Image databases in medical applications

Dissertation

Juha Koikkalainen

    Research output: ThesisDissertationCollection of Articles

    Abstract

    The number of medical images acquired yearly in hospitals increases all the time. These imaging data contain lots of information on the characteristics of anatomical structures and on their variations. This information can be utilized in numerous medical applications. In deformable model-based segmentation and registration methods, the information in the image databases can be used to give a priori information on the shape of the object studied and the gray-level values in the image, and on their variations. On the other hand, by studying the variations of the object of interest in different populations, the effects of, for example, aging, gender, and diseases on anatomical structures can be detected. In the work described in this Thesis, methods that utilize image databases in medical applications were studied. Methods were developed and compared for deformable model-based segmentation and registration. Model selection procedure, mean models, and combination of classifiers were studied for the construction of a good a priori model. Statistical and probabilistic shape models were generated to constrain the deformations in segmentation and registration so that only the shapes typical to the object studied were accepted. In the shape analysis of the striatum, both volume and local shape changes were studied. The effects of aging and gender, and also the asymmetries were examined. The results proved that the segmentation and registration accuracy of deformable model-based methods can be improved by utilizing the information in image databases. The databases used were relatively small. Therefore, the statistical and probabilistic methods were not able to model all the population-specific variation. On the other hand, the simpler methods, the model selection procedure, mean models, and combination of classifiers, gave good results also with the small image databases. Two main applications were the reconstruction of 3-D geometry from incomplete data and the segmentation of heart ventricles and atria from short- and long-axis magnetic resonance images. In both applications, the methods studied provided promising results. The shape analysis of the striatum showed that the volume of the striatum decreases in aging. Also, the shape of the striatum changes locally. Asymmetries in the shape were found, too, but any gender-related local shape differences were not found.
    Original languageEnglish
    QualificationDoctor Degree
    Awarding Institution
    • Helsinki University of Technology
    Supervisors/Advisors
    • Ilmoniemi, Risto, Supervisor, External person
    • Lötjönen, Jyrki, Advisor
    Award date17 Mar 2006
    Place of PublicationEspoo
    Publisher
    Print ISBNs951-22-8083-3
    Electronic ISBNs951-22-8084-1
    Publication statusPublished - 2006
    MoE publication typeG5 Doctoral dissertation (article)

    Fingerprint

    Medical applications
    Aging of materials
    Classifiers
    Magnetic resonance
    Imaging techniques
    Geometry

    Keywords

    • medical image processing
    • deformable models
    • statistical and probabilistic shape models
    • shape analysis

    Cite this

    Koikkalainen, J. (2006). Image databases in medical applications: Dissertation. Espoo: Helsinki University of Technology.
    Koikkalainen, Juha. / Image databases in medical applications : Dissertation. Espoo : Helsinki University of Technology, 2006. 123 p.
    @phdthesis{c322013a39bc4d8e9ecf1cd5a8095c9c,
    title = "Image databases in medical applications: Dissertation",
    abstract = "The number of medical images acquired yearly in hospitals increases all the time. These imaging data contain lots of information on the characteristics of anatomical structures and on their variations. This information can be utilized in numerous medical applications. In deformable model-based segmentation and registration methods, the information in the image databases can be used to give a priori information on the shape of the object studied and the gray-level values in the image, and on their variations. On the other hand, by studying the variations of the object of interest in different populations, the effects of, for example, aging, gender, and diseases on anatomical structures can be detected. In the work described in this Thesis, methods that utilize image databases in medical applications were studied. Methods were developed and compared for deformable model-based segmentation and registration. Model selection procedure, mean models, and combination of classifiers were studied for the construction of a good a priori model. Statistical and probabilistic shape models were generated to constrain the deformations in segmentation and registration so that only the shapes typical to the object studied were accepted. In the shape analysis of the striatum, both volume and local shape changes were studied. The effects of aging and gender, and also the asymmetries were examined. The results proved that the segmentation and registration accuracy of deformable model-based methods can be improved by utilizing the information in image databases. The databases used were relatively small. Therefore, the statistical and probabilistic methods were not able to model all the population-specific variation. On the other hand, the simpler methods, the model selection procedure, mean models, and combination of classifiers, gave good results also with the small image databases. Two main applications were the reconstruction of 3-D geometry from incomplete data and the segmentation of heart ventricles and atria from short- and long-axis magnetic resonance images. In both applications, the methods studied provided promising results. The shape analysis of the striatum showed that the volume of the striatum decreases in aging. Also, the shape of the striatum changes locally. Asymmetries in the shape were found, too, but any gender-related local shape differences were not found.",
    keywords = "medical image processing, deformable models, statistical and probabilistic shape models, shape analysis",
    author = "Juha Koikkalainen",
    note = "TK103 Teknillinen korkeakoulu, Teknillisen fysiikan ja matematiikan osasto, L{\"a}{\"a}ketieteellisen tekniikan laboratorio Project code: 1271 51 p. + app. 72 p.",
    year = "2006",
    language = "English",
    isbn = "951-22-8083-3",
    series = "TKK Dissertations",
    publisher = "Helsinki University of Technology",
    address = "Finland",
    school = "Helsinki University of Technology",

    }

    Koikkalainen, J 2006, 'Image databases in medical applications: Dissertation', Doctor Degree, Helsinki University of Technology, Espoo.

