Professional Documents
Culture Documents
fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier 10.1109/ACCESS.2018.Doi Number
ABSTRACT Various brain tumors are very harmful to human health, and their incidence rate has risen
gradually in recent years. Magnetic resonance imaging (MRI) is widely used in the evaluation and
treatment of brain tumors, but a radiologist’s manual segmentation of massive images is time-consuming
and produces some personal bias, and so a computer-aided diagnostic system could improve the working
efficiency of radiologists. In recent years, a variety of automatic segmentation methods for brain tumor
images has been proposed. Compared with other methods, machine-learning-based methods are able to
obtain better segmentation accuracy, but such methods require the manual labeling of lots of samples to
ensure the accuracy of the segmentation. In this study, semi-supervised learning theory and image spatial
and clinical a priori knowledge of brain tumors are combined to propose a new brain-tumor segmentation
method that can improve the segmentation accuracy with multiple classifier collaborative training
(CoTraining) under the premise of fewer labeled data. In addition, according to the prior knowledge that
image adjacent pixels belong to similar classes and clinical knowledge, we used superpixel graphs to
construct a spatial and clinical constraint to improve brain-tumor segmentation accuracy further. The
proposed method was tested on the Brain Tumor Segmentation Challenge 2012 and 2013 datasets (BRATS
2012, 2013). The experimental results demonstrate that the proposed method was able to overcome the
drawbacks of fewer training samples effectively and obtained remarkable brain-tumor segmentation
performance.
diseases. According to the degree of malignancy of a glioma, method is very simple and easy to use for unlabeled data and
it can be divided into low-grade or high-grade [3]. does not require additional prior knowledge for the model
Multi-sequence magnetic resonance imaging (MRI) is assumptions. It is a very effective semi-supervised learning
often used in the evaluation of gliomas to assist in clinical approach in practical applications.
diagnosis, qualitative analysis, and treatment. The commonly Aimed at the clinical application of glioma segmentation,
used image sequences include T1-weighted, T2-weighted, we propose a new glioma segmentation method using the
fluid-attenuated inversion recovery (FLAIR), and post- multiple classifier collaborative training (CoTraining)
contrast T1-weighted images [4]. The appearance of a glioma algorithm based on the difference between SVM and SRC
in the various sequence image methods are different. In the classifiers, and superpixel-based spatial and clinical
T1-weighted sequence images, the regions of brain tissue constraints. The method includes the following key steps.
cannot be clearly segmented because the image intensities of First, labeled brain MRI data are used to train the SVM and
the tumor region are similar to those of the gray matter. In SRC classifiers for selecting high confidence data from the
the post-contrast T1-weighted images, the active and necrotic testing samples as pseudo-labeled samples. Second, the
regions of a tumor can be clearly distinguished for that the pseudo-labeled samples obtained from each of the classifiers
active tumor shows bright while the necrotic tissue are added to the other side of the training set to retrain the
demonstrates dark. Meanwhile, compared to images of brain corresponding classifier; this process is executed iteratively
tissues, the intensities of edema and tumor regions are much until a stable result is obtained. Finally, a superpixel graph is
higher in the T2-weighted sequence images and FLAIR constructed on the post-contrast T1-weighted image to build
images and the intensities of cerebrospinal fluid (CSF) is a spatial and clinical constraint. The glioma segmentation
higher in the T2-weighted images and lower in FLAIR model is then established according to the classification
images. probability and prior constraint, and the glioma segmentation
At present, there is an urgent necessity to extract brain results are obtained by optimizing the preceding model. This
glioma images automatically for clinical diagnosis to provide method has two advantages. First, the classification accuracy
accurate tumor information for subsequent treatment is improved by the iterative method for the two-classifier
planning and assessment. In recent years, many glioma collaborative training when the number of labeled samples is
segmentation methods using multi-sequence MRI have been insufficient, and second, the construction of the spatial and
proposed, and among them, methods based on machine- clinical constraint using a superpixel graph can overcome the
learning classification using the already marked samples to interference caused by noise and false positive regions, and
train a classification model and then utilizing the trained thus further improve the segmentation accuracy. The
model to classify the test samples have been widely proposed method was tested on Brain Tumor Segmentation
employed [5-12]. The commonly used machine-learning Challenge 2012 and 2013 datasets (BRATS 2012, BRATS
methods include support vector machines (SVMs)[13], sparse 2013) and the experimental results demonstrate that this
representation classification (SRC)[14], multinomial logistic method was able to effectively overcome the drawbacks of
regression[15], and so on. With the explosive development of insufficient training samples and unstable spatial distribution,
deep learning methods, convolutional neural networks and obtained competitive glioma segmentation accuracy.
