An efficient brain tumor segmentation based on cellular automata and improved tumor-cut algorithm
Introduction
Magnetic resonance image (MRI) provides a good soft tissue imaging and valuable information in pathology of brain tumor without invasive from radioactivity. According to diverse characteristics of brain tumor, MRI could reveal a tumor information in various tissues. As shown in Fig. 1, contrast- enhanced T1-weighted (T1C) highlights the tumor core including active tumor and necrotic, whereas T2-weight visualizes the edema tissue in hyper-intense signal. In clinical practice, MRI is more attentions for diagnosis and prognosis of brain disease (Lawler & Chiocca, 2013).
Brain tumor segmentation is an important and challenging task in surgical and treatment planning. In practice, manual segmentation is widely used in clinical routines but it has still an error and time-consuming. In addition, the radiologists have to have some additional knowledge such as pathology and anatomy (Liu et al., 2014). As such, several semi and fully automated segmentation techniques dealing with various variation of tumor have been proposed (Gordillo et al., 2013, Liu et al., 2014; El Sayed et al., 2014). However, there were a few works dealing with the unclear and irregular boundary (Gordillo et al., 2013, Liu et al., 2014, Sachdeva et al., 2012). Moreover, most of the existing algorithms are not flexible for realistic clinical practice (Njeh, Sallemi, Ayed, Chtourou, Lehericy, & Galanaud, 2015) due to non-reliable model building with ill-training data and inflexible parameters in different datasets. In addition, tumor segmentation result reported to date is 70–85% on average on dice metric (Hamamci et al., 2012, Menze et al., 2015). These techniques still provided an over and under segmentation from the ambiguous tumor boundary, which often occurs on edema tissues.
Cellular Automata (CA) are promising model being successfully applied to a variety of advanced researches (Wolfram, 2002, Wongthanavasu and Ponkaew, 2016). More specifically, CA-based segmentation algorithms were introduced to address the global optimization for different datasets which are robust to noise (Huang et al., 2014, Menze et al., 2015). These algorithms establish the connecting of graph-based seed segmentation to CA model. Grow-Cut is a beginning CA-based segmentation proposed by Vezhnevets et al. (2005). It is an efficient algorithm, but has some drawbacks when cope with specific structures which anatomical structure exhibits relative smooth boundaries. Subsequently, Tumor-Cut (Hamamci et al., 2012), which is a CA-based direct-purposed tumor segmentation algorithm, was proposed. It modified the local transition function of Grow-Cut to eliminate the drawbacks. In addition, it figured out the shortest path problem encountered in the graph-based seed segmentation. Tumor-Cut provides an outstanding result superior to other graph-based seed segmentation techniques; Grow-Cut, Graph-Cut and random walker (Hamamci et al., 2012). Unlike other semi-automatic segmentation algorithms, Tumor-Cut requires a minimal degree of user interaction to draw a line over diameter tumor (Huang et al., 2014). Although Tumor-Cut provides an outstanding result for tumor segmentation, it has still faced the problem of robustness in seed growing. CA's state energy defined by the similarity function in Tumor-Cut will decrease significantly when moving from seed pixels. This leads to under segmentation.
Besides, there are attempts to enhance tumor boundaries on an tranforming image. Saad, Abu-Bakar, Muda, Mokji, and Salahuddin (2011) used GLCM feature similar to 3D histogram to segment the brain lesions. They learned and identified the characteristic of abnormal areas, such as tumor, infraction, abscess and haemorrhage, using contour plot based on GLCM feature space. The brain lesions are then segmented by threshold-based technique. Although the method can segment the brain lesions on both hyper-intense and hypo-intense signal, it still provided wrong results from the drawback of threshold-based technique. In addition, Sachdeva et al. (2012) proposed the method to transform MRI to content-based image. They used features from a gray-level co-occurrence matrix (GLCM) to analyze a characteristic of tumor and non-tumor. The predominant texture obtained by GLCM features and original intensity (MRI) values are identified the tumor region. Then, the content-based image was segmented using Active Contour Model (ACM) (Kass et al., 1988, Wang et al., 2009a, Xu and Prince, 1998) for core tumor only. However, the result was in problem with unclear boundary. In additon, Sompong and Wongthanavasu (2014) proposed an image transformation based on GLCM feature prior to segmentation. The proposed local transition function is inferior to the problem that the tumor areas are similar to the background area. The resulting transforming image is segmented in comparison with Tumor-cut algorithm (Hamamci et al., 2012) and active contour model (Wang, Cheng, & Basu, 2009) on small dataset. The work needs to be improved.
This paper presents a novel brain tumor segmentation framework. It consists of two main contributions: (i) MRI enhancement using the proposed GLCM-based CA, and (ii) improvement of the seed growing robustness in Tumor-Cut algorithm. For the first issue, GLCM-based CA (GLCM-CA) is proposed. Firstly, an original MRI is carried out transforming to new features using the proposed GLCM. The tumor characteristic is now learned by GLCM feature space. Secondly, the proposed CA algorithm maps these features to the target image. For the second issue, the improved Tumor-Cut (ITC) is proposed to cope with the robustness of seed growing. In this regard, a novel patch weighted feature is proposed in the similarity function. Subsequently, the traditional distance in Tumor-Cut algorithm is replaced by the proposed patch weighted distance. Ultimately, the ITC implements on the GLCM-CA-based target image. For performance evaluation, the public benchmark datasets from BraTS2013 Challenges (2013) are implemented throughout using dice quantitative evaluation metrics in comparison with the state-of-the-art methods summarized in Table 3 and detailed in Section 5.4.
