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
. 2021 Jul 30;21(Suppl 2):89.
doi: 10.1186/s12911-021-01430-z.

A deep semantic segmentation correction network for multi-model tiny lesion areas detection

Yue Liu #  1   2 , Xiang Li #  1   2   3 , Tianyang Li  1   2 , Bin Li  4 , Zhensong Wang  4 , Jie Gan  4 , Benzheng Wei  5   6
Affiliations

A deep semantic segmentation correction network for multi-model tiny lesion areas detection

Yue Liu et al. BMC Med Inform Decis Mak. .

Abstract

Background: Semantic segmentation of white matter hyperintensities related to focal cerebral ischemia (FCI) and lacunar infarction (LACI) is of significant importance for the automatic screening of tiny cerebral lesions and early prevention of LACI. However, existing studies on brain magnetic resonance imaging lesion segmentation focus on large lesions with obvious features, such as glioma and acute cerebral infarction. Owing to the multi-model tiny lesion areas of FCI and LACI, reliable and precise segmentation and/or detection of these lesion areas is still a significant challenge task.

Methods: We propose a novel segmentation correction algorithm for estimating the lesion areas via segmentation and correction processes, in which we design two sub-models simultaneously: a segmentation network and a correction network. The segmentation network was first used to extract and segment diseased areas on T2 fluid-attenuated inversion recovery (FLAIR) images. Consequently, the correction network was used to classify these areas at the corresponding locations on T1 FLAIR images to distinguish between FCI and LACI. Finally, the results of the correction network were used to correct the segmentation results and achieve segmentation and recognition of the lesion areas.

Results: In our experiment on magnetic resonance images of 113 clinical patients, our method achieved a precision of 91.76% for detection and 92.89% for classification, indicating a powerful method to distinguish between small lesions, such as FCI and LACI.

Conclusions: Overall, we developed a complete method for segmentation and detection of WMHs related to FCI and LACI. The experimental results show that it has potential clinical application potential. In the future, we will collect more clinical data and test more types of tiny lesions at the same time.

Keywords: Focal cerebral ischemia; Lacunar infarct; Magnetic resonance imaging; Multi-modality; White matter hyperintensities.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
a Comparison of FCI and LACI signals on T2 FLAIR and T1 FLAIR images.This patient had both of these lesions on the same slice. It is observed that the signals of FCI and LACI can only be distinguished on T1 FLAIR images. b Two slices with strong differences in the number and brightness of abnormal signals. These differences make it difficult for the segmentation model to accurately segment both types of slices at the same time
Fig. 2
Fig. 2
Segmentation correction network
Fig. 3
Fig. 3
Primary network: segmentation network
Fig. 4
Fig. 4
Secondary network: semantic correction network
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Wardlaw JM, Pantoni L. Sporadic small vessel disease: pathogenic. Cereb Small Vessel Dis. 2014;52.
    1. Lee Y, Ko J, Choi YE, Oh JS, Kim JS, Sunwoo MK, Yoon JH, Kang SY, Hong JY. Areas of white matter hyperintensities and motor symptoms of Parkinson disease. Neurology. 2020;95(3):291–298. doi: 10.1212/WNL.0000000000009890. - DOI - PubMed
    1. Birenbaum A, Greenspan H. Longitudinal multiple sclerosis lesion segmentation using multi-view convolutional neural networks. In: Deep learning and data labeling for medical applications, pp. 58–67. Springer, Cham; 2016.
    1. Moscoso A, Rey-Bretal D, Silva-Rodríguez J, Aldrey JM, Cortés J, Pías-Peleteiro J, Ruibal Á, Aguiar P, Initiative ADN, et al. White matter hyperintensities are associated with subthreshold amyloid accumulation. NeuroImage. 2020;218:116944. doi: 10.1016/j.neuroimage.2020.116944. - DOI - PubMed
    1. Bokde A, Teipel S, Zebuhr Y, Leinsinger G, Gootjes L, Schwarz R, Buerger K, Scheltens P, Moeller H-J, Hampel H. A new rapid landmark-based regional MRI segmentation method of the brain. J Neurol Sci. 2002;194(1):35–40. doi: 10.1016/S0022-510X(01)00667-0. - DOI - PubMed

Publication types