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
. 2025 Mar 27;15(1):10593.
doi: 10.1038/s41598-025-95143-2.

CTA image segmentation method for intracranial aneurysms based on MGLIA net

Lijie Hou  1 , Jian Zhang  1 , Lihui Zhao  1 , Ke Meng  2 , Xin Feng  3   4
Affiliations

CTA image segmentation method for intracranial aneurysms based on MGLIA net

Lijie Hou et al. Sci Rep. .

Abstract

Accurately segmenting the aneurysm area from CTA data can reconstruct the three-dimensional morphology of the aneurysm, effectively evaluating the type, size, and risk of rupture of the aneurysm. However, accurate separation of the aneurysm is limited by the accuracy of image segmentation algorithms. Currently, the segmentation methods for intracranial aneurysms using CTA big data and deep learning lack universality. When faced with a new hospital acquired imaging modality, it is usually necessary to redesign and train the segmentation network. In response to this issue, this article proposes a more universal segmentation model and develops the GLIA Net algorithm (MGLIA Net model) based on MoblieNet, which can perform adaptive target segmentation on aneurysm images collected under different conditions. To verify the effectiveness of the algorithm in intracranial aneurysm segmentation, performance tests were conducted on an open-source dataset. The results showed that the proposed algorithm achieved segmentation accuracy of 55.9% and 73.1% on two datasets, respectively, significantly better than the original GLIA-Net algorithm.

Keywords: CTA; Deep learning network model; Image segmentation; Intracranial aneurysm.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Conventional convolution.
Fig. 2
Fig. 2
Depthwise convolution.
Fig. 3
Fig. 3
Pointwise convolution.
Fig. 4
Fig. 4
Schematic diagram of residual block and inverted residual block.
Fig. 5
Fig. 5
Schematic diagram of the MobileNet V2 model.
Fig. 6
Fig. 6
Schematic diagram of GLIA-Net model.
Fig. 7
Fig. 7
Schematic diagram of MGLIA network model.
Fig. 8
Fig. 8
Comparison of segmentation results for large-sized intracranial aneurysms.
Fig. 9
Fig. 9
Comparison of segmentation results for medium-sized intracranial aneurysms.
Fig. 10
Fig. 10
Comparison of segmentation results for small-sized intracranial aneurysms.
See this image and copyright information in PMC

References

    1. Hoh, B. L. et al. 2023 Guideline for the management of patients with aneurysmal subarachnoid hemorrhage: a guideline from the American heart association/american stroke Association[J]. Stroke54 (7), e314–e370 (2023). - PubMed
    1. Neifert, S. N. et al. Aneurysmal subarachnoid hemorrhage: the last decade[J]. Translational Stroke Res.12, 428–446 (2021). - PubMed
    1. Brisman, J. L., Song, J. K. & Newell, D. W. Cerebral aneurysms[J]. N. Engl. J. Med.355 (9), 928–939 (2006). - PubMed
    1. Abdulazim, A. et al. Diagnosis of delayed cerebral ischemia in patients with aneurysmal subarachnoid hemorrhage and triggers for intervention[J]. Neurocrit. Care. 39 (2), 311–319 (2023). - PMC - PubMed
    1. Szántó, D. et al. Diagnosis and management of Takotsubo syndrome in acute aneurysmal subarachnoid hemorrhage: A comprehensive Review[J]. Rev. Cardiovasc. Med.24 (6), 177 (2023). - PMC - PubMed

MeSH terms

LinkOut - more resources