Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation

Haocheng Shen, Jianguo Zhang, Weishi Zheng

Research output: Contribution to conferencePaper

3 Citations (Scopus)
60 Downloads (Pure)

Abstract

In this paper, we present a novel and efficient method for brain tumor (and sub regions) segmentation in multimodal MR images based on a fully convolutional network (FCN) that enables end-to-end training and fast inference. Our structure consists of a downsampling path and three upsampling paths, which extract multi-level contextual information by concatenating hierarchical feature representation from each upsampling path. Meanwhile, we introduce a symmetry-driven FCN by the proposal of using symmetry difference images. The model was evaluated on Brain Tumor Image Segmentation Benchmark (BRATS) 2013 challenge dataset and achieved the state-of-the-art results while the computational cost is less than competitors.
Original languageEnglish
Pages3864-3868
Number of pages5
DOIs
Publication statusPublished - 17 Sep 2017
EventThe International Conference on Image Processing 2017 - China National Convention Center, Beijing, China
Duration: 17 Sep 201720 Dec 2017

Conference

ConferenceThe International Conference on Image Processing 2017
Abbreviated titleIEEE ICIP 2017
CountryChina
CityBeijing
Period17/09/1720/12/17

Fingerprint

Tumors
Brain
Image segmentation
Costs

Keywords

  • FCN
  • brain tumor segmentati

Cite this

Shen, H., Zhang, J., & Zheng, W. (2017). Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation. 3864-3868. Paper presented at The International Conference on Image Processing 2017, Beijing, China. https://doi.org/10.1109/ICIP.2017.8297006
Shen, Haocheng ; Zhang, Jianguo ; Zheng, Weishi. / Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation. Paper presented at The International Conference on Image Processing 2017, Beijing, China.5 p.
@conference{dc4427f5192340a497ddab8ff2dfa3fc,
title = "Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation",
abstract = "In this paper, we present a novel and efficient method for brain tumor (and sub regions) segmentation in multimodal MR images based on a fully convolutional network (FCN) that enables end-to-end training and fast inference. Our structure consists of a downsampling path and three upsampling paths, which extract multi-level contextual information by concatenating hierarchical feature representation from each upsampling path. Meanwhile, we introduce a symmetry-driven FCN by the proposal of using symmetry difference images. The model was evaluated on Brain Tumor Image Segmentation Benchmark (BRATS) 2013 challenge dataset and achieved the state-of-the-art results while the computational cost is less than competitors.",
keywords = "FCN, brain tumor segmentati",
author = "Haocheng Shen and Jianguo Zhang and Weishi Zheng",
note = "This work was supported partially by the National Natural Science Foundation of China (No. 61628212); The International Conference on Image Processing 2017, IEEE ICIP 2017 ; Conference date: 17-09-2017 Through 20-12-2017",
year = "2017",
month = "9",
day = "17",
doi = "10.1109/ICIP.2017.8297006",
language = "English",
pages = "3864--3868",

}

Shen, H, Zhang, J & Zheng, W 2017, 'Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation' Paper presented at The International Conference on Image Processing 2017, Beijing, China, 17/09/17 - 20/12/17, pp. 3864-3868. https://doi.org/10.1109/ICIP.2017.8297006

Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation. / Shen, Haocheng; Zhang, Jianguo; Zheng, Weishi.

2017. 3864-3868 Paper presented at The International Conference on Image Processing 2017, Beijing, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation

AU - Shen, Haocheng

AU - Zhang, Jianguo

AU - Zheng, Weishi

N1 - This work was supported partially by the National Natural Science Foundation of China (No. 61628212)

PY - 2017/9/17

Y1 - 2017/9/17

N2 - In this paper, we present a novel and efficient method for brain tumor (and sub regions) segmentation in multimodal MR images based on a fully convolutional network (FCN) that enables end-to-end training and fast inference. Our structure consists of a downsampling path and three upsampling paths, which extract multi-level contextual information by concatenating hierarchical feature representation from each upsampling path. Meanwhile, we introduce a symmetry-driven FCN by the proposal of using symmetry difference images. The model was evaluated on Brain Tumor Image Segmentation Benchmark (BRATS) 2013 challenge dataset and achieved the state-of-the-art results while the computational cost is less than competitors.

AB - In this paper, we present a novel and efficient method for brain tumor (and sub regions) segmentation in multimodal MR images based on a fully convolutional network (FCN) that enables end-to-end training and fast inference. Our structure consists of a downsampling path and three upsampling paths, which extract multi-level contextual information by concatenating hierarchical feature representation from each upsampling path. Meanwhile, we introduce a symmetry-driven FCN by the proposal of using symmetry difference images. The model was evaluated on Brain Tumor Image Segmentation Benchmark (BRATS) 2013 challenge dataset and achieved the state-of-the-art results while the computational cost is less than competitors.

KW - FCN

KW - brain tumor segmentati

U2 - 10.1109/ICIP.2017.8297006

DO - 10.1109/ICIP.2017.8297006

M3 - Paper

SP - 3864

EP - 3868

ER -

Shen H, Zhang J, Zheng W. Efficient Symmetry-driven Fully Convolutional Network for Multimodal Brain Tumor Segmentation. 2017. Paper presented at The International Conference on Image Processing 2017, Beijing, China. https://doi.org/10.1109/ICIP.2017.8297006