A Hybrid Multi-Stage Framework For Intracranial Aneurysm Detection From Cta Images: A Comparative Study With End-To-End Deep Learning
DOI:
https://doi.org/10.29284/cpt60r37Keywords:
Brain CTA; Intracranial aneurysm detection; Attention U-Net; Hybrid feature fusion; End-to-end comparison; XGBoost.Abstract
Intracranial aneurysm detection from brain CTA images remains challenging due to the small size of vascular abnormalities and the limited availability of expert annotations. This paper proposes a hybrid multi-stage framework and presents a direct comparison with a baseline end-to-end deep learning classifier. The framework integrates image preprocessing, synthetic mask generation, attention-based segmentation, hybrid feature extraction, and independent classification.
Synthetic vessel masks generated using vesselness filters and morphological operations were employed as surrogate labels to support training. An Attention U-Net enhanced with CBAM and optimized using Tversky loss achieved reliable segmentation performance, with a Dice score of 0.8798 and an IoU of 0.8056, enabling accurate localization of aneurysm regions even in low-contrast cases.
For classification, deep features extracted from ResNet50 were combined with handcrafted structural and textural descriptors and classified using an XGBoost model. This hybrid strategy achieved an accuracy of 98.46% and eliminated false-negative aneurysm cases, outperforming the baseline end-to-end ResNet50 classifier.
The results demonstrate that separating segmentation, feature extraction, and classification while integrating deep and structural information leads to improved diagnostic reliability and clinically safer predictions compared to conventional CNN-based approaches.
References
[1] T. Di Noto, M. Artzi, O. Aizenstein, et al., “Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge,” Neuroinformatics, vol. 21, pp. 21–34, 2023,
[2] Z. Zhu, X. He, W. Chen, et al., “Deep learning-based recognition and segmentation of intracranial aneurysms under small sample size,” Frontiers in Physiology, vol. 13, Art. no. 1084202, Dec. 2022, doi: 10.3389/fphys.2022.1084202.
[3] B.-s. Kim, “Unruptured Intracranial Aneurysm: Screening, Prevalence and Risk Factors,” Neurointervention, vol. 16, pp. 201–203, 2021, doi:10.5469/neuroint.2021.00451
[4] Hlavata et al, “Automated Method for Intracranial Aneurysm Classification Using Deep Learning,” Sensors, vol. 24, Art. no. 4556, 2024, doi: 10.3390/s24144556.
[5] W. Yuan et al., “DCAU-Net: Dense convolutional attention U-Net for segmentation of intracranial aneurysm images,” Visual Computing for Industry, Biomedicine and Art, vol. 5, Art. no. 9, 2022, doi: 10.1186/s42492-022-00110-6.
[6] R. Shahzad et al., “Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning,” Scientific Reports, vol. 10, Art. no. 21799, 2020, doi: 10.1038/s41598-020-78384-1.
[7] C. O’Rourke, S. Glover, R. Guerrero, et al., “Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge,” Neuroinformatics, vol. 21, pp. 21–34, 2023, doi: 10.1007/s12021-022-09597-0
[8] S. Ham, J. Seo, J. Yun, et al., “Automated detection of intracranial aneurysms using skeleton-based 3D patches, semantic segmentation, and auxiliary classification,” Scientific Reports, vol. 13, Art. no. 12018, 2023, doi: 10.1038/s41598-023-38106-2.
[9] W. Hou et al., “CTA image segmentation method for intracranial aneurysms based on MGLIA net,” Scientific Reports, vol. 15, Art. no. 10593, 2025, doi: 10.1038/s41598-025-95143-2.
[10] F. Shahoveisi, H. T. Gorji, S. Shahabi, S. Hosseinirad, S. Markell, and F. Vasefi, "Application of image processing and transfer learning for the detection of rust disease," Scientific Reports, vol. 13, p. 5133, 2023.
[11] A. A. Taha and A. Hanbury, "Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool," BMC Medical Imaging, vol. 15, no. 29, pp. 1–28, Aug. 2015.
[12] D. M. W. Powers, "Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation," J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011.
[13] H. K. Abdul Atheem, I. T. Ali, and F. A. Al Alawy, “A comprehensive analysis of deep learning and swarm intelligence techniques to enhance vehicular ad-hoc network performance,” Journal of Soft Computing and Computer Applications, vol. 1, no. 1, Art. 1004, pp. 1–12, 2024. doi: [10.70403/3008-1084.1004]
[14] Z. S. Mahdi, R. M. Zaki, A. K. Farhan, and N. Majma, “Development of a hybrid methodology of deep learning and machine learning for lung nodule detection in medical computed tomography images,” Journal of Soft Computing and Computer Applications, vol. 1, no. 2, Art. 1011, pp. 1–12, 2024. doi: [10.70403/3008-1084.1011]
[15] E. Talib, A. S. Jamil, N. F. Hassan, and M. E. Rana, “The robust digital video watermarking methods: A comparative study,” Journal of Soft Computing and Computer Applications, vol. 1, no. 1, Art. 1002, pp. 1–10, 2024. doi: [10.70403/3008-1084.1002]
[16] S. S. Hamad, N. J. Ibrahim, and M. N. Fadhil, “Texture features with Resnet50V2 for face spoofing detection,” AIP Conference Proceedings, vol. 3264, no. 1, Art. 030033, pp. 1–11, Mar. 2025. doi: [10.1063/5.0260733].
[17]Kaggle Dataset. (n.d.). Brain MRI aneurysm detection. Retrieved from: https://www.kaggle.com
[18]Roboflow Dataset. (n.d.). Tumor, cancer, and aneurysm detection. Retrieved from: https://universe.roboflow.com/discoverai/tumor-cancer-aneurysm-detection
[19] A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever, “Multiscale Vessel Enhancement Filtering,” in Medical Image Computing and Computer-Assisted Intervention — MICCAI’98, 1998, pp. 130–137.
[20] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
[21] L. G. Nyúl, J. K. Udupa, and X. Zhang, “New Variants of a Method of MRI Scale Standardization,” IEEE Transactions on Medical Imaging, vol. 19, no. 2, pp. 143–150, Feb. 2000.
[22] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. W. M. van der Laak, B. van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, Dec. 2017.
[23] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE CVPR, Las Vegas, NV, USA, 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
[24] M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. ICML, Long Beach, CA, USA, 2019, pp. 6105–6114.
[25] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in Proc. ICLR, 2015.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
