Image registration and segmentation in longitudinal MRI using temporal appearance modeling

Yang Gao, Miaomiao Zhang, Karen Grewen, P. Thomas Fletcher, Guido Gerig

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

    Abstract

    With increasing use of subject-specific longitudinal imaging for assessment of development, degeneration and disease progression, there is a clear need for image analysis segmentation/registration tools dedicated to 4D image time series. Previous work has mostly focused on temporal modeling of geometric deformations and shape changes, assuming that image intensity changes can be normalized. However, in studies of early infant development or aging, e.g., we encounter low contrast and appearance alterations due to tissue property changes which pose challenges to temporal registration and 4D segmentation. The two problems are linked since registration can be solved if appearance changes are accounted for, but 4D segmentation requires registration of image time series. In this paper, we propose to integrate a temporal appearance change model into diffeomorphic registration thus accounting for such variations, where voxel-wise intensity model parameters are calculated jointly with temporal image coregistration. Moreover, we demonstrate novel 4D segmentation of co-registered images that uses local intensity change rather than intensity itself via Gaussian mixture model. Both methods can be seen as two stages of an integrated registration/segmentation framework for 4D time-discrete image data making use of the same underlying model of longitudinal appearance changes. We demonstrate feasibility of the new approach with verification on longitudinal, multimodal pediatric MRI of infants in the age range neonates to 24 months.

    Original languageEnglish (US)
    Title of host publication2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings
    PublisherIEEE Computer Society
    Pages629-632
    Number of pages4
    Volume2016-June
    ISBN (Electronic)9781479923502
    DOIs
    StatePublished - Jun 15 2016
    Event2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Prague, Czech Republic
    Duration: Apr 13 2016Apr 16 2016

    Other

    Other2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
    CountryCzech Republic
    CityPrague
    Period4/13/164/16/16

    Fingerprint

    Image registration
    Image segmentation
    Magnetic resonance imaging
    Time series
    Pediatrics
    Image analysis
    Aging of materials
    Tissue
    Imaging techniques
    Child Development
    Disease Progression
    Newborn Infant

    Keywords

    • 4D segmentation and registration
    • longitudinal imaging
    • Temporal appearance modeling

    ASJC Scopus subject areas

    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging

    Cite this

    Gao, Y., Zhang, M., Grewen, K., Fletcher, P. T., & Gerig, G. (2016). Image registration and segmentation in longitudinal MRI using temporal appearance modeling. In 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings (Vol. 2016-June, pp. 629-632). [7493346] IEEE Computer Society. https://doi.org/10.1109/ISBI.2016.7493346

    Image registration and segmentation in longitudinal MRI using temporal appearance modeling. / Gao, Yang; Zhang, Miaomiao; Grewen, Karen; Fletcher, P. Thomas; Gerig, Guido.

    2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. Vol. 2016-June IEEE Computer Society, 2016. p. 629-632 7493346.

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

    Gao, Y, Zhang, M, Grewen, K, Fletcher, PT & Gerig, G 2016, Image registration and segmentation in longitudinal MRI using temporal appearance modeling. in 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. vol. 2016-June, 7493346, IEEE Computer Society, pp. 629-632, 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016, Prague, Czech Republic, 4/13/16. https://doi.org/10.1109/ISBI.2016.7493346
    Gao Y, Zhang M, Grewen K, Fletcher PT, Gerig G. Image registration and segmentation in longitudinal MRI using temporal appearance modeling. In 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. Vol. 2016-June. IEEE Computer Society. 2016. p. 629-632. 7493346 https://doi.org/10.1109/ISBI.2016.7493346
    Gao, Yang ; Zhang, Miaomiao ; Grewen, Karen ; Fletcher, P. Thomas ; Gerig, Guido. / Image registration and segmentation in longitudinal MRI using temporal appearance modeling. 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. Vol. 2016-June IEEE Computer Society, 2016. pp. 629-632
    @inproceedings{4c206ddc19104cfb813c2379507d321f,
    title = "Image registration and segmentation in longitudinal MRI using temporal appearance modeling",
    abstract = "With increasing use of subject-specific longitudinal imaging for assessment of development, degeneration and disease progression, there is a clear need for image analysis segmentation/registration tools dedicated to 4D image time series. Previous work has mostly focused on temporal modeling of geometric deformations and shape changes, assuming that image intensity changes can be normalized. However, in studies of early infant development or aging, e.g., we encounter low contrast and appearance alterations due to tissue property changes which pose challenges to temporal registration and 4D segmentation. The two problems are linked since registration can be solved if appearance changes are accounted for, but 4D segmentation requires registration of image time series. In this paper, we propose to integrate a temporal appearance change model into diffeomorphic registration thus accounting for such variations, where voxel-wise intensity model parameters are calculated jointly with temporal image coregistration. Moreover, we demonstrate novel 4D segmentation of co-registered images that uses local intensity change rather than intensity itself via Gaussian mixture model. Both methods can be seen as two stages of an integrated registration/segmentation framework for 4D time-discrete image data making use of the same underlying model of longitudinal appearance changes. We demonstrate feasibility of the new approach with verification on longitudinal, multimodal pediatric MRI of infants in the age range neonates to 24 months.",
    keywords = "4D segmentation and registration, longitudinal imaging, Temporal appearance modeling",
    author = "Yang Gao and Miaomiao Zhang and Karen Grewen and Fletcher, {P. Thomas} and Guido Gerig",
    year = "2016",
    month = "6",
    day = "15",
    doi = "10.1109/ISBI.2016.7493346",
    language = "English (US)",
    volume = "2016-June",
    pages = "629--632",
    booktitle = "2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings",
    publisher = "IEEE Computer Society",
    address = "United States",