The paper was organized as follows. Following this section, background related to the proposed method is given in Section 2. Section 3 presents the proposed scheme in details and evaluation metrics. In Section 4, benchmark datasets with detailed information are provided. Section 5 gives extensive experimental results of the proposed and compared methods. Ultimately, conclusions and discussions were given in Section 6.
Section snippets
Brain tumor segmentation
Brain tumor segmentation processes generally consist of three components shown in Fig. 2: image acquisition and pre-processing, and segmentation technique and performance evaluation (Liu et al., 2014, El-Dahshan et al., 2014). Pre-processing operation includes de-noising, skull-striping, bias field reducing, intensity quantization, etc. that have direct effect on the result of brain tumor segmentation. Subsequently, segmentation technique is applied to extract the tumor in various tissues
Proposed GLCM-CA for image transformation
In order to cope with an ambiguity of tumor boundary, this section presents the proposed method consisting of the tumor characteristic learning through GLCM feature space, and the CA-based approach for transforming such a feature space to the target image.
Data preparation
This section describes the multimodal MRI brain tumor dataset called BraTS2013 which was used in the experimentation in the proposed and the compared methods throughout. BraTS2013 is available from Virtual Skeleton Database; https://www.smir.ch/BRATS/Start2013 (BraTS2013, 2013; Menze et al., 2015). BraTS2013 dataset aims to validate the various tumor and edema segmentation methods. Although numerous segmentation methods have been proposed during the last few decades, they are too difficult to
Experimental design
This section describe an experimental design of the proposed approach which is separated to core tumor segmentation and edema segmentation. We initially setup the experiment for the proposed ITC. Since BraTS2013 dataset is a 3D multimodal MRI, the proposed ITC is applied a 26-cell cubic neighborhood to use in 3D voxels segmentation. Initial seed selection is performed on MRI input on z-axis. The seeds are drawn on MRI every three slices. A seed of non-tumor is identified by rectangles that
Conclusion
Brain tumor segmentation on MRI is an important and challenging task in surgical and treatment planning. A variety of state-of-the-art methods have been proposed to cope with ambiguous tumor boundary, which often occurs on edema tissues. Some focus on the improvement of segmentation algorithms, other attempt to transform images to enhance tumor boundaries prior to segmentation. However, they have still faced over and under segmentation.
The proposed method takes two paradigms to improve the
References (32)
- et al.
Magnetic resonance imaging-based target volume delineation in radiation therapy treatment planning for brain tumors using localized region-based active contour
International Journal of Radiation Oncology Biology Physics
(2013) - et al.
Computer-aided diagnosis of human brain tumor through MRI: a survey and a new algorithm
Expert Systems with Applications
(2014) - et al.
State of the art survey on MRI brain tumor segmentation
Magnetic Resonance Imaging
(2013) - et al.
3D multimodal MRI brain glioma tumor and edema segmentation: a graph cut distribution matching approach
Computerized Medical Imaging and Graphics
(2015) - et al.
Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies
Applied Soft Computing
(2013) - et al.
A novel content-based active contour model for brain tumor segmentation
Magnetic Resonance Imaging
(2012) - et al.
Active contours driven by local Gaussian distribution fitting energy
Signal Processing
(2009) - et al.
A cellular automata-based learning method for classification
Expert Systems With Applications
(2016) - et al.
Semi-automated brain tumor and edema segmentation using MRI
European Journal of Radiology
(2005) - Challenges, B. A. T.S2013 (2013). (https://www.virtualskeleton.ch/BRATS/Start2013) Virtualskeleton database...
Segmentation of brain tumor images based on integrated hierarchical classification and regularization
Patch-based segmentation of brain tissues
Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound
IEEE Transactions on Medical Imaging
Semi-automatic segmentation of multimodal brain tumor using active contours
Tumor-cut: segmentation of brain tumors on contrast enhanced MR images for radiosurgery applications
IEEE Transactions on Medical Imaging
Textural features for image classification
IEEE Transactions on Systems, Man and Cybernetics
Cited by (38)
CGFFCM: Cluster-weight and Group-local Feature-weight learning in Fuzzy C-Means clustering algorithm for color image segmentation [Formula presented]
2021, Applied Soft ComputingCitation Excerpt :GLCM is a set of features based on second-order statistics that are easy to implement and performs well in terms of time and complexity [56]. GLCM considers spatial correlation between image pixels [58,59]. By using GLCM, better segmentation can be achieved for images [60].
Investigating Brain Tumor Segmentation and Detection Techniques
2020, Procedia Computer ScienceMedGA: A novel evolutionary method for image enhancement in medical imaging systems
2019, Expert Systems with ApplicationsCitation Excerpt :In addition, we plan to integrate MedGA as a pre-processing step within an automatic pipeline defined in the context of MR image classification for efficient computer-assisted segmentation using thresholding techniques, such as (Otsu, 1975; Ridler & Calvard, 1978; Trussell, 1979). Indeed, MR image segmentation is a compelling task in radiology practice, for instance in brain tumor detection and delineation (Sompong & Wongthanavasu, 2017). Especially, we plan to apply MedGA to metastatic cancer segmentation in neuro-radiosurgery therapy (Leksell, 1949), wherein the enhancement region must be accurately segmented (Militello et al., 2015a; Rundo et al., 2017).
Multi-channeled MR brain image segmentation: A new automated approach combining BAT and clustering technique for better identification of heterogeneous tumors
2019, Biocybernetics and Biomedical EngineeringMulti-channeled MR brain image segmentation: A novel double optimization approach combined with clustering technique for tumor identification and tissue segmentation
2019, Biocybernetics and Biomedical EngineeringDeep Cellular Automata-Based Feature Extraction for Classification of the Breast Cancer Image
2023, Applied Sciences (Switzerland)