(CNNs)[16,17], deep belief networks (DBNs)[18], and other
neural networks have also been applied in brain-tumor II. THE PROPOSED METHOD
segmentation. However, these neural network methods The overall process of the proposed glioma segmentation
require a large amount of marked data to train a good method using CoTraining and superpixel-based spatial
classification model, and the classification performance and clinical constraints is shown in Figure 1.
cannot be guaranteed when the number of training samples is
limited. However, manually labeling enough data is time-
consuming. In a clinical setting, it is necessary to use a
smaller number of labeled data to train a good classification
model and thus obtain preferable tumor segmentation results.
In clinical applications, unlabeled data is relatively easy to
obtain, and so the semi-supervised learning method[19-21] has
become a hot topic in the research field of machine learning
in recent years. This method can use a small number of
labeled data and a large number of unlabeled data to train a
good classifier for perfectly solving the problem of fewer
labeled data in practical applications. Among them, the FIGURE 1. A flowchart of the proposed method
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
will lead to differences in intensity for the same tissues. We where 'j are the slack variables on the pseudo-labeled data
used the N4ITK method[22] to carry out nonhomogeneous
and 1 is a weight parameter. The minimization of this
image correction and to adjust the intensity values of each
MR image sequence into [0 255]. After this, we intercepted model can be transferred to solve the dual problem, the
details of which are available in reference [21].
the image block of each pixel in different sequence images
and transformed it into a vector. The values of vector are the 2) THE WEIGHTED SRC METHOD
intensities of the pixel and its neighborhood in different After setting D as the labeled dataset and y as the
sequences. For each pixel on one slice of an image, its block unlabeled sample, the SRC classifier can obtain the sparse
size is . For k sequence images, the initial feature size representation coefficient of y on D by
of one pixel is k and its corresponding vector size min 1 D y
2
. (3)
2 2
is k 1 . We set k =4 in this study and used these
*
intensity vectors as the input for the CoTraining method. After optimal coefficient is obtained, the corresponding
class of y can be determined by the representation residuals
B. THE COTRAINING METHOD on each class as
We used the SVM classifier and SRC classifier as the base
y* = arg min ek ( y ) , ek ( y ) y Dk k* .(4)
classifiers for CoTraining. Those samples with high 2
confidence are selected as pseudo-labeled samples to classify Where Dk represents the data subset of the k -th class and
the unlabeled data. The pseudo-labeled samples obtained by
k* is the optimal representation coefficient on Dk .
one classifier are added to the training set for retraining with
the other classifier; this cross process is executed iteratively After the introduction of the pseudo-labeled data, objective
until a stable result has been obtained. We also assign function (2) can be rewritten as
min( 1 D y 2 +2 ( ' 1 D ' ' y 2 )) , (5)
2 2
weights for the pseudo-labeled data to modify the target , '
functions of the SVM and SRC classifiers and thus propose a where D ' is the pseudo-labeled dataset and ' is the
weighted SVM and SRC classification model. coefficient of y on D ' . The details of the optimization of (5)
can be found in reference [16].
