Automatic detection method of intracranial aneurysms on maximum intensity projection images based on SE-CaraNet_Journal of Biomedical Engineering

Authors：

BAI Peirui ¹ , SONG Xuefeng ¹ ,  LIU Qingyi ¹ , LIU Jiahui ¹ , CHENG Jin ¹ , XIU Xiaona ¹ , REN Yande ² , WANG Chengjian ²

1. School of Electronic Information Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266590, P. R. China;
2. Department of Radiology, Affiliated Hospital of Qingdao University, Qingdao, Shandong 265000, P. R. China;

Corresponding author：

LIU Qingyi, Email: lqy_raphael@sdust.edu.cn

Keywords：

Intracranial aneurysm detection; Maximum intensity projection; Squeeze-and-Excitation module; CaraNet

DOI：

10.7507/1001-5515.202301008

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Conventional maximum intensity projection (MIP) images tend to ignore some morphological features in the detection of intracranial aneurysms, resulting in missed detection and misdetection. To solve this problem, a new method for intracranial aneurysm detection based on omni-directional MIP image is proposed in this paper. Firstly, the three-dimensional magnetic resonance angiography (MRA) images were projected with the maximum density in all directions to obtain the MIP images. Then, the region of intracranial aneurysm was prepositioned by matching filter. Finally, the Squeeze and Excitation (SE) module was used to improve the CaraNet model. Excitation and the improved model were used to detect the predetermined location in the omni-directional MIP image to determine whether there was intracranial aneurysm. In this paper, 245 cases of images were collected to test the proposed method. The results showed that the accuracy and specificity of the proposed method could reach 93.75% and 93.86%, respectively, significantly improved the detection performance of intracranial aneurysms in MIP images.

Citation： BAI Peirui, SONG Xuefeng, LIU Qingyi, LIU Jiahui, CHENG Jin, XIU Xiaona, REN Yande, WANG Chengjian. Automatic detection method of intracranial aneurysms on maximum intensity projection images based on SE-CaraNet. Journal of Biomedical Engineering, 2024, 41(2): 228-236. doi: 10.7507/1001-5515.202301008 Copy

