Volume 4, No. 12, December 2013 Journal of Global Research in Computer Science RESEARCH PAPER Available Online at www.jgrcs.info

Combining Evolutionary Algorithms and Average Overlap Metric Rules for Medical Image Segmentation M. A. Abdallah*, Ashraf Afifi, E. A .Zanaty Information Technology Département, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia. Abstract: In this paper, we explore a new algorithm based on evolutionary algorithms and fusion concepts for improving medical image segmentation. The proposed approach starts by finding seeds that cover the image using genetic algorithm (GA). This initial partition is used as the seed to a computationally efficient region growing method to produce the closed regions. The average overlap metric (AOM) is used to classify these regions into groups based on the similarity criterion. The fusion modules are applied to each group to find the points that label the suite membership values. The different fusion rules will be applied to these groups to produce a set of chromosomes to select the best data in each chromosome to represent the final segment. To prove the efficiency of the proposed algorithm, the proposed algorithm will be applied to challenging applications: MRI datasets, 3D simulated MRIs, and gray matter/white matter of brain segmentations. Keywords: Evolutionary algorithms, genetic algorithm, region growing, average overlap metric, decision fusion.

INTRODUCTION Image processing covers various techniques that are applicable to a wide range of applications. Image processing can be viewed as a special form of two-dimensional signal processing used to uncover information about images. Among various image processing tasks, segmentation can be viewed as the first essential and important step of low level vision [1]. Image segmentation is a process by which an image is partitioned into non-intersecting regions. These regions have two properties: (1) homogeneity within a region, i.e., the texture or color in a region should be as similar as possible, and (2) heterogeneity between the regions, i.e., texture or color that in one region should be distinct from those in another region. A variety of approaches have been proposed for image segmentation [2-19]. Xu et al. [13] summarized these methods into two categories: (1) boundary detection-based approaches, which try to search closed boundary contours for segmenting an image, and (2) region clustering-based approach, which group „„similar‟‟ neighboring pixels into clusters. Cheriet et al. [5] proposed a modified Otsu‟s approach (Otsu, [20]) called recursive thresholding technique (dynamic thresholding) for imagesegmentation. Grau et al.[8] proposed an improvement to the watershed transform that enables the introduction of prior information for medical image segmentation. Yan and Kassim [14] used minimal path deformable models incorporated with statistical shape priors to extract organ contours. Karayiannis and Pai [9] used a fuzzy algorithm for learning vector quantization in MRI segmentation. Fuzzy c-means clustering algorithms with spatial information were also proposed for medical image segmentation [3,6]. Recently, the Hopfield neural networks have been proposed as alternative approaches [2,4]. Among them, the segmentation using competitive Hopfield neural networks (CHNN) are formulated as a cost-function-minimization problem to perform gray level thresholding on the image histogram or

© JGRCS 2010, All Rights Reserved

the pixels‟ gray levels arranged in a one-dimensional array [2,4] Even though many segmentation methods have been presented, most of them are still limited in two respects: First, the number of classes is predetermined, which implies that users must identify the number of regions beforehand. Second, most of the proposed methods need some preprocessing to reduce or remove the noise. Recently, to rectify these limitations, Felzenszwalb and Huttenlocher [7] proposed a graph-based image segmentation method, which obeys the properties of being neither too coarse nor too fine according to a particular region comparison function. In spirit of the segmentation property, an automatic hierarchical evolutionary based image segmentation approach is proposed in this paper. Unlike the conventional genetic algorithm [21], which uses a fixed or pre-defined chromosome and the phenotype structure, the hierarchical evolutionary algorithm (HEA) [22] can relax these constraints. The intrinsic property of the HEA is its ability to code the parameters of the considered problem in a hierarchical structure. This particular property makes it a potential technology for automatic medical image segmentation. Recently, the researchers have shown that GAs have been found to be effective in medical image segmentation [23]. Lai and Chang [24] presented hierarchical evolutionary algorithms (HEA) for medical image segmentation. By means of a hierarchical structure in the chromosome, the approach can classify the image into appropriate classes and avoid the difficulty of searching for the proper number of classes. Karteeka et al. [25] studied medical image segmentation and attempted to extract the shape of the tissues in medical images automatically using automatic clustering using differential evolution. Karman [26] proposed face detection based on usage of Genetic algorithm for advance classification of cases and objects of the input image. He subdivided the image into “face” and “Non face” objects to accelerate face detection. For more 1

M. A. Abdallah et al, Journal of Global Research in Computer Science, 4 (12), December 2013,1-7

recently, the use of the genetic model besides the active contour has been suggested [26]. A method based on hybrid genetic algorithm (GA) and active contour was presented to solve some of active contour problems for accurate medical ultrasound image segmentation [27]. Wang et al. [29] combined GA and fuzzy clustering in which the genetic algorithm is adopted to optimize the initial cluster center and then the fuzzy clustering is used for image segmentation. More discussions can be shown in [28] for the major applications of GAs to the domain of medical image segmentation.

