A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury

Bo Wang, Marcel Prastawa, Andrei Irimia, Micah C. Chambers, Paul M. Vespa, John D. Van Horn, Guido Gerig

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

    Abstract

    Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Robust, reproducible segmentations of MR images with TBI are crucial for quantitative analysis of recovery and treatment efficacy. However, this is a significant challenge due to severe anatomy changes caused by edema (swelling), bleeding, tissue deformation, skull fracture, and other effects related to head injury. In this paper, we introduce a multi-modal image segmentation framework for longitudinal TBI images. The framework is initialized through manual input of primary lesion sites at each time point, which are then refined by a joint approach composed of Bayesian segmentation and construction of a personalized atlas. The personalized atlas construction estimates the average of the posteriors of the Bayesian segmentation at each time point and warps the average back to each time point to provide the updated priors for Bayesian segmentation. The difference between our approach and segmenting longitudinal images independently is that we use the information from all time points to improve the segmentations. Given a manual initialization, our framework automatically segments healthy structures (white matter, grey matter, cerebrospinal fluid) as well as different lesions such as hemorrhagic lesions and edema. Our framework can handle different sets of modalities at each time point, which provides flexibility in analyzing clinical scans. We show results on three subjects with acute baseline scans and chronic follow-up scans. The results demonstrate that joint analysis of all the points yields improved segmentation compared to independent analysis of the two time points.

    Original languageEnglish (US)
    Title of host publicationMedical Imaging 2012: Image Processing
    Volume8314
    DOIs
    StatePublished - 2012
    EventMedical Imaging 2012: Image Processing - San Diego, CA, United States
    Duration: Feb 6 2012Feb 9 2012

    Other

    OtherMedical Imaging 2012: Image Processing
    CountryUnited States
    CitySan Diego, CA
    Period2/6/122/9/12

    Fingerprint

    brain damage
    Brain
    lesions
    Cerebrospinal fluid
    edema
    Atlases
    Image segmentation
    Swelling
    Edema
    Tissue
    cerebrospinal fluid
    Skull Fractures
    disabilities
    Recovery
    bleeding
    skull
    Bayes Theorem
    anatomy
    yield point
    Chemical analysis

    Keywords

    • Atlas formation
    • Image segmentation
    • Longitudinal analysis

    ASJC Scopus subject areas

    • Atomic and Molecular Physics, and Optics
    • Electronic, Optical and Magnetic Materials
    • Biomaterials
    • Radiology Nuclear Medicine and imaging

    Cite this

    Wang, B., Prastawa, M., Irimia, A., Chambers, M. C., Vespa, P. M., Van Horn, J. D., & Gerig, G. (2012). A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury. In Medical Imaging 2012: Image Processing (Vol. 8314). [831402] https://doi.org/10.1117/12.911043

    A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury. / Wang, Bo; Prastawa, Marcel; Irimia, Andrei; Chambers, Micah C.; Vespa, Paul M.; Van Horn, John D.; Gerig, Guido.

    Medical Imaging 2012: Image Processing. Vol. 8314 2012. 831402.

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

    Wang, B, Prastawa, M, Irimia, A, Chambers, MC, Vespa, PM, Van Horn, JD & Gerig, G 2012, A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury. in Medical Imaging 2012: Image Processing. vol. 8314, 831402, Medical Imaging 2012: Image Processing, San Diego, CA, United States, 2/6/12. https://doi.org/10.1117/12.911043
    Wang B, Prastawa M, Irimia A, Chambers MC, Vespa PM, Van Horn JD et al. A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury. In Medical Imaging 2012: Image Processing. Vol. 8314. 2012. 831402 https://doi.org/10.1117/12.911043
    Wang, Bo ; Prastawa, Marcel ; Irimia, Andrei ; Chambers, Micah C. ; Vespa, Paul M. ; Van Horn, John D. ; Gerig, Guido. / A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury. Medical Imaging 2012: Image Processing. Vol. 8314 2012.
    @inproceedings{1314b7bc36c64640926d3dfcf4826741,
    title = "A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury",
    abstract = "Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Robust, reproducible segmentations of MR images with TBI are crucial for quantitative analysis of recovery and treatment efficacy. However, this is a significant challenge due to severe anatomy changes caused by edema (swelling), bleeding, tissue deformation, skull fracture, and other effects related to head injury. In this paper, we introduce a multi-modal image segmentation framework for longitudinal TBI images. The framework is initialized through manual input of primary lesion sites at each time point, which are then refined by a joint approach composed of Bayesian segmentation and construction of a personalized atlas. The personalized atlas construction estimates the average of the posteriors of the Bayesian segmentation at each time point and warps the average back to each time point to provide the updated priors for Bayesian segmentation. The difference between our approach and segmenting longitudinal images independently is that we use the information from all time points to improve the segmentations. Given a manual initialization, our framework automatically segments healthy structures (white matter, grey matter, cerebrospinal fluid) as well as different lesions such as hemorrhagic lesions and edema. Our framework can handle different sets of modalities at each time point, which provides flexibility in analyzing clinical scans. We show results on three subjects with acute baseline scans and chronic follow-up scans. The results demonstrate that joint analysis of all the points yields improved segmentation compared to independent analysis of the two time points.",
    keywords = "Atlas formation, Image segmentation, Longitudinal analysis",
    author = "Bo Wang and Marcel Prastawa and Andrei Irimia and Chambers, {Micah C.} and Vespa, {Paul M.} and {Van Horn}, {John D.} and Guido Gerig",
    year = "2012",
    doi = "10.1117/12.911043",
    language = "English (US)",
    isbn = "9780819489630",
    volume = "8314",
    booktitle = "Medical Imaging 2012: Image Processing",