After calculating the optimal coefficients * and '* , the
appropriate class of y can be determined by
y * = arg min f k ( y ) ,
f k ( y ) y Dk k* +2 y D 'k '*k . (6)
2 2
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
(a) (b)
FIGURE 6. The average accuracy of tumor and edema segmentation
results for the simulation datasets with increasing iterations
(b)
FIGURE 7.The average accuracies for SVM and SRC executed on the
clinical dataset with different parameter values
(a)
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
(a) FIGURE 9. The average accuracies of SVM and SRC executed on the
clinical dataset with different numbers of training samples
FIGURE 10. The average accuracies of SVM and SRC executed on the
(b) simulation dataset with different numbers of training samples
FIGURE 8. The average accuracies for SVM and SRC executed on the
simulation dataset with different parameter values E. THE SPATIAL AND CLINICAL CONSTRAINTS’
SEGMENTATION RESULTS
D. THE NUMBER OF INITIAL TRAINING SAMPLES Figure 11 and Figure 12 demonstrate the segmentation
The number of initial training samples determines the results of the two datasets using CoTraining, CoTraining
classification effect of CoTraining. The CoTraining method with the spatial constraint, and CoTraining with the spatial
does not play a significant role in improving the and clinical constraints. From the results, the noise effect
classification accuracy when the number of initial training was overcome very well and the result was much smoother
samples is very large but may lead to a further reduction in after adding the spatial knowledge during the segmentation
classification accuracy even though the effect is not as good process. The false positive region was eliminated
as the result of a single classifier when the number of initial effectively and the segmentation accuracy was further
samples is small. Figures 9 and 10 show the classification improved when the clinical constraint was considered
accuracy for the clinical and simulation datasets, during the segmentation.
respectively, using different brain tumor initial training
samples. Edema and brain tissues were set according to the
ratio of 3:1 to 1:3 in the experiment. As can be seen from
the images, the classification accuracy was very low when
the number of initial training samples was within 10 and
basically met the clinical requirement when the initial
sample number was between 20 and 40. In our experiment,
the number of initial brain-tumor training samples was set
at 30.
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
FIGURE 13. The full segmentation results on BraTS 2013 datasets. The
rows in order: the post-contrast T1-weighted image, CoTraining with the
spatial and clinical constraints and the ground truth.
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
results. However, the segmentation results obtained by the [4] Kircher M F, Mahmood U, King R S, et al. A multimodal
proposed method are at the forefront and are competitive. nanoparticle for preoperative magnetic resonance imaging and
TABLE II intraoperative optical brain tumor delineation[J]. Cancer Research,
RESULTS IN THE CHALLENGE DATASET OF BRATS 2013. 2003, 63(23):8122-8125.
[5] Qian J, Yang J, Gao G. Discriminative histograms of local dominant
DSC PPV Sensitivity
Dataset orientation (D-HLDO) for biometric image feature extraction.
Core Enh. Core Enh. Core Enh. Pattern Recognition, 2013, 46(10): 2724-2739.
Kwon et al. [32] 0.83 0.72 0.90 0.74 0.78 0.72 [6] Zhang Y, Peng B, Wang S, et al. Image processing methods to
Tustison et al. [33] 0.78 0.74 0.74 0.69 0.88 0.83 elucidate spatial characteristics of retinal microglia after optic nerve
CNNs [16] 0.83 0.77 0.87 0.74 0.83 0.81 transection. Scientific reports, 2016, 6:21816.
Urban et al. [34] 0.75 0.73 0.75 0.79 0.79 0.80
[7] Hong R, Tang L, Hu J, et al. Advertising object in web videos.
Havaei et al. [35] 0.79 0.73 0.79 0.68 0.79 0.80
Davy et al. [36] 0.74 0.68 0.74 0.62 0.78 0.77 Neurocomputing, 119: 118-124,2013.
The proposed [8] Wu Z, Wang Q, Plaza A, et al. Parallel Spatial–Spectral
0.81 0.74 0.87 0.74 0.84 0.83
method Hyperspectral Image Classification With Sparse Representation and
Markov Random Fields on GPUs[J]. IEEE Journal of Selected
IV. CONCLUSIONS Topics in Applied Earth Observations & Remote Sensing, 2015,
A CoTraining method with spatial and clinical 8(6):2926-2938.
constraints is proposed in this paper aimed at the problem [9] Hong R, Cao W, Pang J, et al. Directional projection based image
of automatic glioma image extraction from multi-sequence fusion quality metric. Information Sciences, 2014, 281: 611-619.