By applying AOM and fusion methods [18] to these segments, we can obtain the best segment which represents the candidate segment. a. Creating candidate populations (IPS); b. Seed region growing to isolate suitable regions; c. AOM procedure for classifying regions; d. Decision fusion for improving segmentation. Decision fusion applied to each group

Although the concept of HEA for infinite-impulse-response (IIR) filter was designed [17], as far as we know, no one has applied the HEA method to image segmentation. The main objective of our contribution is to successfully employ HEA in medical image segmentation without considering any auxiliary or extra medical image information, such as contextual or textual properties, in given medical images. On the other hand, when we apply this method, the number of clusters in the given image does not need to be known in advance. To avoid the drawbacks of the previous work, this paper introduces a new combination between GA, seed region growing, average overlap metric (AOM) and fusion concepts to improve the quality of image segmentation and accelerate the search for finding the optima. The structure of our approach consists of four steps: finding the initial population, performing seed region growing, evaluating fitness function for each chromosome, and evolving the chromosomes. The initial population is randomly generated by uniform discrete image sampling. The proposed GA attempts to find out the optimal centroid for each region for fine segmentation result. The chromosome representation includes control genes, gray-levels genes, and x and y-axis values of the gray level. The gray-level genes with controlgenes equal to one and with x and y-axis values are centroid of the clusters. Then, the initial population is passed to the seed region growing with initial seed (with location (x,y)). The fitness function is improved by considering the covered and uncovered data for quantitative measure of a segmentation result. Then, AOM method is used to classify the output regions of seed region growing method into groups according to similarity measure. Since the seed region growing produces crisp outputs while the largest group of fusion methods combines soft decisions, Gaussian membership function is used to convert the hard decisions to soft. The different fusion rules are applied to these groups to produce segments of points that label the similar membership values. The proposed algorithm is applied to challenging applications: MRI datasets, 3D simulated MRIs, and gray matter/white matter of brain segmentations. The experimental results show that the proposed technique produces accurate and stable results. THE PROPOSED METHOD The proposed method start by creating initial population and applying region growing algorithm based on seed estimation from chromosome such as described in [17]. Now, each chromosome includes a seed point which represents a segment. If we have n-population we can get 0.70 indicates excellent agreement. After applying this algorithm k group ( Lk ) of regions is given. Decision Fusion Once the set of segmentation has been created, an effective way of combining their outputs must be found. Fusion of multiple methods can be performed either at data level or at the decision level. We focus in this paper on decision fusion using parallel architectures. There are many decision fusion methods for each type of outputs. In this paper, we will use several of them, namely, the popular voting methods [8] for hard outputs and the minimum, maximum, median, and product rules [24] for soft outputs. The largest group of fusion methods combines soft decisions. Most popular among them are the minimum, maximum, mean, median and product fusion rules, which are defined as follows [28][30]. a) Median rule: The rule assigns p to Ri region where

Pmed ( Ri , p)

In this section, we experiment the proposed method using T1-weighted MR phantom with slice thickness of 1mm, slice#91, size is 129 129 pixels, as shown in Fig. (2). The test image is segmented at various noise levels 0%, 3%, and 6% using fusion voting, median, mean, maximum, minimum, product methods (see Fig. (2)). The comparison score S for each algorithm as proposed in [29] is defined as follows:

S

A Aref A Aref

where A represents the set of pixels belonging to a class as found by a particular method and

Aref

represents the

reference cluster pixels.

(a)

(b)

(c)

Figure.(2): Test images slice#91.

is maximum: ml

Pmed ( Ri , p ) med ui , j ( p) k 1

b) Mean rule: The rule assigns p to Ri

Pmean ( Ri , p)

region where

is maximum: ml

Pmean ( Ri , p) mean ui , j ( p) k 1

(d)

c) Maximum rule: The rule assigns p to Ri region where

Pmax ( Ri , p) is maximum:

Pmax ( Ri , p) max ui , j ( p) k 1

d) Minimum rule: The rule assigns p to Ri region where

Pm in ( Ri , p ) is maximum: ml

Pmin ( Ri , p) min ui , j ( p) k 1

e) Product rule: The rule assigns p to Ri region where is

Figure.(3): Segmentation results for the slice (z=91):

Fig.(3) depicts the results of the proposed fusion methods. Table (9) shows the score S of the image using fusion voting, median, mean, maximum, minimum, product methods. It shows that mean and maximum methods achieve better accuracy than other methods with no noise (0%). For 3% noise, maximum method is the best. In the case of 6% noise, mean and maximum obtain the best accuracy. Product method is worst for all noise levels. Table (9): The score S of the slice (z=91).

maximum:

ml

Pprod ( Ri , p ) ui , j ( p ) k 1

These fusion schemes need no training in order to produce the output decision, while the others such as probabilistic product, weighted average, Dempster-shafer, and neural networks require training.