    Image databases in medical applications : Dissertation. / Koikkalainen, Juha.

    Espoo : Helsinki University of Technology, 2006. 123 p.

    Research output: ThesisDissertationCollection of Articles

    TY - THES

    T1 - Image databases in medical applications

    T2 - Dissertation

    AU - Koikkalainen, Juha

    N1 - TK103 Teknillinen korkeakoulu, Teknillisen fysiikan ja matematiikan osasto, Lääketieteellisen tekniikan laboratorio Project code: 1271 51 p. + app. 72 p.

    PY - 2006

    Y1 - 2006

    N2 - The number of medical images acquired yearly in hospitals increases all the time. These imaging data contain lots of information on the characteristics of anatomical structures and on their variations. This information can be utilized in numerous medical applications. In deformable model-based segmentation and registration methods, the information in the image databases can be used to give a priori information on the shape of the object studied and the gray-level values in the image, and on their variations. On the other hand, by studying the variations of the object of interest in different populations, the effects of, for example, aging, gender, and diseases on anatomical structures can be detected. In the work described in this Thesis, methods that utilize image databases in medical applications were studied. Methods were developed and compared for deformable model-based segmentation and registration. Model selection procedure, mean models, and combination of classifiers were studied for the construction of a good a priori model. Statistical and probabilistic shape models were generated to constrain the deformations in segmentation and registration so that only the shapes typical to the object studied were accepted. In the shape analysis of the striatum, both volume and local shape changes were studied. The effects of aging and gender, and also the asymmetries were examined. The results proved that the segmentation and registration accuracy of deformable model-based methods can be improved by utilizing the information in image databases. The databases used were relatively small. Therefore, the statistical and probabilistic methods were not able to model all the population-specific variation. On the other hand, the simpler methods, the model selection procedure, mean models, and combination of classifiers, gave good results also with the small image databases. Two main applications were the reconstruction of 3-D geometry from incomplete data and the segmentation of heart ventricles and atria from short- and long-axis magnetic resonance images. In both applications, the methods studied provided promising results. The shape analysis of the striatum showed that the volume of the striatum decreases in aging. Also, the shape of the striatum changes locally. Asymmetries in the shape were found, too, but any gender-related local shape differences were not found.

    AB - The number of medical images acquired yearly in hospitals increases all the time. These imaging data contain lots of information on the characteristics of anatomical structures and on their variations. This information can be utilized in numerous medical applications. In deformable model-based segmentation and registration methods, the information in the image databases can be used to give a priori information on the shape of the object studied and the gray-level values in the image, and on their variations. On the other hand, by studying the variations of the object of interest in different populations, the effects of, for example, aging, gender, and diseases on anatomical structures can be detected. In the work described in this Thesis, methods that utilize image databases in medical applications were studied. Methods were developed and compared for deformable model-based segmentation and registration. Model selection procedure, mean models, and combination of classifiers were studied for the construction of a good a priori model. Statistical and probabilistic shape models were generated to constrain the deformations in segmentation and registration so that only the shapes typical to the object studied were accepted. In the shape analysis of the striatum, both volume and local shape changes were studied. The effects of aging and gender, and also the asymmetries were examined. The results proved that the segmentation and registration accuracy of deformable model-based methods can be improved by utilizing the information in image databases. The databases used were relatively small. Therefore, the statistical and probabilistic methods were not able to model all the population-specific variation. On the other hand, the simpler methods, the model selection procedure, mean models, and combination of classifiers, gave good results also with the small image databases. Two main applications were the reconstruction of 3-D geometry from incomplete data and the segmentation of heart ventricles and atria from short- and long-axis magnetic resonance images. In both applications, the methods studied provided promising results. The shape analysis of the striatum showed that the volume of the striatum decreases in aging. Also, the shape of the striatum changes locally. Asymmetries in the shape were found, too, but any gender-related local shape differences were not found.

    KW - medical image processing

    KW - deformable models

    KW - statistical and probabilistic shape models

    KW - shape analysis

    M3 - Dissertation

    SN - 951-22-8083-3

    T3 - TKK Dissertations

    PB - Helsinki University of Technology

    CY - Espoo

    ER -

    Koikkalainen J. Image databases in medical applications: Dissertation. Espoo: Helsinki University of Technology, 2006. 123 p.