MR images. First, two base classifiers SVM and SRC are [10] Xu Y, Wu Z, Wei Z. Spectral–Spatial Classification of Hyperspectral
trained with a small number of labeled samples, then high Image Based on Low-Rank Decomposition[J]. IEEE Journal of
confidence samples are selected as pseudo-labeled samples Selected Topics in Applied Earth Observations & Remote Sensing,
according to the classification results for the two base 2015, 8(6):2370-2380.
classifiers. Next, the pseudo-labeled samples obtained from [11] Sun L, Wu Z, Liu J, et al. Supervised Spectral–Spatial Hyperspectral
each classifier are added to each other's training sets, and Image Classification With Weighted Markov Random Fields[J].
this process is repeated iteratively until the classification IEEE Transactions on Geoscience & Remote Sensing, 2015,
results are stable. Finally, we use a T1- enhanced sequence 53(3):1490-1503.
image to construct a superpixel graph and design spatial [12] Wu Z, Wang Q, Plaza A, et al. Real-Time Implementation of the
and clinical constraints. A segmentation model based on Sparse Multinomial Logistic Regression for Hyperspectral Image
classification probability and spatial and clinical constraints Classification on GPUs[J]. IEEE Geoscience & Remote Sensing
is then minimized to obtain the final glioma segmentation Letters, 2015, 12(7):1456-1460.
results. [13] Ramakrishnan T, Sankaragomathi B. A professional estimate on the
By using the two base classifiers to carry out cross- computed tomography brain tumor images using SVM-SMO for
training iteratively, the proposed method was able to classification and MRG-GWO for segmentation[J]. Pattern
improve the classification accuracy when the labeled Recognition Letters, 2017, 94.
samples were insufficient. In addition, by constructing [14] Li Y, Jia F, Qin J. Brain tumor segmentation from multimodal
image space and clinical a priori knowledge constraints, the magnetic resonance images via sparse representation[J]. Artificial
interference of noise and false positive regions was Intelligence in Medicine, 2016, 73:1.
removed and the segmentation precision was further [15] Ting G E, Ning M U, Li L I. A Brain Tumor Segmentation Method
improved. The proposed method was performed on the Based on Softmax Regression and Graph Cut[J]. Acta Electronica
BRATS2012 and BRATS2013 datasets, and the average Sinica, 2017, 45(3):644-649.
segmentation accuracy demonstrated that the proposed [16] Pereira S, Pinto A, Alves V, et al. Brain Tumor Segmentation using
method was able to obtain good performance for glioma Convolutional Neural Networks in MRI Images.[J]. IEEE
segmentation. Transactions on Medical Imaging, 2016, 35(5):1240-1251.
REFERENCES [17] Iqbal S, Ghani M U, Saba T, et al. Brain tumor segmentation in
[1] Khwairakpam A D, Monisha J, Banik K, et al. Chemoresistance in multi-spectral MRI using convolutional neural networks (CNN)[J].
Brain Cancer and Different Chemosensitization Approaches[M]// Microsc Res Tech, 2018(10).
Cancer Cell Chemoresistance and Chemosensitization. 2018. [18] Zhan T, Chen Y, Hong X, et al. Brain Tumor Segmentation Using
[2] Vierhout M, Daniels M, Mazzotta P, et al. The views of patients Deep Belief Networks and Pathological Knowledge[J]. CNS &
with brain cancer about palliative care: a qualitative study[J]. Neurological Disorders Drug Targets, 2017, 16(2):129-136.
Current Oncology, 2017, 24(6):374. [19] Saha S, Alok A K, Ekbal A. Brain image segmentation using semi-
[3] Baene W D, Rutten G, Sitskoorn M M. P04.09 Low-grade and high- supervised clustering[J]. Expert Systems with Applications, 2016,
grade glioma patients show different remote effects of the brain 52(C):50-63.
tumor on the functional network topology of the contralesional [20] Yang L, Zhang Y, Chen J, et al. Suggestive Annotation: A Deep
hemisphere[J]. Neuro-Oncology, 2017, 19(suppl_3):iii41-iii42. Active Learning Framework for Biomedical Image Segmentation[J].
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2018.2873674, IEEE Access
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.