Spatial intensity prior correction for tissue segmentation in the developing human brain

Sun Hyung Kim, Vladimir Fonov, Joe Piven, John Gilmore, Clement Vachet, Guido Gerig, D. Louis Collins, Martin Styner

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    The degree of white matter (WM) myelination is rather inhomogeneous across the brain. As a consequence, white matter appears differently across the cortical lobes in MR images acquired during early postnatal development. At 1 year old specifically, the gray/white matter contrast of MR images in prefrontal and temporal lobes is limited and thus tissue segmentation results show commonly reduce accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted image to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance inhomogeneity is highly reduced by the age of 24 months. For that purpose, we employ MRI data from a large dataset of longitudinal (12 and 24 month old subjects) MR study of Autism. The IGM creation is based on automatically co-registered images at 12 months, corresponding registered 24 months images, and a final registration of all image to a prior average template. In template space, voxelwise correspondence is thus achieved and the IGM is computed as the coefficient of a voxelwise linear regression model between corresponding intensities at 1-year and 2-years. The proposed IGM shows low regression values of 1-10% in GM and CSF regions, as well as in WM regions at advanced stage of myelination at 1-year. However, in the prefrontal and temporal lobe we observed regression values of 20-25%, indicating that the IGM appropriately captures the expected large intensity change in these lobes due to myelination.The IGM is applied to cross-sectional MRI datasets of 1-year old subjects via registration, correction and tissue segmentation of the corrected dataset. We validated our approach in a small study of images with known, manual ground truth segmentations. We furthermore present an EM-like optimization of adapting existing non-optimal prior atlas probability maps to fit known expert rater segmentations.

    Original languageEnglish (US)
    Title of host publication2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
    Pages2049-2052
    Number of pages4
    DOIs
    StatePublished - 2011
    Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
    Duration: Mar 30 2011Apr 2 2011

    Other

    Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
    CountryUnited States
    CityChicago, IL
    Period3/30/114/2/11

    Fingerprint

    Brain
    Tissue
    Growth
    Temporal Lobe
    Linear Models
    Magnetic resonance imaging
    Atlases
    Granulocyte-Macrophage Colony-Stimulating Factor
    Autistic Disorder
    Linear regression
    White Matter
    Datasets

    Keywords

    • classification
    • expectation maximization (EM) algorithm
    • MRI
    • tissue segmentation

    ASJC Scopus subject areas

    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging

    Cite this

    Kim, S. H., Fonov, V., Piven, J., Gilmore, J., Vachet, C., Gerig, G., ... Styner, M. (2011). Spatial intensity prior correction for tissue segmentation in the developing human brain. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 (pp. 2049-2052). [5872815] https://doi.org/10.1109/ISBI.2011.5872815

    Spatial intensity prior correction for tissue segmentation in the developing human brain. / Kim, Sun Hyung; Fonov, Vladimir; Piven, Joe; Gilmore, John; Vachet, Clement; Gerig, Guido; Collins, D. Louis; Styner, Martin.

    2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 2049-2052 5872815.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kim, SH, Fonov, V, Piven, J, Gilmore, J, Vachet, C, Gerig, G, Collins, DL & Styner, M 2011, Spatial intensity prior correction for tissue segmentation in the developing human brain. in 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11., 5872815, pp. 2049-2052, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872815
    Kim SH, Fonov V, Piven J, Gilmore J, Vachet C, Gerig G et al. Spatial intensity prior correction for tissue segmentation in the developing human brain. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 2049-2052. 5872815 https://doi.org/10.1109/ISBI.2011.5872815
    Kim, Sun Hyung ; Fonov, Vladimir ; Piven, Joe ; Gilmore, John ; Vachet, Clement ; Gerig, Guido ; Collins, D. Louis ; Styner, Martin. / Spatial intensity prior correction for tissue segmentation in the developing human brain. 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. pp. 2049-2052
    @inproceedings{3431cdaaf3d242139474e76915f18f86,
    title = "Spatial intensity prior correction for tissue segmentation in the developing human brain",
    abstract = "The degree of white matter (WM) myelination is rather inhomogeneous across the brain. As a consequence, white matter appears differently across the cortical lobes in MR images acquired during early postnatal development. At 1 year old specifically, the gray/white matter contrast of MR images in prefrontal and temporal lobes is limited and thus tissue segmentation results show commonly reduce accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted image to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance inhomogeneity is highly reduced by the age of 24 months. For that purpose, we employ MRI data from a large dataset of longitudinal (12 and 24 month old subjects) MR study of Autism. The IGM creation is based on automatically co-registered images at 12 months, corresponding registered 24 months images, and a final registration of all image to a prior average template. In template space, voxelwise correspondence is thus achieved and the IGM is computed as the coefficient of a voxelwise linear regression model between corresponding intensities at 1-year and 2-years. The proposed IGM shows low regression values of 1-10{\%} in GM and CSF regions, as well as in WM regions at advanced stage of myelination at 1-year. However, in the prefrontal and temporal lobe we observed regression values of 20-25{\%}, indicating that the IGM appropriately captures the expected large intensity change in these lobes due to myelination.The IGM is applied to cross-sectional MRI datasets of 1-year old subjects via registration, correction and tissue segmentation of the corrected dataset. We validated our approach in a small study of images with known, manual ground truth segmentations. We furthermore present an EM-like optimization of adapting existing non-optimal prior atlas probability maps to fit known expert rater segmentations.",
    keywords = "classification, expectation maximization (EM) algorithm, MRI, tissue segmentation",
    author = "Kim, {Sun Hyung} and Vladimir Fonov and Joe Piven and John Gilmore and Clement Vachet and Guido Gerig and Collins, {D. Louis} and Martin Styner",
    year = "2011",
    doi = "10.1109/ISBI.2011.5872815",
    language = "English (US)",
    isbn = "9781424441280",
    pages = "2049--2052",
    booktitle = "2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11",

