Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers

Yan Li, Rong Xu, Jun Ohya, Hiroyasu Iwata

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

    2 Citations (Scopus)

    Abstract

    This paper explores the effectiveness of applying a deep learning based method to segment the amniotic fluid and fetal tissues in fetal ultrasound (US) images. The deeply learned model firstly encodes the input image into down scaled feature maps by convolution and pooling structures, then up-scale the feature maps to confidence maps by corresponded un-pooling and convolution layers. Additional convolution layers with 1×1 sized kernels are adopted to enhance the feature representations, which could be used to further improve the discriminative learning of our model. We effectively update the weights of the network by fine-tuning on part of the layers from a pre-trained model. By conducting experiments using clinical data, the feasibility of our proposed approach is compared and discussed. The result proves that this work achieves satisfied results for segmentation of specific anatomical structures from US images.

    Original languageEnglish
    Title of host publication2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    Subtitle of host publicationSmarter Technology for a Healthier World, EMBC 2017 - Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1485-1488
    Number of pages4
    ISBN (Electronic)9781509028092
    DOIs
    Publication statusPublished - 2017 Sep 13
    Event39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 - Jeju Island, Korea, Republic of
    Duration: 2017 Jul 112017 Jul 15

    Other

    Other39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
    CountryKorea, Republic of
    CityJeju Island
    Period17/7/1117/7/15

    Fingerprint

    Body Fluids
    Amniotic Fluid
    Convolution
    Ultrasonics
    Learning
    Fluids
    Fetus
    Weights and Measures
    Tuning
    Tissue
    Experiments

    ASJC Scopus subject areas

    • Signal Processing
    • Biomedical Engineering
    • Computer Vision and Pattern Recognition
    • Health Informatics

    Cite this

    Li, Y., Xu, R., Ohya, J., & Iwata, H. (2017). Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings (pp. 1485-1488). [8037116] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2017.8037116

    Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. / Li, Yan; Xu, Rong; Ohya, Jun; Iwata, Hiroyasu.

    2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1485-1488 8037116.

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

    Li, Y, Xu, R, Ohya, J & Iwata, H 2017, Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings., 8037116, Institute of Electrical and Electronics Engineers Inc., pp. 1485-1488, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017, Jeju Island, Korea, Republic of, 17/7/11. https://doi.org/10.1109/EMBC.2017.8037116
    Li Y, Xu R, Ohya J, Iwata H. Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1485-1488. 8037116 https://doi.org/10.1109/EMBC.2017.8037116
    Li, Yan ; Xu, Rong ; Ohya, Jun ; Iwata, Hiroyasu. / Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1485-1488
    @inproceedings{89ba903d44d7443fa21405282cf936a8,
    title = "Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers",
    abstract = "This paper explores the effectiveness of applying a deep learning based method to segment the amniotic fluid and fetal tissues in fetal ultrasound (US) images. The deeply learned model firstly encodes the input image into down scaled feature maps by convolution and pooling structures, then up-scale the feature maps to confidence maps by corresponded un-pooling and convolution layers. Additional convolution layers with 1×1 sized kernels are adopted to enhance the feature representations, which could be used to further improve the discriminative learning of our model. We effectively update the weights of the network by fine-tuning on part of the layers from a pre-trained model. By conducting experiments using clinical data, the feasibility of our proposed approach is compared and discussed. The result proves that this work achieves satisfied results for segmentation of specific anatomical structures from US images.",
    author = "Yan Li and Rong Xu and Jun Ohya and Hiroyasu Iwata",
    year = "2017",
    month = "9",
    day = "13",
    doi = "10.1109/EMBC.2017.8037116",
    language = "English",
    pages = "1485--1488",
    booktitle = "2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers

    AU - Li, Yan

    AU - Xu, Rong

    AU - Ohya, Jun

    AU - Iwata, Hiroyasu

    PY - 2017/9/13

    Y1 - 2017/9/13

    N2 - This paper explores the effectiveness of applying a deep learning based method to segment the amniotic fluid and fetal tissues in fetal ultrasound (US) images. The deeply learned model firstly encodes the input image into down scaled feature maps by convolution and pooling structures, then up-scale the feature maps to confidence maps by corresponded un-pooling and convolution layers. Additional convolution layers with 1×1 sized kernels are adopted to enhance the feature representations, which could be used to further improve the discriminative learning of our model. We effectively update the weights of the network by fine-tuning on part of the layers from a pre-trained model. By conducting experiments using clinical data, the feasibility of our proposed approach is compared and discussed. The result proves that this work achieves satisfied results for segmentation of specific anatomical structures from US images.

    AB - This paper explores the effectiveness of applying a deep learning based method to segment the amniotic fluid and fetal tissues in fetal ultrasound (US) images. The deeply learned model firstly encodes the input image into down scaled feature maps by convolution and pooling structures, then up-scale the feature maps to confidence maps by corresponded un-pooling and convolution layers. Additional convolution layers with 1×1 sized kernels are adopted to enhance the feature representations, which could be used to further improve the discriminative learning of our model. We effectively update the weights of the network by fine-tuning on part of the layers from a pre-trained model. By conducting experiments using clinical data, the feasibility of our proposed approach is compared and discussed. The result proves that this work achieves satisfied results for segmentation of specific anatomical structures from US images.

    UR - http://www.scopus.com/inward/record.url?scp=85032174265&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85032174265&partnerID=8YFLogxK

    U2 - 10.1109/EMBC.2017.8037116

    DO - 10.1109/EMBC.2017.8037116

    M3 - Conference contribution

    C2 - 29060160

    AN - SCOPUS:85032174265

    SP - 1485

    EP - 1488

    BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -