Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data

Guido Gerig, Daniel Welti, Charles R G Guttmann, Alan C F Colchester, Gábor Székely

    Research output: Contribution to journalArticle

    Abstract

    This paper presents a new method for the automatic segmentation and characterization of object changes in time series of three-dimensional data sets. The technique was inspired by procedures developed for analysis of functional MRI data sets. After precise registration of serial volume data sets to 4-D data, we applied a time series analysis taking into account the characteristic time function of variable lesions. The images were preprocessed with a correction of image field inhomogeneities and a normalization of the brightness over the whole time series. Thus, static regions remain unchanged over time, whereas changes in tissue characteristics produce typical intensity variations in the voxel's time series. A set of features was derived from the time series, expressing probabilities for membership to the sought structures. These multiple sources of uncertain evidence were combined to a single evidence value using Dempster Shafer's theory. The project was driven by the objective of improving the segmentation and characterization of white matter lesions in serial MR data of multiple sclerosis patients. Pharmaceutical research and patient follow-up requires efficient and robust methods with a high degree of automation. The new approach replaces conventional segmentation of series of 3-D data sets by a 1-D processing of the temporal change at each voxel in the 4-D image data set. The new method has been applied to a total of 11 time series from different patient studies, covering time resolutions of 12 and 24 data sets over a period of about 1 year. The results demonstrate that time evolution is a highly sensitive feature for detection of fluctuating structures.

    Original languageEnglish (US)
    Pages (from-to)31-42
    Number of pages12
    JournalMedical Image Analysis
    Volume4
    Issue number1
    StatePublished - 2000

    Fingerprint

    Time series
    Time series analysis
    Drug products
    Luminance
    Automation
    Tissue
    Processing
    Multiple Sclerosis
    Datasets
    Magnetic Resonance Imaging

    Keywords

    • Lesions in magnetic resonance imaging
    • Multiple sclerosis
    • Temporal analysis
    • Time series analysis

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition
    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging
    • Medicine (miscellaneous)
    • Computer Science (miscellaneous)

    Cite this

    Gerig, G., Welti, D., Guttmann, C. R. G., Colchester, A. C. F., & Székely, G. (2000). Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data. Medical Image Analysis, 4(1), 31-42.

    Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data. / Gerig, Guido; Welti, Daniel; Guttmann, Charles R G; Colchester, Alan C F; Székely, Gábor.

    In: Medical Image Analysis, Vol. 4, No. 1, 2000, p. 31-42.

    Research output: Contribution to journalArticle

    Gerig, G, Welti, D, Guttmann, CRG, Colchester, ACF & Székely, G 2000, 'Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data', Medical Image Analysis, vol. 4, no. 1, pp. 31-42.
    Gerig, Guido ; Welti, Daniel ; Guttmann, Charles R G ; Colchester, Alan C F ; Székely, Gábor. / Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data. In: Medical Image Analysis. 2000 ; Vol. 4, No. 1. pp. 31-42.
    @article{a5020db04a274f49be18308c5fb4e396,
    title = "Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data",
    abstract = "This paper presents a new method for the automatic segmentation and characterization of object changes in time series of three-dimensional data sets. The technique was inspired by procedures developed for analysis of functional MRI data sets. After precise registration of serial volume data sets to 4-D data, we applied a time series analysis taking into account the characteristic time function of variable lesions. The images were preprocessed with a correction of image field inhomogeneities and a normalization of the brightness over the whole time series. Thus, static regions remain unchanged over time, whereas changes in tissue characteristics produce typical intensity variations in the voxel's time series. A set of features was derived from the time series, expressing probabilities for membership to the sought structures. These multiple sources of uncertain evidence were combined to a single evidence value using Dempster Shafer's theory. The project was driven by the objective of improving the segmentation and characterization of white matter lesions in serial MR data of multiple sclerosis patients. Pharmaceutical research and patient follow-up requires efficient and robust methods with a high degree of automation. The new approach replaces conventional segmentation of series of 3-D data sets by a 1-D processing of the temporal change at each voxel in the 4-D image data set. The new method has been applied to a total of 11 time series from different patient studies, covering time resolutions of 12 and 24 data sets over a period of about 1 year. The results demonstrate that time evolution is a highly sensitive feature for detection of fluctuating structures.",
    keywords = "Lesions in magnetic resonance imaging, Multiple sclerosis, Temporal analysis, Time series analysis",
    author = "Guido Gerig and Daniel Welti and Guttmann, {Charles R G} and Colchester, {Alan C F} and G{\'a}bor Sz{\'e}kely",
    year = "2000",
    language = "English (US)",
    volume = "4",
    pages = "31--42",
    journal = "Medical Image Analysis",
    issn = "1361-8415",
    publisher = "Elsevier",
    number = "1",

