Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net

被引:20
|
作者
Wang, Chuanbo [1 ]
Guo, Ye [1 ]
Chen, Wei [2 ]
Yu, Zeyun [1 ]
机构
[1] Univ Wisconsin, Dept Comp Sci, Milwaukee, WI 53201 USA
[2] Army Med Univ, Southwestern Hosp, Dept Radiol, Chongqing, Peoples R China
关键词
deep learning; machine learning; convolutional neural network; intervertebral discs; biomedical imaging; image segmentation; LOCALIZATION;
D O I
10.1109/COMPSAC.2019.00109
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Intervertebral discs (IVDs), as small joints lying between adjacent vertebrae, have played an important role in pressure buffering and tissue protection. The fully-automatic localization and segmentation of IVDs have been discussed in the literature for many years since they are crucial to spine disease diagnosis and provide quantitative parameters in the treatment. Traditionally hand-crafted features are derived based on image intensities and shape priors to localize and segment IVDs. With the advance of deep learning, various neural network models have gained great success in image analysis including the recognition of intervertebral discs. Particularly, U-Net stands out among other approaches due to its outstanding performance on biomedical images with a relatively small set of training data. This paper proposes a novel convolutional framework based on 3D U-Net to segment IVDs from multi-modality MRI images. We first localize the centers of intervertebral discs in each spine sample and then train the network based on the cropped small volumes centered at the localized intervertebral discs. A detailed comprehensive analysis of the results using various combinations of multi-modalities is presented. Furthermore, experiments conducted on 2D and 3D U-Nets with augmented and non-augmented datasets are demonstrated and compared in terms of Dice coefficient and Hausdorff distance. Our method has proved to be effective with a mean segmentation Dice coefficient of 89.0% and a standard deviation of 1.4%.
引用
收藏
页码:730 / 739
页数:10
相关论文
共 50 条
  • [1] Fully automatic intervertebral disc segmentation using multimodal 3D U-net
    Wang, Chuanbo
    Guo, Ye
    Chen, Wei
    Yu, Zeyun
    arXiv, 2020,
  • [2] Automatic segmentation and quantification of the optic nerve on MRI using a 3D U-Net
    van Elst, Sabien
    de Bloeme, Christiaan M. M.
    Noteboom, Samantha
    de Jong, Marcus C. C.
    Moll, Annette C. C.
    Goericke, Sophia
    de Graaf, Pim
    Caan, Matthan W. A.
    JOURNAL OF MEDICAL IMAGING, 2023, 10 (03)
  • [3] Automatic segmentation of nonhuman primate brain structures using 3D U-net
    Li, C.
    Zugaro, A. Galli
    Carr, Z.
    Korszen, S.
    Smith, G.
    Stigall, J.
    Salegio, E. A.
    Zagorchev, L.
    HUMAN GENE THERAPY, 2024, 35 (3-4) : A192 - A193
  • [4] Automatic Liver Segmentation in CT Volumes with Improved 3D U-net
    Liu, Chunlei
    Cui, Deqi
    Shi, Dejun
    Hu, Zhiqiang
    Qin, Yuan
    Lang, Jinyi
    ISICDM 2018: PROCEEDINGS OF THE 2ND INTERNATIONAL SYMPOSIUM ON IMAGE COMPUTING AND DIGITAL MEDICINE, 2018, : 78 - 82
  • [5] A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
    Baid, Ujjwal
    Talbar, Sanjay
    Rane, Swapnil
    Gupta, Sudeep
    Thakur, Meenakshi H.
    Moiyadi, Aliasgar
    Sable, Nilesh
    Akolkar, Mayuresh
    Mahajan, Abhishek
    FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2020, 14
  • [6] Automatic multilabel aorta segmentation in PET/CT using a modified 3D U-Net
    Van Praagh, G.
    Nienhuis, P. H.
    Reijrink, M.
    Davidse, M. E. J.
    Spottiswoode, B. S.
    Gao, F.
    Prakken, N. H. J.
    Wolterink, J. M.
    Mouridsen, K.
    Sinha, B.
    Borra, R. J. H.
    Slart, R. H. J.
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2022, 49 (SUPPL 1) : S285 - S285
  • [7] 3D Automatic Brain Tumor Segmentation Using a Multiscale Input U-Net Network
    Gonzalez, S. Rosas
    Sekou, T. Birgui
    Hidane, M.
    Tauber, C.
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2019), PT II, 2020, 11993 : 113 - 123
  • [8] Automatic Internal Auditory Canal Segmentation Using a Weakly Supervised 3D U-Net
    Mason, Hannah G.
    Noble, Jack H.
    MEDICAL IMAGING 2022: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, 2022, 12034
  • [9] Automatic segmentation of brain tumor in intraoperative ultrasound images using 3D U-Net
    Carton, Francois-Xavier
    Chabanas, Matthieu
    Munkvold, Bodil K. R.
    Reinertsen, Ingerid
    Noble, Jack H.
    MEDICAL IMAGING 2020: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, 2021, 11315
  • [10] MULTIMODAL SEGMENTATION BASED ON A NOVEL 3D U-NET DEEP LEARNING ARCHITECTURE
    Swaroopa, K. M.
    Chetty, Girija
    2021 IEEE ASIA-PACIFIC CONFERENCE ON COMPUTER SCIENCE AND DATA ENGINEERING (CSDE), 2021,