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
来源
2019 IEEE 43RD ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 1 | 2019年
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
  • [21] SEGMENTATION OF SPINAL SUBARACHNOID LUMEN WITH 3D ATTENTION U-NET
    Keles, Ayse
    Algin, Oktay
    Ozisik, Pinar Akdemir
    Sen, Baha
    Celebi, Fatih Vehbi
    JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY, 2023, 23 (04)
  • [22] A Bispectral 3D U-Net for Rotation Robustness in Medical Segmentation
    Chevalley, Arthur
    Oreiller, Valentin
    Fageot, Julien
    Prior, John O.
    Andrearczyk, Vincent
    Depeursinge, Adrien
    TOPOLOGY-AND GRAPH-INFORMED IMAGING INFORMATICS, TGI3 2024, 2025, 15239 : 43 - 54
  • [23] Residual 3D U-Net with Localization for Brain Tumor Segmentation
    Demoustier, Marc
    Khemir, Ines
    Nguyen, Quoc Duong
    Martin-Gaffe, Lucien
    Boutry, Nicolas
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2021, PT I, 2022, 12962 : 389 - 399
  • [24] Automatic Liver Segmentation with CT Images based on 3D U-net Deep Learning Approach
    Su, Ting-Yu
    Yang, Wei-Tse
    Cheng, Tsu-Chi
    He, Yi-Fei
    Fang, Yu-Hua
    INTERNATIONAL FORUM ON MEDICAL IMAGING IN ASIA 2019, 2019, 11050
  • [25] Deep Convolutional Neural Networks Using U-Net for Automatic Brain Tumor Segmentation in Multimodal MRI Volumes
    Kermi, Adel
    Mahmoudi, Issam
    Khadir, Mohamed Tarek
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2018, PT II, 2019, 11384 : 37 - 48
  • [26] Feature Learning by Attention and Ensemble with 3D U-Net to Glioma Tumor Segmentation
    Cai, Xiaohong
    Lou, Shubin
    Shuai, Mingrui
    An, Zhulin
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2021, PT II, 2022, 12963 : 68 - 79
  • [27] Fully Automated Segmentation of Brain Tumor from Multiparametric MRI Using 3D Context U-Net with Deep Supervision
    Lin, Mingquan
    Momin, Shadab
    Zhou, Boran
    Tang, Katherine
    Lei, Yang
    Curran, Walter J.
    Liu, Tian
    Yang, Xiaofeng
    MEDICAL IMAGING 2021: COMPUTER-AIDED DIAGNOSIS, 2021, 11597
  • [28] Fully automated segmentation of brain tumor from multiparametric MRI using 3D context deep supervised U-Net
    Lin, Mingquan
    Momin, Shadab
    Lei, Yang
    Wang, Hesheng
    Curran, Walter J.
    Liu, Tian
    Yang, Xiaofeng
    MEDICAL PHYSICS, 2021, 48 (08) : 4365 - 4374
  • [29] Comparison of tissue segmentation performance between 2D U-Net and 3D U-Net on brain MR Images
    Woo, Boyeong
    Lee, Myungeun
    2021 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC), 2021,
  • [30] A Multiscale Spatial Transformer U-Net for Simultaneously Automatic Reorientation and Segmentation of 3-D Nuclear Cardiac Images
    Ni, Yangfan
    Zhang, Duo
    Ma, Gege
    Rao, Fan
    Wu, Yuanfeng
    Lu, Lijun
    Huang, Zhongke
    Zhu, Wentao
    IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, 2024, 8 (06) : 632 - 645