    }

    TY - GEN

    T1 - Spatial intensity prior correction for tissue segmentation in the developing human brain

    AU - Kim, Sun Hyung

    AU - Fonov, Vladimir

    AU - Piven, Joe

    AU - Gilmore, John

    AU - Vachet, Clement

    AU - Gerig, Guido

    AU - Collins, D. Louis

    AU - Styner, Martin

    PY - 2011

    Y1 - 2011

    N2 - The degree of white matter (WM) myelination is rather inhomogeneous across the brain. As a consequence, white matter appears differently across the cortical lobes in MR images acquired during early postnatal development. At 1 year old specifically, the gray/white matter contrast of MR images in prefrontal and temporal lobes is limited and thus tissue segmentation results show commonly reduce accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted image to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance inhomogeneity is highly reduced by the age of 24 months. For that purpose, we employ MRI data from a large dataset of longitudinal (12 and 24 month old subjects) MR study of Autism. The IGM creation is based on automatically co-registered images at 12 months, corresponding registered 24 months images, and a final registration of all image to a prior average template. In template space, voxelwise correspondence is thus achieved and the IGM is computed as the coefficient of a voxelwise linear regression model between corresponding intensities at 1-year and 2-years. The proposed IGM shows low regression values of 1-10% in GM and CSF regions, as well as in WM regions at advanced stage of myelination at 1-year. However, in the prefrontal and temporal lobe we observed regression values of 20-25%, indicating that the IGM appropriately captures the expected large intensity change in these lobes due to myelination.The IGM is applied to cross-sectional MRI datasets of 1-year old subjects via registration, correction and tissue segmentation of the corrected dataset. We validated our approach in a small study of images with known, manual ground truth segmentations. We furthermore present an EM-like optimization of adapting existing non-optimal prior atlas probability maps to fit known expert rater segmentations.

    AB - The degree of white matter (WM) myelination is rather inhomogeneous across the brain. As a consequence, white matter appears differently across the cortical lobes in MR images acquired during early postnatal development. At 1 year old specifically, the gray/white matter contrast of MR images in prefrontal and temporal lobes is limited and thus tissue segmentation results show commonly reduce accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted image to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance inhomogeneity is highly reduced by the age of 24 months. For that purpose, we employ MRI data from a large dataset of longitudinal (12 and 24 month old subjects) MR study of Autism. The IGM creation is based on automatically co-registered images at 12 months, corresponding registered 24 months images, and a final registration of all image to a prior average template. In template space, voxelwise correspondence is thus achieved and the IGM is computed as the coefficient of a voxelwise linear regression model between corresponding intensities at 1-year and 2-years. The proposed IGM shows low regression values of 1-10% in GM and CSF regions, as well as in WM regions at advanced stage of myelination at 1-year. However, in the prefrontal and temporal lobe we observed regression values of 20-25%, indicating that the IGM appropriately captures the expected large intensity change in these lobes due to myelination.The IGM is applied to cross-sectional MRI datasets of 1-year old subjects via registration, correction and tissue segmentation of the corrected dataset. We validated our approach in a small study of images with known, manual ground truth segmentations. We furthermore present an EM-like optimization of adapting existing non-optimal prior atlas probability maps to fit known expert rater segmentations.

    KW - classification

    KW - expectation maximization (EM) algorithm

    KW - MRI

    KW - tissue segmentation

    UR - http://www.scopus.com/inward/record.url?scp=80055053465&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=80055053465&partnerID=8YFLogxK

    U2 - 10.1109/ISBI.2011.5872815

    DO - 10.1109/ISBI.2011.5872815

    M3 - Conference contribution

    SN - 9781424441280

    SP - 2049

    EP - 2052

    BT - 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11

    ER -