©JGRCS 2010, All Rights Reserved

(f)

(a) Voting (b) Median, (c) Mean, (d) Maximum, (e) Minimum, (f) Product.

ml

Pprod ( Ri , p )

(e)

Noise/RF

0

3%

6%

Voting

0.82

0.73

0.60

Mean

0.84

0.80

0.67

Min

0.80

0.76

0.65

Max

0.83

0.82

0.67

Median

0.82

0.70

0.66

Product

0.75

0.61

0.60

5

M. A. Abdallah et al, Journal of Global Research in Computer Science, 4 (12), December 2013,1-7

Comparative results using experiments on the simulated 3D data: To prove the efficiency of the proposed approach, we compare the accuracy of the proposed fusion voting, median, mean, maximum, minimum, product methods and the recent fuzzy methods k-means [27] and c-means [13] for a simulated volumetric MRIs data (with 3% noise) of ten slices from #82 to #91 (see Fig.(3)). These methods are applied to each slice individually and the mean segmentation accuracy is evaluated for each image. The upper part of the 1rd and 2rd row of Table (10) show the corresponding accuracy scores of the k-means and c-means after applying them on the ten slices. Obviously, c-means acquires the better segmentation performance than k-means, and the fusion methods gave the best accuracy.

Figure.(4): Original brain volume (simulated 3D data).

The lower part of Table (10) shows the performance of each fusion method on the simulated data. This table shows that the highest segmentation accuracy is obtained using the mean fusion rule. It gives an improvement about 1.6% over the accuracy of the best method and an improvement 9.8% and 13% over c-means and k-means methods respectively. It shows that the least performance is obtained applying product and the minimum fusion rules.

Table (10): Segmentation performance of the fusion techniques on MRI volume dataset.

Fusion techniques

Existing methods

Methods FCM

MRI volume #1 #2 55.28 40.9

#3 35.76

#4 50.34

#5 38.32

#6 43.65

#7 53.87

#8 34.65

#9 48.09

#10 44.98

average 44.584

k-means

54.54

50.43

16.98

51.21

31.43

38.23

53.65

28.32

46.98

41.98

41.375

Voting Mean Min Max Median Product

65.98 67.54 59.54 70.43 66.98 66.40

52.76 76.89 60.43 56.3 65.9 64.25

43.09 44.07 36.98 44.65 45.76 35.21

55.09 47.02 55.21 59.18 50.34 44.05

42.76 45.12 39.43 46.17 48.32 3 .54

59.3 48.34 58.23 56.18 53.65 50.87

55.19 59.54 47.65 57.84 53.87 57.23

44.38 46.72 48.32 47.64 44.65 45.12

53.52 57.98 56.98 54.92 58.09 57.65

46.32 42.66 43.87 51.01 45.18 43.98

51.839 53.588 50.664 54.432 53.274 49.63

CONCLUSION Structural MRI markers now support earlier and moreprecise diagnosis and measurement of progression. The presence of atrophy of medial temporal structures is a partially validated candidate marker for early diagnosis of the disease. Rates of whole-brain and hippocampal atrophy are sensitive and powerful markers of progression of neurodegeneration and, as a result, are increasingly used, along with clinical metrics, as outcomes in clinical trials of potential disease-modifying therapies. Measures of cortical thinning and automated classification approaches that assess the overall pattern of atrophy seem to show promise for the Alzheimer‟s diagnosis. For improving patient's diagnosis using of MRI images, in this paper, we have presented an approach which integrates GA, region growing, and average overlap metric (AOM) coefficient with fusion modules to increase segmentation accuracy compared to the existing methods. The presented algorithm pipelines can align an individual digital brain to a reference template on a voxel-by-voxel basis and automatically label brain structures without basis of prior knowledge of a digital atlas. The proposed approach starts by finding seeds that cover the image using GA algorithm. This initial partition is used as the seed to a computationally efficient region growing method to produce the closed regions. The average overlap metric (AOM) is used to classify these regions into groups based on the similarity criterion. The fusion modules are applied to each group to find the points that label the suite membership values.

©JGRCS 2010, All Rights Reserved

Although the cost of the algorithm computation is not low; it is acceptable for accurate MRIs segmentation. The proposed voting, mean, minimum, maximum, median, and product have shown higher robustness to segment most of brain images data. The segmentation of the slice #91 shows that the mean and maximum methods have obtained the higher accuracy than others for 0% and 3% noise. For higher noise 6%, the median and mean methods have achieved the best accuracy. Despite the high noise, the proposed method has given acceptable results higher than 60% in the case of 9% noise. For the simulated 3D data (brain volume consists of ten slices), the mean accuracy of the proposed algorithm have been evaluated and compared to fuzzy c-means and k-means methods. Although the diversity of applying the fusion modules, they have still achieved better results than fuzzy cmeans and k-means methods i.e. maximum, mean, and median methods achieved an improvement about 10.0% and 13% over the average segmentation accuracy of fuzzy cmeans and k-means respectively. REFERENCES [1].

