Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr 25;41(2):228-236.
doi: 10.7507/1001-5515.202301008.

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

[Article in Chinese]
Peirui Bai  1 , Xuefeng Song  1 , Qingyi Liu  1 , Jiahui Liu  1 , Jin Cheng  1 , Xiaona Xiu  1 , Yande Ren  2 , Chengjian Wang  2
Affiliations

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

[Article in Chinese]
Peirui Bai et al. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. .

Abstract
in English, Chinese

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.

传统的单一方位最大密度投影（MIP）图像在检测颅内动脉瘤时容易忽略部分形态特征，造成漏检和误检。针对该问题，本文提出一种新的基于全方位MIP图像的颅内动脉瘤检测方法。首先，对三维磁共振血管造影（MRA）图像进行全方位最大密度投影，获得MIP图像；然后，利用匹配滤波对颅内动脉瘤区域进行预定位；最后，使用Squeeze and Excitation（SE）模块对CaraNet模型进行了改进，并用改进后的模型对全方位MIP图像中的预定位区域进行检测，确定是否患有颅内动脉瘤。本文收集了245例图像对所提方法进行了测试实验。实验结果表明本文所提方法的精确率和特异性分别可以达到93.75%和93.86%，显著提高了对MIP图像中颅内动脉瘤的检测性能。.

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

PubMed Disclaimer

Conflict of interest statement

利益冲突声明：本文全体作者均声明不存在利益冲突。

Figures

图 1
图 1
The overall process of algorithm in this paper 本文算法整体流程
图 2
图 2
TOF-MRA (Left) and MIP (Right) images TOF-MRA（左）与MIP图像（右）
图 3
图 3
Omni-directional projection diagram 全方位投影示意图
图 4
图 4
Pre-position of intracranial aneurysm 颅内动脉瘤预定位
图 5
图 5
SE-CaraNet network architecture SE-CaraNet 网络架构
图 6
图 6
Structure of SE module SE模块结构
图 7
图 7
Results of MIP image detection by different methods 不同方法MIP图像检测结果
图 8
图 8
Intracranial aneurysms in omni-directional MIP images 全方位MIP图像中的颅内动脉瘤
图 9
图 9
Intracranial aneurysm detection results when vessels are covered 存在血管遮挡时的颅内动脉瘤检测结果
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Chalouhi N, Hoh B L, Hasan D Review of cerebral aneurysm formation, growth, and rupture. Stroke. 2013;44(12):3613–3622. doi: 10.1161/STROKEAHA.113.002390. - DOI - PubMed
    1. 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. - PubMed
    1. 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. doi: 10.1016/j.jstrokecerebrovasdis.2022.106690. - DOI - PubMed
    1. 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. doi: 10.15274/INR-2014-10092. - DOI - PMC - PubMed
    1. 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. doi: 10.1007/s10278-021-00504-8. - DOI - PMC - PubMed

Publication types

MeSH terms

LinkOut - more resources