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 Oct 16:15:1394435.
doi: 10.3389/fneur.2024.1394435. eCollection 2024.

Identification of middle cerebral artery stenosis in transcranial Doppler using a modified VGG-16

Dong Xu  1 , Hao Li  2 , Fanghui Su  1 , Sizheng Qiu  1 , Huixia Tong  1 , Meifeng Huang  1 , Jianzhong Yao  1
Affiliations

Identification of middle cerebral artery stenosis in transcranial Doppler using a modified VGG-16

Dong Xu et al. Front Neurol. .

Abstract

Objectives: The diagnosis of intracranial atherosclerotic stenosis (ICAS) is of great significance for the prevention of stroke. Deep learning (DL)-based artificial intelligence techniques may aid in the diagnosis. The study aimed to identify ICAS in the middle cerebral artery (MCA) based on a modified DL model.

Methods: This retrospective study included two datasets. Dataset1 consisted of 3,068 transcranial Doppler (TCD) images of the MCA from 1,729 patients, which were assessed as normal or stenosis by three physicians with varying levels of experience, in conjunction with other medical imaging data. The data were used to improve and train the VGG16 models. Dataset2 consisted of TCD images of 90 people who underwent physical examination, which were used to verify the robustness of the model and compare the consistency between the model and human physicians.

Results: The accuracy, precision, specificity, sensitivity, and area under curve (AUC) of the best model VGG16 + Squeeze-and-Excitation (SE) + skip connection (SC) on dataset1 reached 85.67 ± 0.43(%),87.23 ± 1.17(%),87.73 ± 1.47(%),83.60 ± 1.60(%), and 0.857 ± 0.004, while those of dataset2 were 93.70 ± 2.80(%),62.65 ± 11.27(%),93.00 ± 3.11(%),100.00 ± 0.00(%), and 0.965 ± 0.016. The kappa coefficient showed that it reached the recognition level of senior doctors.

Conclusion: The improved DL model has a good diagnostic effect for MCV stenosis in TCD images and is expected to help in ICAS screening.

Keywords: ICAS; deep learning; screening; stroke; transcranial Doppler.

PubMed Disclaimer

Conflict of interest statement

Dong Xu and Hao Li are co-inventors of a Chinese patent application (not yet granted) that includes some of the material used in this manuscript. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
(A) VGG16 network structure. (B) Modified VGG16 network structure.
Figure 2
Figure 2
The performance of the algorithmic models. (A) Each algorithmic model on dataset1. (B) Each algorithmic model on dataset2. It can be observed that VGG16 + SE + SC achieved a higher mean and a smaller standard deviation.
Figure 3
Figure 3
Comparison of the consistency between the 3 DL models, GT, and human physicians. GT, ground truth.
Figure 4
Figure 4
Visual thermodynamic diagram. Normal represents the normal control, while narrow represents the spectrum with stenosis in the TCD image. The color of the heat map from red to blue represents the focus of the model to identify features from strong to weak.
See this image and copyright information in PMC

References

    1. Powers WJ, Rabinstein AA, Ackerson T, Adeoye OM, Bambakidis NC, Becker K, et al. . 2018 guidelines for the early Management of Patients with Acute Ischemic Stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke. (2018) 49:e46–e110. doi: 10.1161/STR.0000000000000158, PMID: - DOI - PubMed
    1. Gutierrez J, Turan TN, Hoh BL, Chimowitz MI. Intracranial atherosclerotic stenosis: risk factors, diagnosis, and treatment. Lancet Neurol. (2022) 21:355–68. doi: 10.1016/S1474-4422(21)00376-8 - DOI - PubMed
    1. Mattioni A, Cenciarelli S, Eusebi P, Brazzelli M, Mazzoli T, del Sette M, et al. . Transcranial Doppler sonography for detecting stenosis or occlusion of intracranial arteries in people with acute ischaemic stroke. Cochrane Database Syst Rev. (2020) 2:CD010722. doi: 10.1002/14651858.CD010722.pub2, PMID: - DOI - PMC - PubMed
    1. Mowla A, Shakibajahromi B, Kabir R, Garami Z, Volpi JJ. Transcranial Doppler and magnetic resonance angiography assessment of intracranial stenosis: an analysis of screening modalities. Brain Circ. (2020) 6:181–4. doi: 10.4103/bc.bc_21_20, PMID: - DOI - PMC - PubMed
    1. Gulland A. Shortage of health workers is set to double, says WHO. BMJ. (2013) 347:f6804. doi: 10.1136/bmj.f6804, PMID: - DOI - PubMed

LinkOut - more resources