Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries

Rong Xu, Jun Ohya, Bo Zhang, Masakatsu G. Fujie, Yoshinobu Sato

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

    1 Citation (Scopus)

    Abstract

    With the wide clinical application of 3D ultrasound (US) imaging, automatic location of fetal facial features from US volumes for navigating fetoscopic tracheal occlusion (FETO) surgeries becomes possible, which plays an important role in reducing surgical risk. In this paper, we propose a feature-based method to automatically detect 3D fetal face and accurately locate key facial features without any priori knowledge or training data. The candidates of the key facial features, such as the nose, eyes, nose upper bridge and upper lip are detected by analyzing the mean and Gaussian curvatures of the facial surface. Each feature is gradually identified from the candidates by a boosting traversal scheme based on the spatial relations between each feature. In experiments, all key feature points are detected for each case, and thus a detection success rate of 100% is achieved by using 72 3D US images from a test database of 6 fetal faces in the frontal view and any pose within 15° from the frontal view, and the location error 3.18 ± 0.91 mm of the detected upper lip for all test data is obtained, which can be tolerated by the FETO surgery. Moreover, this system has a high efficiency and can detect all key facial features in about 625 ms on a quad-core 2.60 GHz computer.

    Original languageEnglish
    Title of host publication2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013
    DOIs
    Publication statusPublished - 2013
    Event2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013 - Shanghai
    Duration: 2013 Apr 222013 Apr 26

    Other

    Other2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013
    CityShanghai
    Period13/4/2213/4/26

    Fingerprint

    Face recognition
    Surgery
    Ultrasonics
    Imaging techniques
    Experiments

    Keywords

    • 3D fetal face detection
    • 3D ultrasound image
    • face curvature
    • FETO surgery
    • HK classification

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Xu, R., Ohya, J., Zhang, B., Fujie, M. G., & Sato, Y. (2013). Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries. In 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013 [6553722] https://doi.org/10.1109/FG.2013.6553722

    Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries. / Xu, Rong; Ohya, Jun; Zhang, Bo; Fujie, Masakatsu G.; Sato, Yoshinobu.

    2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013. 2013. 6553722.

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

    Xu, R, Ohya, J, Zhang, B, Fujie, MG & Sato, Y 2013, Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries. in 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013., 6553722, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013, Shanghai, 13/4/22. https://doi.org/10.1109/FG.2013.6553722
    Xu R, Ohya J, Zhang B, Fujie MG, Sato Y. Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries. In 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013. 2013. 6553722 https://doi.org/10.1109/FG.2013.6553722
    Xu, Rong ; Ohya, Jun ; Zhang, Bo ; Fujie, Masakatsu G. ; Sato, Yoshinobu. / Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries. 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013. 2013.
    @inproceedings{e7e570092c4c42f09137b34783c869d8,
    title = "Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries",
    abstract = "With the wide clinical application of 3D ultrasound (US) imaging, automatic location of fetal facial features from US volumes for navigating fetoscopic tracheal occlusion (FETO) surgeries becomes possible, which plays an important role in reducing surgical risk. In this paper, we propose a feature-based method to automatically detect 3D fetal face and accurately locate key facial features without any priori knowledge or training data. The candidates of the key facial features, such as the nose, eyes, nose upper bridge and upper lip are detected by analyzing the mean and Gaussian curvatures of the facial surface. Each feature is gradually identified from the candidates by a boosting traversal scheme based on the spatial relations between each feature. In experiments, all key feature points are detected for each case, and thus a detection success rate of 100{\%} is achieved by using 72 3D US images from a test database of 6 fetal faces in the frontal view and any pose within 15° from the frontal view, and the location error 3.18 ± 0.91 mm of the detected upper lip for all test data is obtained, which can be tolerated by the FETO surgery. Moreover, this system has a high efficiency and can detect all key facial features in about 625 ms on a quad-core 2.60 GHz computer.",
    keywords = "3D fetal face detection, 3D ultrasound image, face curvature, FETO surgery, HK classification",
    author = "Rong Xu and Jun Ohya and Bo Zhang and Fujie, {Masakatsu G.} and Yoshinobu Sato",
    year = "2013",
    doi = "10.1109/FG.2013.6553722",
    language = "English",
    isbn = "9781467355452",
    booktitle = "2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013",

    }

    TY - GEN

    T1 - Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries

    AU - Xu, Rong

    AU - Ohya, Jun

    AU - Zhang, Bo

    AU - Fujie, Masakatsu G.

    AU - Sato, Yoshinobu

    PY - 2013

    Y1 - 2013

    N2 - With the wide clinical application of 3D ultrasound (US) imaging, automatic location of fetal facial features from US volumes for navigating fetoscopic tracheal occlusion (FETO) surgeries becomes possible, which plays an important role in reducing surgical risk. In this paper, we propose a feature-based method to automatically detect 3D fetal face and accurately locate key facial features without any priori knowledge or training data. The candidates of the key facial features, such as the nose, eyes, nose upper bridge and upper lip are detected by analyzing the mean and Gaussian curvatures of the facial surface. Each feature is gradually identified from the candidates by a boosting traversal scheme based on the spatial relations between each feature. In experiments, all key feature points are detected for each case, and thus a detection success rate of 100% is achieved by using 72 3D US images from a test database of 6 fetal faces in the frontal view and any pose within 15° from the frontal view, and the location error 3.18 ± 0.91 mm of the detected upper lip for all test data is obtained, which can be tolerated by the FETO surgery. Moreover, this system has a high efficiency and can detect all key facial features in about 625 ms on a quad-core 2.60 GHz computer.

    AB - With the wide clinical application of 3D ultrasound (US) imaging, automatic location of fetal facial features from US volumes for navigating fetoscopic tracheal occlusion (FETO) surgeries becomes possible, which plays an important role in reducing surgical risk. In this paper, we propose a feature-based method to automatically detect 3D fetal face and accurately locate key facial features without any priori knowledge or training data. The candidates of the key facial features, such as the nose, eyes, nose upper bridge and upper lip are detected by analyzing the mean and Gaussian curvatures of the facial surface. Each feature is gradually identified from the candidates by a boosting traversal scheme based on the spatial relations between each feature. In experiments, all key feature points are detected for each case, and thus a detection success rate of 100% is achieved by using 72 3D US images from a test database of 6 fetal faces in the frontal view and any pose within 15° from the frontal view, and the location error 3.18 ± 0.91 mm of the detected upper lip for all test data is obtained, which can be tolerated by the FETO surgery. Moreover, this system has a high efficiency and can detect all key facial features in about 625 ms on a quad-core 2.60 GHz computer.

    KW - 3D fetal face detection

    KW - 3D ultrasound image

    KW - face curvature

    KW - FETO surgery

    KW - HK classification

    UR - http://www.scopus.com/inward/record.url?scp=84881540809&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84881540809&partnerID=8YFLogxK

    U2 - 10.1109/FG.2013.6553722

    DO - 10.1109/FG.2013.6553722

    M3 - Conference contribution

    AN - SCOPUS:84881540809

    SN - 9781467355452

    BT - 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013

    ER -