Fully automated segmentation of the mitral leaflets using multi-atlas label fusion and deformable medial modeling

Comprehensive visual and quantitative analysis of in vivo human mitral valve morphology is central to the diagnosis and surgical treatment of mitral valve disease. Real-time 3D transesophageal echocardiography (3D TEE) is a practical, highly informative imaging modality for examining the mitral valve in a clinical setting. To facilitate visual and quantitative 3D TEE image analysis, we describe a fully automated method for segmenting the mitral leaflets in 3D TEE image data. The algorithm integrates complementary probabilistic segmentation and shape modeling techniques:

  • multi-atlas joint label fusion, and
  • deformable modeling with continuous medial representation

to automatically generate 3D geometric models of the mitral leaflets from 3D TEE image data. These models are unique in that they establish a shape-based coordinate system on the valves of different subjects and represent the leaflets volumetrically, as structures with locally varying thickness. Without any user interaction, the method accurately captures patient-specific leaflet geometry at both systole and diastole in 3D TEE data acquired from a mixed population of subjects with normal valve morphology and mitral valve disease.

fully automated segmentation of the mitral leaflets

Automatic segmentation of the mitral leaflets at diastole (top row) and systole (bottom row) for a given patient. First, a probabilistic segmentation is generated by multi-atlas label fusion (red = anterior leaflet, blue = posterior leaflet). Then the cm-rep template (translucent) is initialized to the multi-atlas segmentation and the template is deformed to obtain a medial model of the mitral leaflets. The fitted diastolic model is used to initialize model fitting of the same subject’s valve at systole.

  • [DOI] A. M. Pouch, H. Wang, M. Takabe, B. M. Jackson, J. Gorman 3rd, R. C. Gorman, P. A. Yushkevich, and C. M. Sehgal, “Fully automatic segmentation of the mitral leaflets in 3D transesophageal echocardiographic images using multi-atlas joint label fusion and deformable medial modeling.,” Med Image Anal, vol. 18, iss. 1, pp. 118-129, 2014.
    [Bibtex]
    @ARTICLE{Pouch2014MIA,
    author = {Pouch, A. M. and Wang, H. and Takabe, M. and Jackson, B. M. and Gorman,
    3rd, JH and Gorman, R. C. and Yushkevich, P. A. and Sehgal, C. M.},
    title = {{F}ully automatic segmentation of the mitral leaflets in 3{D} transesophageal
    echocardiographic images using multi-atlas joint label fusion and
    deformable medial modeling.},
    journal = {{M}ed {I}mage {A}nal},
    year = {2014},
    volume = {18},
    pages = {118--129},
    number = {1},
    month = {Jan},
    abstract = {Comprehensive visual and quantitative analysis of in vivo human mitral
    valve morphology is central to the diagnosis and surgical treatment
    of mitral valve disease. Real-time 3D transesophageal echocardiography
    (3D TEE) is a practical, highly informative imaging modality for
    examining the mitral valve in a clinical setting. To facilitate visual
    and quantitative 3D TEE image analysis, we describe a fully automated
    method for segmenting the mitral leaflets in 3D TEE image data. The
    algorithm integrates complementary probabilistic segmentation and
    shape modeling techniques (multi-atlas joint label fusion and deformable
    modeling with continuous medial representation) to automatically
    generate 3D geometric models of the mitral leaflets from 3D TEE image
    data. These models are unique in that they establish a shape-based
    coordinate system on the valves of different subjects and represent
    the leaflets volumetrically, as structures with locally varying thickness.
    In this work, expert image analysis is the gold standard for evaluating
    automatic segmentation. Without any user interaction, we demonstrate
    that the automatic segmentation method accurately captures patient-specific
    leaflet geometry at both systole and diastole in 3D TEE data acquired
    from a mixed population of subjects with normal valve morphology
    and mitral valve disease.},
    doi = {10.1016/j.media.2013.10.001},
    institution = {{D}epartment of {B}ioengineering, {U}niversity of {P}ennsylvania,
    {P}hiladelphia, {PA}, {U}nited {S}tates; {G}orman {C}ardiovascular
    {R}esearch {G}roup, {U}niversity of {P}ennsylvania, {P}hiladelphia,
    {PA}, {U}nited {S}tates. {E}lectronic address: pouch@seas.upenn.edu.},
    language = {eng},
    medline-pst = {ppublish},
    owner = {alison},
    pii = {S1361-8415(13)00142-4},
    pmid = {24184435},
    timestamp = {2014.02.27},
    url = {http://dx.doi.org/10.1016/j.media.2013.10.001}
    }