Gonzalez, R. C., Woods, R. E.,“Digital image processing. Reading”, MA: Addison-Wesley, 1992.

[2].

Chang, C.-Y., Chung, P.-C.,” Medical image segmentation using a contextual-constraint-based Hopfield neural cube”.Image and Vision Computing, vol.19, pp.669–678, 2001.

[3].

Chen, S., Zhang, D.,” Robust image segmentation using FCM with spatial constraints based on new kernel-induced 6

M. A. Abdallah et al, Journal of Global Research in Computer Science, 4 (12), December 2013,1-7

distance measure”. IEEE Transactions on Systems Man and Cybernetics B, vol.34, pp.1907–1916, 2004. [4].

Cheng, K. S., Lin, J. S., Mao, C. W.,“The application of competitive Hopfield Neural Network to medical image segmentation”. IEEE Transactions on Medical Imaging, vol. 15, pp.560–567, 1966.

[18].

E.A.Zanaty, “An Approach based on fusion concepts for improving brain magnetic resonance images (MRIs) segmentation”, Journal of Medical Imagining and Health Informatics, Journal of Medical Imaging and Health Informatics, vol. 3, no.1, pp. 30-37(8), March 2013.

[19].

M. Yoshimura, S. Oe, “Evolutionary segmentation of texture using genetic algorithms towards automatic decision of optimum number of segmentation areas”, Pattern Recognition, vol.32, pp.2041–2054, 1999.

[20].

P. Andrey, “Selectionist relaxation: genetic algorithms applied to image segmentation”, Image and Vision Computing, vol. 17, pp.175–187, 1999.

[5].

Cheriet, M., Said, J. N., Suen, C. Y.,“A recursive thresholding technique for image segmentation”. IEEE Transactions on Image Processing, vol. 7, pp.918–921, 1998.

[6].

Chuang, K.-S., Tzeng, H.-L., Chen, S., Wu, J., Chen, T.J.,“Fuzzy c-means clustering with spatial information for image segmentation”. Computerized Medical Imaging and Graphics, vol.30, pp.9–15.2006.

[21].

[7].

Felzenszwalb, P. F., Huttenlocher, D. P.,“Efficient graphbased image segmentation”. International Journal of Computer Vision, vol.59,pp. 1–26, 2004.

C. Li, R. Chiao, “Multiresolution genetic clustering algorithm for texture segmentation”, Image and Vision Computing, vol. 21, pp.955–966, 2003.

[22].

Grau, V., Mewes, A. U. J., Alcaniz, M., Kikinis, R.,Wardield, S. K.,” Improved watershed transform for medical image segmentation using prior information”. IEEE Transactions on Medical Imaging, vol.23, pp.447–458, 2004.

K. E. Melkemi, M. Batouche, S. Foufou, “A multiagen system approach for image segmentation using genetic algorithms and extremal optimization heuristics”, Pattern Recognition Letters, vol. 27, pp.1230– 1238, 2006.

[23].

Karayiannis, N. B.,Pai, P.-I., “Segmentation of magnetic resonance image using fuzzy algorithms for learning vector quantization”. IEEE Transactions on Medical Imaging, vol.18, pp.172–180, 1999.

K. E. Melkemi, M. Batouche, S. Foufou, “A multiagen system approach for image segmentation using genetic algorithms and extremal optimization heuristics”, Pattern Recognition Letters, vol. 27, pp.1230– 1238, 2006.

[24].

[10].

Maulik, U., Banyopadhyay, S.,“Genetic algorithm-based clustering technique. Pattern Recognition”, vol.33, pp.1455– 1465, 2000.

C. C. Lai and C. Y. Chang, “A hierarchical evolutionary algorithm for automatic medical image segmentation”, Expert Systems with Applications, 2007.

[25].

[11].

Sammouda, R., Niki, N., &Nishitani, H.,“Hopfield neural network for the multichannel segmentation of magnetic resonance cerebral images”. Pattern Recognition, vol.30,pp. 921–927, 1997.

K. Karteeka Pavan, V. Sesha Srinivas, A. SriKrishna and B. Eswara Reddy, 2012. Automatic Tissue Segmentation in Medical Images using Differential Evolution”, Journal of Applied Sciences, 12, pp.587-592, 2012.

[26].

