Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries

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

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

    1 Citation (Scopus)

    Abstract

    Recently, a minimally invasive surgery (MIS) called fetoscopic tracheal occlusion (FETO) was developed to treat severe congenital diaphragmatic hernia (CDH) via fetoscopy, by which a detachable balloon is placed into the fetal trachea for preventing pulmonary hypoplasia through increasing the pressure of the chest cavity. This surgery is so dangerous that a supporting system for navigating surgeries is deemed necessary. In this paper, to guide a surgical tool to be inserted into the fetal trachea, an automatic approach is proposed to detect and track the fetal face and mouth via fetoscopic video sequencing. More specifically, the AdaBoost algorithm is utilized as a classifier to detect the fetal face based on Haar-like features, which calculate the difference between the sums of the pixel intensities in each adjacent region at a specific location in a detection window. Then, the CamShift algorithm based on an iterative search in a color histogram is applied to track the fetal face, and the fetal mouth is fitted by an ellipse detected via an improved iterative randomized Hough transform approach. The experimental results demonstrate that the proposed automatic approach can accurately detect and track the fetal face and mouth in real-time in a fetoscopic video sequence, as well as provide an effective and timely feedback to the robot control system of the surgical tool for FETO surgeries.

    Original languageEnglish
    Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
    Volume8671
    DOIs
    Publication statusPublished - 2013
    EventMedical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling - Lake Buena Vista, FL
    Duration: 2013 Feb 122013 Feb 14

    Other

    OtherMedical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling
    CityLake Buena Vista, FL
    Period13/2/1213/2/14

    Fingerprint

    mouth
    surgery
    Surgery
    Face
    trachea
    Real-time
    occlusion
    Occlusion
    robot control
    Minimally Invasive Surgery
    Color Histogram
    Adaptive boosting
    Hough Transform
    Balloon
    sequencing
    Hough transforms
    Robot Control
    AdaBoost
    chest
    Balloons

    Keywords

    • AdaBoost classifier
    • CamShift algorithm
    • Fetal face tracking
    • Fetal mouth detection
    • Fetoscopic video sequence
    • Haar-like features
    • Iterative randomized hough transform (IRHT)

    ASJC Scopus subject areas

    • Applied Mathematics
    • Computer Science Applications
    • Electrical and Electronic Engineering
    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics

    Cite this

    Xu, R., Xie, T., Ohya, J., Zhang, B., Sato, Y., & Fujie, M. G. (2013). Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 8671). [86710Z] https://doi.org/10.1117/12.2002803

    Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries. / Xu, Rong; Xie, Tianliang; Ohya, Jun; Zhang, Bo; Sato, Yoshinobu; Fujie, Masakatsu G.

    Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8671 2013. 86710Z.

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

    Xu, R, Xie, T, Ohya, J, Zhang, B, Sato, Y & Fujie, MG 2013, Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 8671, 86710Z, Medical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling, Lake Buena Vista, FL, 13/2/12. https://doi.org/10.1117/12.2002803
    Xu R, Xie T, Ohya J, Zhang B, Sato Y, Fujie MG. Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8671. 2013. 86710Z https://doi.org/10.1117/12.2002803
    Xu, Rong ; Xie, Tianliang ; Ohya, Jun ; Zhang, Bo ; Sato, Yoshinobu ; Fujie, Masakatsu G. / Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8671 2013.
    @inproceedings{551627242bf24406a9fb20bf57b66792,
    title = "Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries",
    abstract = "Recently, a minimally invasive surgery (MIS) called fetoscopic tracheal occlusion (FETO) was developed to treat severe congenital diaphragmatic hernia (CDH) via fetoscopy, by which a detachable balloon is placed into the fetal trachea for preventing pulmonary hypoplasia through increasing the pressure of the chest cavity. This surgery is so dangerous that a supporting system for navigating surgeries is deemed necessary. In this paper, to guide a surgical tool to be inserted into the fetal trachea, an automatic approach is proposed to detect and track the fetal face and mouth via fetoscopic video sequencing. More specifically, the AdaBoost algorithm is utilized as a classifier to detect the fetal face based on Haar-like features, which calculate the difference between the sums of the pixel intensities in each adjacent region at a specific location in a detection window. Then, the CamShift algorithm based on an iterative search in a color histogram is applied to track the fetal face, and the fetal mouth is fitted by an ellipse detected via an improved iterative randomized Hough transform approach. The experimental results demonstrate that the proposed automatic approach can accurately detect and track the fetal face and mouth in real-time in a fetoscopic video sequence, as well as provide an effective and timely feedback to the robot control system of the surgical tool for FETO surgeries.",
    keywords = "AdaBoost classifier, CamShift algorithm, Fetal face tracking, Fetal mouth detection, Fetoscopic video sequence, Haar-like features, Iterative randomized hough transform (IRHT)",
    author = "Rong Xu and Tianliang Xie and Jun Ohya and Bo Zhang and Yoshinobu Sato and Fujie, {Masakatsu G.}",
    year = "2013",
    doi = "10.1117/12.2002803",
    language = "English",
    isbn = "9780819494450",
    volume = "8671",
    booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