    }

    TY - GEN

    T1 - A patient-specific segmentation framework for longitudinal MR images of traumatic brain injury

    AU - Wang, Bo

    AU - Prastawa, Marcel

    AU - Irimia, Andrei

    AU - Chambers, Micah C.

    AU - Vespa, Paul M.

    AU - Van Horn, John D.

    AU - Gerig, Guido

    PY - 2012

    Y1 - 2012

    N2 - Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Robust, reproducible segmentations of MR images with TBI are crucial for quantitative analysis of recovery and treatment efficacy. However, this is a significant challenge due to severe anatomy changes caused by edema (swelling), bleeding, tissue deformation, skull fracture, and other effects related to head injury. In this paper, we introduce a multi-modal image segmentation framework for longitudinal TBI images. The framework is initialized through manual input of primary lesion sites at each time point, which are then refined by a joint approach composed of Bayesian segmentation and construction of a personalized atlas. The personalized atlas construction estimates the average of the posteriors of the Bayesian segmentation at each time point and warps the average back to each time point to provide the updated priors for Bayesian segmentation. The difference between our approach and segmenting longitudinal images independently is that we use the information from all time points to improve the segmentations. Given a manual initialization, our framework automatically segments healthy structures (white matter, grey matter, cerebrospinal fluid) as well as different lesions such as hemorrhagic lesions and edema. Our framework can handle different sets of modalities at each time point, which provides flexibility in analyzing clinical scans. We show results on three subjects with acute baseline scans and chronic follow-up scans. The results demonstrate that joint analysis of all the points yields improved segmentation compared to independent analysis of the two time points.

    AB - Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Robust, reproducible segmentations of MR images with TBI are crucial for quantitative analysis of recovery and treatment efficacy. However, this is a significant challenge due to severe anatomy changes caused by edema (swelling), bleeding, tissue deformation, skull fracture, and other effects related to head injury. In this paper, we introduce a multi-modal image segmentation framework for longitudinal TBI images. The framework is initialized through manual input of primary lesion sites at each time point, which are then refined by a joint approach composed of Bayesian segmentation and construction of a personalized atlas. The personalized atlas construction estimates the average of the posteriors of the Bayesian segmentation at each time point and warps the average back to each time point to provide the updated priors for Bayesian segmentation. The difference between our approach and segmenting longitudinal images independently is that we use the information from all time points to improve the segmentations. Given a manual initialization, our framework automatically segments healthy structures (white matter, grey matter, cerebrospinal fluid) as well as different lesions such as hemorrhagic lesions and edema. Our framework can handle different sets of modalities at each time point, which provides flexibility in analyzing clinical scans. We show results on three subjects with acute baseline scans and chronic follow-up scans. The results demonstrate that joint analysis of all the points yields improved segmentation compared to independent analysis of the two time points.

    KW - Atlas formation

    KW - Image segmentation

    KW - Longitudinal analysis

    UR - http://www.scopus.com/inward/record.url?scp=84860752786&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84860752786&partnerID=8YFLogxK

    U2 - 10.1117/12.911043

    DO - 10.1117/12.911043

    M3 - Conference contribution

    AN - SCOPUS:84860752786

    SN - 9780819489630

    VL - 8314

    BT - Medical Imaging 2012: Image Processing

    ER -