Sarkar, M., Yegnanarayana, B.,Khemani, D.,“A clustering algorithm using an evolutionary programming-based approach”. Pattern Recognition Letters, vol.18, pp.975–986, 1997.

M. Karman, S. Lee, “Advanced classification using genetic algorithm and image segmentation for Improved FD”, Second International Conference on Computer Research and Development, pp.364-368, 2010.

[27].

Xu, Y., Olman, V., Uberbacher, E. C.,“A segmentation algorithm for noisy images: Design and evaluation”. Pattern Recognition Letters, vol.19, 1213, pp.1224, 1998.

M. Talebi, A. Ayatollahi, A. Kermani, “Medical ultrasound image segmentation genetic active countor”, J. Biomedical Science and Engineering4, pp.105-109,2011.

[28].

[14].

Yan, P., Kassim, A. A.,“Medical image segmentation using minimal path deformable models with implicit shape priors”. IEEE Transactions on Information Technology B, vol.10, pp.677–684, 2006.

Chih-Chin Lai a, Chuan-Yu Chang, “A hierarchical evolutionary algorithm for automatic medical image segmentation”, Expert Systems with Applications 36, 248– 259, 2009.

[29].

[15].

Coleman, G. B., Andrews, H. C.,“Image segmentation by clustering”. Proceedings oF IEEE, vol. 67, pp.773–785, 1979.

H. Wang, B.J. Zhang, X.Z. Liu, D.Z. Luo, S.B. Zhong, “Image segmentation method based on improved genetic algorithm and fuzzy clustering”, Advanced Materials Research379, pp. 143-144, 2011.

[16].

Singh, M., Patel, P., Khosla, D., Kim, T.,“Segmentation of functional MRI by K-means clustering”. IEEE Transactions on Nuclear Science, vol.43,pp. 2030–2036, 1996.

[30].

P. Jaccard, "The distribution of the flora in the alpine zone". New phytol., vol. 11, no. 2, pp. 37 50,1912.

[31].

L. Dice, "Measures of the amount of ecologic association between species", Ecology vol.26, pp. 297-302, 1945

[32].

A. P. Zijdenbos, “MRI segmentation and the quantification of white matter lesion”, PhD thesis, Vanderbilt University, Electrical Engineering Department, Nashville Tennessee; December 1994.

[8].

[9].

[12].

[13].

[17].

E.A.Zanaty, Ahmed S. Ghiduk, “A novel approach for medical image segmentation based on genetic and seed region growing algorithms”, Journal of Computer Science and Information Systems ComSIS Vol. 10, No. 3, pp.13191342, 2013.

©JGRCS 2010, All Rights Reserved

7

Combining Evolutionary Algorithms and Average Overlap Metric Rules for Medical Image Segmentation M. A. Abdallah*, Ashraf Afifi, E. A .Zanaty Information Technology Département, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia. Abstract: In this paper, we explore a new algorithm based on evolutionary algorithms and fusion concepts for improving medical image segmentation. The proposed approach starts by finding seeds that cover the image using genetic algorithm (GA). This initial partition is used as the seed to a computationally efficient region growing method to produce the closed regions. The average overlap metric (AOM) is used to classify these regions into groups based on the similarity criterion. The fusion modules are applied to each group to find the points that label the suite membership values. The different fusion rules will be applied to these groups to produce a set of chromosomes to select the best data in each chromosome to represent the final segment. To prove the efficiency of the proposed algorithm, the proposed algorithm will be applied to challenging applications: MRI datasets, 3D simulated MRIs, and gray matter/white matter of brain segmentations. Keywords: Evolutionary algorithms, genetic algorithm, region growing, average overlap metric, decision fusion.

INTRODUCTION Image processing covers various techniques that are applicable to a wide range of applications. Image processing can be viewed as a special form of two-dimensional signal processing used to uncover information about images. Among various image processing tasks, segmentation can be viewed as the first essential and important step of low level vision [1]. Image segmentation is a process by which an image is partitioned into non-intersecting regions. These regions have two properties: (1) homogeneity within a region, i.e., the texture or color in a region should be as similar as possible, and (2) heterogeneity between the regions, i.e., texture or color that in one region should be distinct from those in another region. A variety of approaches have been proposed for image segmentation [2-19]. Xu et al. [13] summarized these methods into two categories: (1) boundary detection-based approaches, which try to search closed boundary contours for segmenting an image, and (2) region clustering-based approach, which group „„similar‟‟ neighboring pixels into clusters. Cheriet et al. [5] proposed a modified Otsu‟s approach (Otsu, [20]) called recursive thresholding technique (dynamic thresholding) for imagesegmentation. Grau et al.[8] proposed an improvement to the watershed transform that enables the introduction of prior information for medical image segmentation. Yan and Kassim [14] used minimal path deformable models incorporated with statistical shape priors to extract organ contours. Karayiannis and Pai [9] used a fuzzy algorithm for learning vector quantization in MRI segmentation. Fuzzy c-means clustering algorithms with spatial information were also proposed for medical image segmentation [3,6]. Recently, the Hopfield neural networks have been proposed as alternative approaches [2,4]. Among them, the segmentation using competitive Hopfield neural networks (CHNN) are formulated as a cost-function-minimization problem to perform gray level thresholding on the image histogram or