    }

    TY - GEN

    T1 - Automatic real-time tracking of fetal mouth in fetoscopic video sequence for supporting fetal surgeries

    AU - Xu, Rong

    AU - Xie, Tianliang

    AU - Ohya, Jun

    AU - Zhang, Bo

    AU - Sato, Yoshinobu

    AU - Fujie, Masakatsu G.

    PY - 2013

    Y1 - 2013

    N2 - Recently, a minimally invasive surgery (MIS) called fetoscopic tracheal occlusion (FETO) was developed to treat severe congenital diaphragmatic hernia (CDH) via fetoscopy, by which a detachable balloon is placed into the fetal trachea for preventing pulmonary hypoplasia through increasing the pressure of the chest cavity. This surgery is so dangerous that a supporting system for navigating surgeries is deemed necessary. In this paper, to guide a surgical tool to be inserted into the fetal trachea, an automatic approach is proposed to detect and track the fetal face and mouth via fetoscopic video sequencing. More specifically, the AdaBoost algorithm is utilized as a classifier to detect the fetal face based on Haar-like features, which calculate the difference between the sums of the pixel intensities in each adjacent region at a specific location in a detection window. Then, the CamShift algorithm based on an iterative search in a color histogram is applied to track the fetal face, and the fetal mouth is fitted by an ellipse detected via an improved iterative randomized Hough transform approach. The experimental results demonstrate that the proposed automatic approach can accurately detect and track the fetal face and mouth in real-time in a fetoscopic video sequence, as well as provide an effective and timely feedback to the robot control system of the surgical tool for FETO surgeries.

    AB - Recently, a minimally invasive surgery (MIS) called fetoscopic tracheal occlusion (FETO) was developed to treat severe congenital diaphragmatic hernia (CDH) via fetoscopy, by which a detachable balloon is placed into the fetal trachea for preventing pulmonary hypoplasia through increasing the pressure of the chest cavity. This surgery is so dangerous that a supporting system for navigating surgeries is deemed necessary. In this paper, to guide a surgical tool to be inserted into the fetal trachea, an automatic approach is proposed to detect and track the fetal face and mouth via fetoscopic video sequencing. More specifically, the AdaBoost algorithm is utilized as a classifier to detect the fetal face based on Haar-like features, which calculate the difference between the sums of the pixel intensities in each adjacent region at a specific location in a detection window. Then, the CamShift algorithm based on an iterative search in a color histogram is applied to track the fetal face, and the fetal mouth is fitted by an ellipse detected via an improved iterative randomized Hough transform approach. The experimental results demonstrate that the proposed automatic approach can accurately detect and track the fetal face and mouth in real-time in a fetoscopic video sequence, as well as provide an effective and timely feedback to the robot control system of the surgical tool for FETO surgeries.

    KW - AdaBoost classifier

    KW - CamShift algorithm

    KW - Fetal face tracking

    KW - Fetal mouth detection

    KW - Fetoscopic video sequence

    KW - Haar-like features

    KW - Iterative randomized hough transform (IRHT)

    UR - http://www.scopus.com/inward/record.url?scp=84878540533&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84878540533&partnerID=8YFLogxK

    U2 - 10.1117/12.2002803

    DO - 10.1117/12.2002803

    M3 - Conference contribution

    AN - SCOPUS:84878540533

    SN - 9780819494450

    VL - 8671

    BT - Proceedings of SPIE - The International Society for Optical Engineering

    ER -