    }

    TY - GEN

    T1 - Image registration and segmentation in longitudinal MRI using temporal appearance modeling

    AU - Gao, Yang

    AU - Zhang, Miaomiao

    AU - Grewen, Karen

    AU - Fletcher, P. Thomas

    AU - Gerig, Guido

    PY - 2016/6/15

    Y1 - 2016/6/15

    N2 - With increasing use of subject-specific longitudinal imaging for assessment of development, degeneration and disease progression, there is a clear need for image analysis segmentation/registration tools dedicated to 4D image time series. Previous work has mostly focused on temporal modeling of geometric deformations and shape changes, assuming that image intensity changes can be normalized. However, in studies of early infant development or aging, e.g., we encounter low contrast and appearance alterations due to tissue property changes which pose challenges to temporal registration and 4D segmentation. The two problems are linked since registration can be solved if appearance changes are accounted for, but 4D segmentation requires registration of image time series. In this paper, we propose to integrate a temporal appearance change model into diffeomorphic registration thus accounting for such variations, where voxel-wise intensity model parameters are calculated jointly with temporal image coregistration. Moreover, we demonstrate novel 4D segmentation of co-registered images that uses local intensity change rather than intensity itself via Gaussian mixture model. Both methods can be seen as two stages of an integrated registration/segmentation framework for 4D time-discrete image data making use of the same underlying model of longitudinal appearance changes. We demonstrate feasibility of the new approach with verification on longitudinal, multimodal pediatric MRI of infants in the age range neonates to 24 months.

    AB - With increasing use of subject-specific longitudinal imaging for assessment of development, degeneration and disease progression, there is a clear need for image analysis segmentation/registration tools dedicated to 4D image time series. Previous work has mostly focused on temporal modeling of geometric deformations and shape changes, assuming that image intensity changes can be normalized. However, in studies of early infant development or aging, e.g., we encounter low contrast and appearance alterations due to tissue property changes which pose challenges to temporal registration and 4D segmentation. The two problems are linked since registration can be solved if appearance changes are accounted for, but 4D segmentation requires registration of image time series. In this paper, we propose to integrate a temporal appearance change model into diffeomorphic registration thus accounting for such variations, where voxel-wise intensity model parameters are calculated jointly with temporal image coregistration. Moreover, we demonstrate novel 4D segmentation of co-registered images that uses local intensity change rather than intensity itself via Gaussian mixture model. Both methods can be seen as two stages of an integrated registration/segmentation framework for 4D time-discrete image data making use of the same underlying model of longitudinal appearance changes. We demonstrate feasibility of the new approach with verification on longitudinal, multimodal pediatric MRI of infants in the age range neonates to 24 months.

    KW - 4D segmentation and registration

    KW - longitudinal imaging

    KW - Temporal appearance modeling

    UR - http://www.scopus.com/inward/record.url?scp=84978370257&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84978370257&partnerID=8YFLogxK

    U2 - 10.1109/ISBI.2016.7493346

    DO - 10.1109/ISBI.2016.7493346

    M3 - Conference contribution

    AN - SCOPUS:84978370257

    VL - 2016-June

    SP - 629

    EP - 632

    BT - 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings

    PB - IEEE Computer Society

    ER -