1.	Chalouhi N, Hoh B L, Hasan D. Review of cerebral aneurysm formation, growth, and rupture. Stroke, 2013, 44(12): 3613-3622.
2.	Alwalid O, Long X, Xie M, et al. Artificial intelligence applications in intracranial aneurysm: Achievements, challenges and opportunities. Acad Radiol, 2022, 29(Suppl 3): S201-S214.
3.	Heit J J, Honce J M, Yedavalli V S, et al. RAPID Aneurysm: Artificial intelligence for unruptured cerebral aneurysm detection on CT angiography. J Stroke Cerebrovasc Dis, 2022, 31(10): 106690.
4.	Kapsas G, Budai C, Toni F, et al. Evaluation of CTA, time-resolved 4D CE-MRA and DSA in the follow-up of an intracranial aneurysm treated with a flow diverter stent: Experience from a single case. Interv Neuroradiol, 2015, 21(1): 69-71.
5.	Chao Z, Xu W. A new general maximum intensity projection technology via the hybrid of U-Net and radial basis function neural network. J Digit Imaging, 2021, 34(5): 1264-1278.
6.	Oguro S, Mugikura S, Ota H, et al. Usefulness of maximum intensity projection images of non-enhanced CT for detection of hyperdense middle cerebral artery sign in acute thromboembolic ischemic stroke. Jpn J Radiol, 2022, 40(10): 1046-1052.
7.	Zellweger C, Berger N, Wieler J, et al. Breast computed tomography diagnostic performance of the maximum intensity projection reformations as a stand-alone method for the detection and characterization of breast findings. Invest Radiol, 2022, 57(4): 205-211.
8.	Amyar A, Modzelewski R, Vera P, et al. Weakly supervised tumor detection in PET using class response for treatment outcome prediction. J Imaging, 2022, 8(5): 130.
9.	Naila Jabeen, Ruby Qureshi, Amjad Sattar, et al. Diagnostic accuracy of maximum intensity projection in diagnosis of malignant pulmonary nodules. Cureus, 2019, 11(11): e6120.
10.	Rahmany I, Laajili S, Khlifa N. Automated computerized method for the detection of unruptured cerebral aneurysms in DSA images. Curr Med Imaging, 2018, 14(5): 771-777.
11.	Uchiyama Y, Ando H, Yokoyama R, et al. Computer-aided diagnosis scheme for detection of unruptured intracranial aneurysms in MR angiography. Conf Proc IEEE Eng Med Biol Soc, 2005, 3: 3031-3034.
12.	Hentschke C M, Beuing O, Paukisch H, et al. A system to detect cerebral aneurysms in multimodality angiographic data sets. Med Phys, 2014, 41(9): 11.
13.	Mensah E, Pringle C, Roberts G, et al. Deep learning in the management of intracranial aneurysms and cerebrovascular diseases: A review of the current literature. World Neurosurg, 2022, 161: 39-45.
14.	Chen G, Wei X, Lei H, et al. Automated computer-assisted detection system for cerebral aneurysms in time-of-flight magnetic resonance angiography using fully convolutional network. Biomed Eng Online, 2020, 19(1): 38.
15.	Park A, Chute C, Rajpurkar P, et al. Deep learning–assisted diagnosis of cerebral aneurysms using the HeadXNet model. JAMA Network Open, 2019, 2(6): e195600.
16.	Chen X, Lei Y, Su J B, et al. A review of artificial intelligence in cerebrovascular disease imaging: Applications and challenges. Curr Neuropharmacol, 2022, 20(7): 1359-1382.
17.	Nakao T, Hanaoka S, Nomura Y, et al. Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging, 2018, 47(4): 948-953.
18.	Hou W G, Mei S J, Gui Q L, et al. 1D CNN-based intracranial aneurysms detection in 3D TOF-MRA. Complexity, 2020, 2020: 7023754.
19.	Stember J N, Chang P, Stember D M, et al. Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography. J Digit Imaging, 2019, 32(5): 808-815.
20.	Lou A, Guan S, Loew M. CaraNet: Context axial reverse attention network for segmentation. arXiv, 2021, 2021: 2103.12212.
21.	罗守华, 刘俊秀, 于洁, 等. 最大密度投影算法实现与改进. 北京生物医学工程, 2009, 28(2): 131-134.
22.	Ho J, Kalchbrenner N, Weissenborn D, et al. Axial attention in multidimensional transformers. arXiv: 2019, 2019: 1912.12180.
23.	Chen S, Tan X, Wang B, et al. Reverse attention for salient object detection. arXiv, 2018, 2018: 1807.09940.
24.	Qin X, Zhang Z, Huang C, et al. BASNet: Boundary-Aware Salient object detection// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE, 2019: 7479-7489.
25.	Wei J, Wang S, Huang Q. F3Net: Fusion, feedback and focus for salient object detection. arXiv, 2020, 2020: 1911.11445.
26.	Hu Jie, Shen Li, Albanie S, et al. Squeeze-and-Excitation metworks. IEEE Trans Pattern Anal Mach Intell, 2020, 42(8): 2011-2023.
27.	Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann Machines// The 27th International Conference on International Conference on Machine Learning. Haifa: ACM, 2010: 807-814.

