study the differences between ruptured and un-ruptured aneurysms.•Results showed satisfactory performance in aneurysm detection and ruptured and un-ruptured aneurysm classification.