    }

    TY - JOUR

    T1 - Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data

    AU - Gerig, Guido

    AU - Welti, Daniel

    AU - Guttmann, Charles R G

    AU - Colchester, Alan C F

    AU - Székely, Gábor

    PY - 2000

    Y1 - 2000

    N2 - This paper presents a new method for the automatic segmentation and characterization of object changes in time series of three-dimensional data sets. The technique was inspired by procedures developed for analysis of functional MRI data sets. After precise registration of serial volume data sets to 4-D data, we applied a time series analysis taking into account the characteristic time function of variable lesions. The images were preprocessed with a correction of image field inhomogeneities and a normalization of the brightness over the whole time series. Thus, static regions remain unchanged over time, whereas changes in tissue characteristics produce typical intensity variations in the voxel's time series. A set of features was derived from the time series, expressing probabilities for membership to the sought structures. These multiple sources of uncertain evidence were combined to a single evidence value using Dempster Shafer's theory. The project was driven by the objective of improving the segmentation and characterization of white matter lesions in serial MR data of multiple sclerosis patients. Pharmaceutical research and patient follow-up requires efficient and robust methods with a high degree of automation. The new approach replaces conventional segmentation of series of 3-D data sets by a 1-D processing of the temporal change at each voxel in the 4-D image data set. The new method has been applied to a total of 11 time series from different patient studies, covering time resolutions of 12 and 24 data sets over a period of about 1 year. The results demonstrate that time evolution is a highly sensitive feature for detection of fluctuating structures.

    AB - This paper presents a new method for the automatic segmentation and characterization of object changes in time series of three-dimensional data sets. The technique was inspired by procedures developed for analysis of functional MRI data sets. After precise registration of serial volume data sets to 4-D data, we applied a time series analysis taking into account the characteristic time function of variable lesions. The images were preprocessed with a correction of image field inhomogeneities and a normalization of the brightness over the whole time series. Thus, static regions remain unchanged over time, whereas changes in tissue characteristics produce typical intensity variations in the voxel's time series. A set of features was derived from the time series, expressing probabilities for membership to the sought structures. These multiple sources of uncertain evidence were combined to a single evidence value using Dempster Shafer's theory. The project was driven by the objective of improving the segmentation and characterization of white matter lesions in serial MR data of multiple sclerosis patients. Pharmaceutical research and patient follow-up requires efficient and robust methods with a high degree of automation. The new approach replaces conventional segmentation of series of 3-D data sets by a 1-D processing of the temporal change at each voxel in the 4-D image data set. The new method has been applied to a total of 11 time series from different patient studies, covering time resolutions of 12 and 24 data sets over a period of about 1 year. The results demonstrate that time evolution is a highly sensitive feature for detection of fluctuating structures.

    KW - Lesions in magnetic resonance imaging

    KW - Multiple sclerosis

    KW - Temporal analysis

    KW - Time series analysis

    UR - http://www.scopus.com/inward/record.url?scp=0034152710&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0034152710&partnerID=8YFLogxK

    M3 - Article

    VL - 4

    SP - 31

    EP - 42

    JO - Medical Image Analysis

    JF - Medical Image Analysis

    SN - 1361-8415

    IS - 1

    ER -