© JGRCS 2010, All Rights Reserved

the pixels‟ gray levels arranged in a one-dimensional array [2,4] Even though many segmentation methods have been presented, most of them are still limited in two respects: First, the number of classes is predetermined, which implies that users must identify the number of regions beforehand. Second, most of the proposed methods need some preprocessing to reduce or remove the noise. Recently, to rectify these limitations, Felzenszwalb and Huttenlocher [7] proposed a graph-based image segmentation method, which obeys the properties of being neither too coarse nor too fine according to a particular region comparison function. In spirit of the segmentation property, an automatic hierarchical evolutionary based image segmentation approach is proposed in this paper. Unlike the conventional genetic algorithm [21], which uses a fixed or pre-defined chromosome and the phenotype structure, the hierarchical evolutionary algorithm (HEA) [22] can relax these constraints. The intrinsic property of the HEA is its ability to code the parameters of the considered problem in a hierarchical structure. This particular property makes it a potential technology for automatic medical image segmentation. Recently, the researchers have shown that GAs have been found to be effective in medical image segmentation [23]. Lai and Chang [24] presented hierarchical evolutionary algorithms (HEA) for medical image segmentation. By means of a hierarchical structure in the chromosome, the approach can classify the image into appropriate classes and avoid the difficulty of searching for the proper number of classes. Karteeka et al. [25] studied medical image segmentation and attempted to extract the shape of the tissues in medical images automatically using automatic clustering using differential evolution. Karman [26] proposed face detection based on usage of Genetic algorithm for advance classification of cases and objects of the input image. He subdivided the image into “face” and “Non face” objects to accelerate face detection. For more 1

M. A. Abdallah et al, Journal of Global Research in Computer Science, 4 (12), December 2013,1-7

recently, the use of the genetic model besides the active contour has been suggested [26]. A method based on hybrid genetic algorithm (GA) and active contour was presented to solve some of active contour problems for accurate medical ultrasound image segmentation [27]. Wang et al. [29] combined GA and fuzzy clustering in which the genetic algorithm is adopted to optimize the initial cluster center and then the fuzzy clustering is used for image segmentation. More discussions can be shown in [28] for the major applications of GAs to the domain of medical image segmentation.

By applying AOM and fusion methods [18] to these segments, we can obtain the best segment which represents the candidate segment. a. Creating candidate populations (IPS); b. Seed region growing to isolate suitable regions; c. AOM procedure for classifying regions; d. Decision fusion for improving segmentation. Decision fusion applied to each group

Although the concept of HEA for infinite-impulse-response (IIR) filter was designed [17], as far as we know, no one has applied the HEA method to image segmentation. The main objective of our contribution is to successfully employ HEA in medical image segmentation without considering any auxiliary or extra medical image information, such as contextual or textual properties, in given medical images. On the other hand, when we apply this method, the number of clusters in the given image does not need to be known in advance. To avoid the drawbacks of the previous work, this paper introduces a new combination between GA, seed region growing, average overlap metric (AOM) and fusion concepts to improve the quality of image segmentation and accelerate the search for finding the optima. The structure of our approach consists of four steps: finding the initial population, performing seed region growing, evaluating fitness function for each chromosome, and evolving the chromosomes. The initial population is randomly generated by uniform discrete image sampling. The proposed GA attempts to find out the optimal centroid for each region for fine segmentation result. The chromosome representation includes control genes, gray-levels genes, and x and y-axis values of the gray level. The gray-level genes with controlgenes equal to one and with x and y-axis values are centroid of the clusters. Then, the initial population is passed to the seed region growing with initial seed (with location (x,y)). The fitness function is improved by considering the covered and uncovered data for quantitative measure of a segmentation result. Then, AOM method is used to classify the output regions of seed region growing method into groups according to similarity measure. Since the seed region growing produces crisp outputs while the largest group of fusion methods combines soft decisions, Gaussian membership function is used to convert the hard decisions to soft. The different fusion rules are applied to these groups to produce segments of points that label the similar membership values. The proposed algorithm is applied to challenging applications: MRI datasets, 3D simulated MRIs, and gray matter/white matter of brain segmentations. The experimental results show that the proposed technique produces accurate and stable results. THE PROPOSED METHOD The proposed method start by creating initial population and applying region growing algorithm based on seed estimation from chromosome such as described in [17]. Now, each chromosome includes a seed point which represents a segment. If we have n-population we can get 0.70 indicates excellent agreement. After applying this algorithm k group ( Lk ) of regions is given. Decision Fusion Once the set of segmentation has been created, an effective way of combining their outputs must be found. Fusion of multiple methods can be performed either at data level or at the decision level. We focus in this paper on decision fusion using parallel architectures. There are many decision fusion methods for each type of outputs. In this paper, we will use several of them, namely, the popular voting methods [8] for hard outputs and the minimum, maximum, median, and product rules [24] for soft outputs. The largest group of fusion methods combines soft decisions. Most popular among them are the minimum, maximum, mean, median and product fusion rules, which are defined as follows [28][30]. a) Median rule: The rule assigns p to Ri region where