1. Chalouhi N, Hoh B L, Hasan D. Review of cerebral aneurysm formation, growth, and rupture. Stroke, 2013, 44(12): 3613-3622.
2. Alwalid O, Long X, Xie M, et al. Artificial intelligence applications in intracranial aneurysm: Achievements, challenges and opportunities. Acad Radiol, 2022, 29(Suppl 3): S201-S214.
3. Heit J J, Honce J M, Yedavalli V S, et al. RAPID Aneurysm: Artificial intelligence for unruptured cerebral aneurysm detection on CT angiography. J Stroke Cerebrovasc Dis, 2022, 31(10): 106690.
4. Kapsas G, Budai C, Toni F, et al. Evaluation of CTA, time-resolved 4D CE-MRA and DSA in the follow-up of an intracranial aneurysm treated with a flow diverter stent: Experience from a single case. Interv Neuroradiol, 2015, 21(1): 69-71.
5. Chao Z, Xu W. A new general maximum intensity projection technology via the hybrid of U-Net and radial basis function neural network. J Digit Imaging, 2021, 34(5): 1264-1278.
6. Oguro S, Mugikura S, Ota H, et al. Usefulness of maximum intensity projection images of non-enhanced CT for detection of hyperdense middle cerebral artery sign in acute thromboembolic ischemic stroke. Jpn J Radiol, 2022, 40(10): 1046-1052.
7. Zellweger C, Berger N, Wieler J, et al. Breast computed tomography diagnostic performance of the maximum intensity projection reformations as a stand-alone method for the detection and characterization of breast findings. Invest Radiol, 2022, 57(4): 205-211.
8. Amyar A, Modzelewski R, Vera P, et al. Weakly supervised tumor detection in PET using class response for treatment outcome prediction. J Imaging, 2022, 8(5): 130.
9. Naila Jabeen, Ruby Qureshi, Amjad Sattar, et al. Diagnostic accuracy of maximum intensity projection in diagnosis of malignant pulmonary nodules. Cureus, 2019, 11(11): e6120.
10. Rahmany I, Laajili S, Khlifa N. Automated computerized method for the detection of unruptured cerebral aneurysms in DSA images. Curr Med Imaging, 2018, 14(5): 771-777.
11. Uchiyama Y, Ando H, Yokoyama R, et al. Computer-aided diagnosis scheme for detection of unruptured intracranial aneurysms in MR angiography. Conf Proc IEEE Eng Med Biol Soc, 2005, 3: 3031-3034.
12. Hentschke C M, Beuing O, Paukisch H, et al. A system to detect cerebral aneurysms in multimodality angiographic data sets. Med Phys, 2014, 41(9): 11.
13. Mensah E, Pringle C, Roberts G, et al. Deep learning in the management of intracranial aneurysms and cerebrovascular diseases: A review of the current literature. World Neurosurg, 2022, 161: 39-45.
14. Chen G, Wei X, Lei H, et al. Automated computer-assisted detection system for cerebral aneurysms in time-of-flight magnetic resonance angiography using fully convolutional network. Biomed Eng Online, 2020, 19(1): 38.
15. Park A, Chute C, Rajpurkar P, et al. Deep learning–assisted diagnosis of cerebral aneurysms using the HeadXNet model. JAMA Network Open, 2019, 2(6): e195600.
16. Chen X, Lei Y, Su J B, et al. A review of artificial intelligence in cerebrovascular disease imaging: Applications and challenges. Curr Neuropharmacol, 2022, 20(7): 1359-1382.
17. Nakao T, Hanaoka S, Nomura Y, et al. Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging, 2018, 47(4): 948-953.
18. Hou W G, Mei S J, Gui Q L, et al. 1D CNN-based intracranial aneurysms detection in 3D TOF-MRA. Complexity, 2020, 2020: 7023754.
19. Stember J N, Chang P, Stember D M, et al. Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography. J Digit Imaging, 2019, 32(5): 808-815.
20. Lou A, Guan S, Loew M. CaraNet: Context axial reverse attention network for segmentation. arXiv, 2021, 2021: 2103.12212.
21. 罗守华, 刘俊秀, 于洁, 等. 最大密度投影算法实现与改进. 北京生物医学工程, 2009, 28(2): 131-134.
22. Ho J, Kalchbrenner N, Weissenborn D, et al. Axial attention in multidimensional transformers. arXiv: 2019, 2019: 1912.12180.
23. Chen S, Tan X, Wang B, et al. Reverse attention for salient object detection. arXiv, 2018, 2018: 1807.09940.
24. Qin X, Zhang Z, Huang C, et al. BASNet: Boundary-Aware Salient object detection// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE, 2019: 7479-7489.
25. Wei J, Wang S, Huang Q. F3Net: Fusion, feedback and focus for salient object detection. arXiv, 2020, 2020: 1911.11445.
26. Hu Jie, Shen Li, Albanie S, et al. Squeeze-and-Excitation metworks. IEEE Trans Pattern Anal Mach Intell, 2020, 42(8): 2011-2023.
27. Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann Machines// The 27th International Conference on International Conference on Machine Learning. Haifa: ACM, 2010: 807-814.

Journal of Biomedical Engineering

Automatic detection method of intracranial aneurysms on maximum intensity projection images based on SE-CaraNet

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content