Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation

Marcel Prastawa, Suyash P. Awate, Guido Gerig

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

    Abstract

    Longitudinal analysis of anatomical changes is a vital component in many personalized-medicine applications for predicting disease onset, determining growth/atrophy patterns, evaluating disease progression, and monitoring recovery. Estimating anatomical changes in longitudinal studies, especially through magnetic resonance (MR) images, is challenging because of temporal variability in shape (e.g. from growth/atrophy) and appearance (e.g. due to imaging parameters and tissue properties affecting intensity contrast, or from scanner calibration). This paper proposes a novel mathematical framework for constructing subject-specific longitudinal anatomical models. The proposed method solves a generalized problem of joint segmentation, registration, and subject-specific atlas building, which involves not just two images, but an entire longitudinal image sequence. The proposed framework describes a novel approach that integrates fundamental principles that underpin methods for image segmentation, image registration, and atlas construction. This paper presents evaluation on simulated longitudinal data and on clinical longitudinal brain MRI data. The results demonstrate that the proposed framework effectively integrates information from 4-D spatiotemporal data to generate spatiotemporal models that allow analysis of anatomical changes over time.

    Original languageEnglish (US)
    Title of host publication2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012
    Pages49-56
    Number of pages8
    DOIs
    StatePublished - 2012
    Event2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012 - Breckenridge, CO, United States
    Duration: Jan 9 2012Jan 10 2012

    Other

    Other2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012
    CountryUnited States
    CityBreckenridge, CO
    Period1/9/121/10/12

    Fingerprint

    Anatomic Models
    Spatio-temporal Model
    Atlases
    Atlas
    Registration
    Atrophy
    Segmentation
    Joints
    Precision Medicine
    Image registration
    Magnetic resonance
    Growth
    Image segmentation
    Integrate
    Longitudinal Analysis
    Magnetic resonance imaging
    Calibration
    Medicine
    Longitudinal Studies
    Disease Progression

    ASJC Scopus subject areas

    • Applied Mathematics
    • Radiology Nuclear Medicine and imaging
    • Biomedical Engineering

    Cite this

    Prastawa, M., Awate, S. P., & Gerig, G. (2012). Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation. In 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012 (pp. 49-56). [6164740] https://doi.org/10.1109/MMBIA.2012.6164740

    Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation. / Prastawa, Marcel; Awate, Suyash P.; Gerig, Guido.

    2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012. 2012. p. 49-56 6164740.

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

    Prastawa, M, Awate, SP & Gerig, G 2012, Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation. in 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012., 6164740, pp. 49-56, 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012, Breckenridge, CO, United States, 1/9/12. https://doi.org/10.1109/MMBIA.2012.6164740
    Prastawa M, Awate SP, Gerig G. Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation. In 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012. 2012. p. 49-56. 6164740 https://doi.org/10.1109/MMBIA.2012.6164740
    Prastawa, Marcel ; Awate, Suyash P. ; Gerig, Guido. / Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation. 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012. 2012. pp. 49-56
    @inproceedings{06504d2f783449a9991625c24f613ab0,
    title = "Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation",
    abstract = "Longitudinal analysis of anatomical changes is a vital component in many personalized-medicine applications for predicting disease onset, determining growth/atrophy patterns, evaluating disease progression, and monitoring recovery. Estimating anatomical changes in longitudinal studies, especially through magnetic resonance (MR) images, is challenging because of temporal variability in shape (e.g. from growth/atrophy) and appearance (e.g. due to imaging parameters and tissue properties affecting intensity contrast, or from scanner calibration). This paper proposes a novel mathematical framework for constructing subject-specific longitudinal anatomical models. The proposed method solves a generalized problem of joint segmentation, registration, and subject-specific atlas building, which involves not just two images, but an entire longitudinal image sequence. The proposed framework describes a novel approach that integrates fundamental principles that underpin methods for image segmentation, image registration, and atlas construction. This paper presents evaluation on simulated longitudinal data and on clinical longitudinal brain MRI data. The results demonstrate that the proposed framework effectively integrates information from 4-D spatiotemporal data to generate spatiotemporal models that allow analysis of anatomical changes over time.",
    author = "Marcel Prastawa and Awate, {Suyash P.} and Guido Gerig",
    year = "2012",
    doi = "10.1109/MMBIA.2012.6164740",
    language = "English (US)",
    isbn = "9781467303521",
    pages = "49--56",
    booktitle = "2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012",

    }

    TY - GEN

    T1 - Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation

    AU - Prastawa, Marcel

    AU - Awate, Suyash P.

    AU - Gerig, Guido

    PY - 2012

    Y1 - 2012

    N2 - Longitudinal analysis of anatomical changes is a vital component in many personalized-medicine applications for predicting disease onset, determining growth/atrophy patterns, evaluating disease progression, and monitoring recovery. Estimating anatomical changes in longitudinal studies, especially through magnetic resonance (MR) images, is challenging because of temporal variability in shape (e.g. from growth/atrophy) and appearance (e.g. due to imaging parameters and tissue properties affecting intensity contrast, or from scanner calibration). This paper proposes a novel mathematical framework for constructing subject-specific longitudinal anatomical models. The proposed method solves a generalized problem of joint segmentation, registration, and subject-specific atlas building, which involves not just two images, but an entire longitudinal image sequence. The proposed framework describes a novel approach that integrates fundamental principles that underpin methods for image segmentation, image registration, and atlas construction. This paper presents evaluation on simulated longitudinal data and on clinical longitudinal brain MRI data. The results demonstrate that the proposed framework effectively integrates information from 4-D spatiotemporal data to generate spatiotemporal models that allow analysis of anatomical changes over time.

    AB - Longitudinal analysis of anatomical changes is a vital component in many personalized-medicine applications for predicting disease onset, determining growth/atrophy patterns, evaluating disease progression, and monitoring recovery. Estimating anatomical changes in longitudinal studies, especially through magnetic resonance (MR) images, is challenging because of temporal variability in shape (e.g. from growth/atrophy) and appearance (e.g. due to imaging parameters and tissue properties affecting intensity contrast, or from scanner calibration). This paper proposes a novel mathematical framework for constructing subject-specific longitudinal anatomical models. The proposed method solves a generalized problem of joint segmentation, registration, and subject-specific atlas building, which involves not just two images, but an entire longitudinal image sequence. The proposed framework describes a novel approach that integrates fundamental principles that underpin methods for image segmentation, image registration, and atlas construction. This paper presents evaluation on simulated longitudinal data and on clinical longitudinal brain MRI data. The results demonstrate that the proposed framework effectively integrates information from 4-D spatiotemporal data to generate spatiotemporal models that allow analysis of anatomical changes over time.

    UR - http://www.scopus.com/inward/record.url?scp=84859885173&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84859885173&partnerID=8YFLogxK

    U2 - 10.1109/MMBIA.2012.6164740

    DO - 10.1109/MMBIA.2012.6164740

    M3 - Conference contribution

    SN - 9781467303521

    SP - 49

    EP - 56

    BT - 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, MMBIA 2012

    ER -