Pmed ( Ri , p)

In this section, we experiment the proposed method using T1-weighted MR phantom with slice thickness of 1mm, slice#91, size is 129 129 pixels, as shown in Fig. (2). The test image is segmented at various noise levels 0%, 3%, and 6% using fusion voting, median, mean, maximum, minimum, product methods (see Fig. (2)). The comparison score S for each algorithm as proposed in [29] is defined as follows:

S

A Aref A Aref

where A represents the set of pixels belonging to a class as found by a particular method and

Aref

represents the

reference cluster pixels.

(a)

(b)

(c)

Figure.(2): Test images slice#91.

is maximum: ml

Pmed ( Ri , p ) med ui , j ( p) k 1

b) Mean rule: The rule assigns p to Ri

Pmean ( Ri , p)

region where

is maximum: ml

Pmean ( Ri , p) mean ui , j ( p) k 1

(d)

c) Maximum rule: The rule assigns p to Ri region where

Pmax ( Ri , p) is maximum:

Pmax ( Ri , p) max ui , j ( p) k 1

d) Minimum rule: The rule assigns p to Ri region where

Pm in ( Ri , p ) is maximum: ml

Pmin ( Ri , p) min ui , j ( p) k 1

e) Product rule: The rule assigns p to Ri region where is

Figure.(3): Segmentation results for the slice (z=91):

Fig.(3) depicts the results of the proposed fusion methods. Table (9) shows the score S of the image using fusion voting, median, mean, maximum, minimum, product methods. It shows that mean and maximum methods achieve better accuracy than other methods with no noise (0%). For 3% noise, maximum method is the best. In the case of 6% noise, mean and maximum obtain the best accuracy. Product method is worst for all noise levels. Table (9): The score S of the slice (z=91).

maximum:

ml

Pprod ( Ri , p ) ui , j ( p ) k 1

These fusion schemes need no training in order to produce the output decision, while the others such as probabilistic product, weighted average, Dempster-shafer, and neural networks require training.

©JGRCS 2010, All Rights Reserved

(f)

(a) Voting (b) Median, (c) Mean, (d) Maximum, (e) Minimum, (f) Product.

ml

Pprod ( Ri , p )

(e)

Noise/RF

0

3%

6%

Voting

0.82

0.73

0.60

Mean

0.84

0.80

0.67

Min

0.80

0.76

0.65

Max

0.83

0.82

0.67

Median

0.82

0.70

0.66

Product

0.75

0.61

0.60

5

M. A. Abdallah et al, Journal of Global Research in Computer Science, 4 (12), December 2013,1-7

Comparative results using experiments on the simulated 3D data: To prove the efficiency of the proposed approach, we compare the accuracy of the proposed fusion voting, median, mean, maximum, minimum, product methods and the recent fuzzy methods k-means [27] and c-means [13] for a simulated volumetric MRIs data (with 3% noise) of ten slices from #82 to #91 (see Fig.(3)). These methods are applied to each slice individually and the mean segmentation accuracy is evaluated for each image. The upper part of the 1rd and 2rd row of Table (10) show the corresponding accuracy scores of the k-means and c-means after applying them on the ten slices. Obviously, c-means acquires the better segmentation performance than k-means, and the fusion methods gave the best accuracy.

Figure.(4): Original brain volume (simulated 3D data).

The lower part of Table (10) shows the performance of each fusion method on the simulated data. This table shows that the highest segmentation accuracy is obtained using the mean fusion rule. It gives an improvement about 1.6% over the accuracy of the best method and an improvement 9.8% and 13% over c-means and k-means methods respectively. It shows that the least performance is obtained applying product and the minimum fusion rules.

Table (10): Segmentation performance of the fusion techniques on MRI volume dataset.

