Journal article
3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images.
- Li X Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Dou Q Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Chen H Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China. Electronic address: hchen@cse.cuhk.edu.hk.
- Fu CW Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Qi X Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Belavý DL Institute of Physical Activity and Nutrition Research, Deakin University, Burwood, Victoria, Australia; Charité University Medical School, Berlin, Germany.
- Armbrecht G Charité University Medical School, Berlin, Germany.
- Felsenberg D Charité University Medical School, Berlin, Germany.
- Zheng G Institute for Surgical Technology and Biomechanics, University of Bern, Switzerland. Electronic address: guoyan.zheng@istb.unibe.ch.
- Heng PA Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- 2018-02-08
Published in:
- Medical image analysis. - 2018
Deep learning
Dropout
Intervertebral discs
Localization
Magnetic resonance imaging
Multi-modality
Segmentation
Algorithms
Deep Learning
Humans
Image Enhancement
Image Interpretation, Computer-Assisted
Imaging, Three-Dimensional
Intervertebral Disc
Magnetic Resonance Imaging
English
Intervertebral discs (IVDs) are small joints that lie between adjacent vertebrae. The localization and segmentation of IVDs are important for spine disease diagnosis and measurement quantification. However, manual annotation is time-consuming and error-prone with limited reproducibility, particularly for volumetric data. In this work, our goal is to develop an automatic and accurate method based on fully convolutional networks (FCN) for the localization and segmentation of IVDs from multi-modality 3D MR data. Compared with single modality data, multi-modality MR images provide complementary contextual information, which contributes to better recognition performance. However, how to effectively integrate such multi-modality information to generate accurate segmentation results remains to be further explored. In this paper, we present a novel multi-scale and modality dropout learning framework to locate and segment IVDs from four-modality MR images. First, we design a 3D multi-scale context fully convolutional network, which processes the input data in multiple scales of context and then merges the high-level features to enhance the representation capability of the network for handling the scale variation of anatomical structures. Second, to harness the complementary information from different modalities, we present a random modality voxel dropout strategy which alleviates the co-adaption issue and increases the discriminative capability of the network. Our method achieved the 1st place in the MICCAI challenge on automatic localization and segmentation of IVDs from multi-modality MR images, with a mean segmentation Dice coefficient of 91.2% and a mean localization error of 0.62 mm. We further conduct extensive experiments on the extended dataset to validate our method. We demonstrate that the proposed modality dropout strategy with multi-modality images as contextual information improved the segmentation accuracy significantly. Furthermore, experiments conducted on extended data collected from two different time points demonstrate the efficacy of our method on tracking the morphological changes in a longitudinal study.
- Language
-
- English
- Open access status
- closed
- Identifiers
-
- DOI 10.1016/j.media.2018.01.004
- PMID 29414435
- Persistent URL
- https://sonar.ch/global/documents/185101
Statistics
Document views: 66
File downloads: