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 Sep;60(3):1165-1175.
doi: 10.1002/jmri.29198. Epub 2023 Dec 27.

Deep-Learning-Based MRI Microbleeds Detection for Cerebral Small Vessel Disease on Quantitative Susceptibility Mapping

Peng Xia  1 , Edward S Hui  2 , Bryan J Chua  3 , Fan Huang  1 , Zuojun Wang  1 , Huiqin Zhang  1 , Han Yu  1 , Kui Kai Lau  3   4 , Henry K F Mak  1 , Peng Cao  1
Affiliations

Deep-Learning-Based MRI Microbleeds Detection for Cerebral Small Vessel Disease on Quantitative Susceptibility Mapping

Peng Xia et al. J Magn Reson Imaging. 2024 Sep.

Abstract

Background: Cerebral microbleeds (CMB) are indicators of severe cerebral small vessel disease (CSVD) that can be identified through hemosiderin-sensitive sequences in MRI. Specifically, quantitative susceptibility mapping (QSM) and deep learning were applied to detect CMBs in MRI.

Purpose: To automatically detect CMB on QSM, we proposed a two-stage deep learning pipeline.

Study type: Retrospective.

Subjects: A total number of 1843 CMBs from 393 patients (69 ± 12) with cerebral small vessel disease were included in this study. Seventy-eight subjects (70 ± 13) were used as external testing.

Field strength/sequence: 3 T/QSM.

Assessment: The proposed pipeline consisted of two stages. In stage I, 2.5D fast radial symmetry transform (FRST) algorithm along with a one-layer convolutional network was used to identify CMB candidate regions in QSM images. In stage II, the V-Net was utilized to reduce false positives. The V-Net was trained using CMB and non CMB labels, which allowed for high-level feature extraction and differentiation between CMBs and CMB mimics like vessels. The location of CMB was assessed according to the microbleeds anatomical rating scale (MARS) system.

Statistical tests: The sensitivity and positive predicative value (PPV) were reported to evaluate the performance of the model. The number of false positive per subject was presented.

Results: Our pipeline demonstrated high sensitivities of up to 94.9% at stage I and 93.5% at stage II. The overall sensitivity was 88.9%, and the false positive rate per subject was 2.87. With respect to MARS, sensitivities of above 85% were observed for nine different brain regions.

Data conclusion: We have presented a deep learning pipeline for detecting CMB in the CSVD cohort, along with a semi-automated MARS scoring system using the proposed method. Our results demonstrated the successful application of deep learning for CMB detection on QSM and outperformed previous handcrafted methods.

Level of evidence: 2 TECHNICAL EFFICACY: Stage 2.

Keywords: CycleGAN; ResNet; V‐Net; cerebral microbleeds; deep learning; quantitative susceptibility mapping.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

References

    1. Pantoni LMD. Cerebral small vessel disease: From pathogenesis and clinical characteristics to therapeutic challenges. Lancet Neurol 2010;9(7):689‐701. https://doi.org/10.1016/S1474-4422(10)70104-6.
    1. Ambler G, Lee K‐J, Shiozawa M, Lovelock C, et al. Cerebral microbleeds and stroke risk after ischaemic stroke or transient ischaemic attack: A pooled analysis of individual patient data from cohort studies. Lancet Neurol 2019;18(7):653‐665. https://doi.org/10.1016/S1474-4422(19)30197-8.
    1. Wardlaw JM, Smith EE, Biessels GJ, et al. Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration. Lancet Neurol 2013;12(8):822‐838. https://doi.org/10.1016/s1474-4422(13)70124-8.
    1. Lau KK, Li L, Schulz U, et al. Total small vessel disease score and risk of recurrent stroke: Validation in 2 large cohorts. Neurology 2017;88(24):2260‐2267. https://doi.org/10.1212/WNL.0000000000004042.
    1. Ambler G, Lim J‐S, Shiozawa M, et al. Development of imaging‐based risk scores for prediction of intracranial haemorrhage and ischaemic stroke in patients taking antithrombotic therapy after ischaemic stroke or transient ischaemic attack: A pooled analysis of individual patient data from cohort studies. Lancet Neurol 2021;20(4):294‐303. https://doi.org/10.1016/S1474-4422(21)00024-7.