In this paper, a novel method of high-grade brain tumor segmentation from multi-sequence magnetic resonance images is presented. Firstly, a Gaussian mixture model (GMM) is introduced to derive an initial posterior probability by fitting the fluid attenuation inversion recovery histogram. Secondly, some grayscale and region properties are extracted from different sequences. Thirdly, grayscale and region characteristics with different weights are proposed to adjust the posterior probability. Finally, a cost function based on the posterior probability and neighborhood information is formulated and optimized via graph cut. Experiment results on a public dataset with 20 high-grade brain tumor patient images show the proposed method could achieve a dice coefficient of 78%, which is higher than the standard graph cut algorithm without a probability-adjusting step or some other cost function-based methods.
Ye AI
Tsinghua University
Feng MIAO
Tsinghua University
Qingmao HU
Chinese Academy of Sciences
Weifeng LI
Tsinghua University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Ye AI, Feng MIAO, Qingmao HU, Weifeng LI, "Multi-Feature Guided Brain Tumor Segmentation Based on Magnetic Resonance Images" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 12, pp. 2250-2256, December 2015, doi: 10.1587/transinf.2015EDP7083.
Abstract: In this paper, a novel method of high-grade brain tumor segmentation from multi-sequence magnetic resonance images is presented. Firstly, a Gaussian mixture model (GMM) is introduced to derive an initial posterior probability by fitting the fluid attenuation inversion recovery histogram. Secondly, some grayscale and region properties are extracted from different sequences. Thirdly, grayscale and region characteristics with different weights are proposed to adjust the posterior probability. Finally, a cost function based on the posterior probability and neighborhood information is formulated and optimized via graph cut. Experiment results on a public dataset with 20 high-grade brain tumor patient images show the proposed method could achieve a dice coefficient of 78%, which is higher than the standard graph cut algorithm without a probability-adjusting step or some other cost function-based methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7083/_p
Copy
@ARTICLE{e98-d_12_2250,
author={Ye AI, Feng MIAO, Qingmao HU, Weifeng LI, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Feature Guided Brain Tumor Segmentation Based on Magnetic Resonance Images},
year={2015},
volume={E98-D},
number={12},
pages={2250-2256},
abstract={In this paper, a novel method of high-grade brain tumor segmentation from multi-sequence magnetic resonance images is presented. Firstly, a Gaussian mixture model (GMM) is introduced to derive an initial posterior probability by fitting the fluid attenuation inversion recovery histogram. Secondly, some grayscale and region properties are extracted from different sequences. Thirdly, grayscale and region characteristics with different weights are proposed to adjust the posterior probability. Finally, a cost function based on the posterior probability and neighborhood information is formulated and optimized via graph cut. Experiment results on a public dataset with 20 high-grade brain tumor patient images show the proposed method could achieve a dice coefficient of 78%, which is higher than the standard graph cut algorithm without a probability-adjusting step or some other cost function-based methods.},
keywords={},
doi={10.1587/transinf.2015EDP7083},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Multi-Feature Guided Brain Tumor Segmentation Based on Magnetic Resonance Images
T2 - IEICE TRANSACTIONS on Information
SP - 2250
EP - 2256
AU - Ye AI
AU - Feng MIAO
AU - Qingmao HU
AU - Weifeng LI
PY - 2015
DO - 10.1587/transinf.2015EDP7083
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2015
AB - In this paper, a novel method of high-grade brain tumor segmentation from multi-sequence magnetic resonance images is presented. Firstly, a Gaussian mixture model (GMM) is introduced to derive an initial posterior probability by fitting the fluid attenuation inversion recovery histogram. Secondly, some grayscale and region properties are extracted from different sequences. Thirdly, grayscale and region characteristics with different weights are proposed to adjust the posterior probability. Finally, a cost function based on the posterior probability and neighborhood information is formulated and optimized via graph cut. Experiment results on a public dataset with 20 high-grade brain tumor patient images show the proposed method could achieve a dice coefficient of 78%, which is higher than the standard graph cut algorithm without a probability-adjusting step or some other cost function-based methods.
ER -