Fusion techniques

Existing methods

Methods FCM

MRI volume #1 #2 55.28 40.9

#3 35.76

#4 50.34

#5 38.32

#6 43.65

#7 53.87

#8 34.65

#9 48.09

#10 44.98

average 44.584

k-means

54.54

50.43

16.98

51.21

31.43

38.23

53.65

28.32

46.98

41.98

41.375

Voting Mean Min Max Median Product

65.98 67.54 59.54 70.43 66.98 66.40

52.76 76.89 60.43 56.3 65.9 64.25

43.09 44.07 36.98 44.65 45.76 35.21

55.09 47.02 55.21 59.18 50.34 44.05

42.76 45.12 39.43 46.17 48.32 3 .54

59.3 48.34 58.23 56.18 53.65 50.87

55.19 59.54 47.65 57.84 53.87 57.23

44.38 46.72 48.32 47.64 44.65 45.12

53.52 57.98 56.98 54.92 58.09 57.65

46.32 42.66 43.87 51.01 45.18 43.98

51.839 53.588 50.664 54.432 53.274 49.63

CONCLUSION Structural MRI markers now support earlier and moreprecise diagnosis and measurement of progression. The presence of atrophy of medial temporal structures is a partially validated candidate marker for early diagnosis of the disease. Rates of whole-brain and hippocampal atrophy are sensitive and powerful markers of progression of neurodegeneration and, as a result, are increasingly used, along with clinical metrics, as outcomes in clinical trials of potential disease-modifying therapies. Measures of cortical thinning and automated classification approaches that assess the overall pattern of atrophy seem to show promise for the Alzheimer‟s diagnosis. For improving patient's diagnosis using of MRI images, in this paper, we have presented an approach which integrates GA, region growing, and average overlap metric (AOM) coefficient with fusion modules to increase segmentation accuracy compared to the existing methods. The presented algorithm pipelines can align an individual digital brain to a reference template on a voxel-by-voxel basis and automatically label brain structures without basis of prior knowledge of a digital atlas. The proposed approach starts by finding seeds that cover the image using GA algorithm. This initial partition is used as the seed to a computationally efficient region growing method to produce the closed regions. The average overlap metric (AOM) is used to classify these regions into groups based on the similarity criterion. The fusion modules are applied to each group to find the points that label the suite membership values.

©JGRCS 2010, All Rights Reserved

Although the cost of the algorithm computation is not low; it is acceptable for accurate MRIs segmentation. The proposed voting, mean, minimum, maximum, median, and product have shown higher robustness to segment most of brain images data. The segmentation of the slice #91 shows that the mean and maximum methods have obtained the higher accuracy than others for 0% and 3% noise. For higher noise 6%, the median and mean methods have achieved the best accuracy. Despite the high noise, the proposed method has given acceptable results higher than 60% in the case of 9% noise. For the simulated 3D data (brain volume consists of ten slices), the mean accuracy of the proposed algorithm have been evaluated and compared to fuzzy c-means and k-means methods. Although the diversity of applying the fusion modules, they have still achieved better results than fuzzy cmeans and k-means methods i.e. maximum, mean, and median methods achieved an improvement about 10.0% and 13% over the average segmentation accuracy of fuzzy cmeans and k-means respectively. REFERENCES [1].

Gonzalez, R. C., Woods, R. E.,“Digital image processing. Reading”, MA: Addison-Wesley, 1992.

[2].

Chang, C.-Y., Chung, P.-C.,” Medical image segmentation using a contextual-constraint-based Hopfield neural cube”.Image and Vision Computing, vol.19, pp.669–678, 2001.

[3].

Chen, S., Zhang, D.,” Robust image segmentation using FCM with spatial constraints based on new kernel-induced 6

M. A. Abdallah et al, Journal of Global Research in Computer Science, 4 (12), December 2013,1-7

distance measure”. IEEE Transactions on Systems Man and Cybernetics B, vol.34, pp.1907–1916, 2004. [4].

Cheng, K. S., Lin, J. S., Mao, C. W.,“The application of competitive Hopfield Neural Network to medical image segmentation”. IEEE Transactions on Medical Imaging, vol. 15, pp.560–567, 1966.

[18].

E.A.Zanaty, “An Approach based on fusion concepts for improving brain magnetic resonance images (MRIs) segmentation”, Journal of Medical Imagining and Health Informatics, Journal of Medical Imaging and Health Informatics, vol. 3, no.1, pp. 30-37(8), March 2013.

[19].

M. Yoshimura, S. Oe, “Evolutionary segmentation of texture using genetic algorithms towards automatic decision of optimum number of segmentation areas”, Pattern Recognition, vol.32, pp.2041–2054, 1999.

[20].

P. Andrey, “Selectionist relaxation: genetic algorithms applied to image segmentation”, Image and Vision Computing, vol. 17, pp.175–187, 1999.

[5].

Cheriet, M., Said, J. N., Suen, C. Y.,“A recursive thresholding technique for image segmentation”. IEEE Transactions on Image Processing, vol. 7, pp.918–921, 1998.

[6].

Chuang, K.-S., Tzeng, H.-L., Chen, S., Wu, J., Chen, T.J.,“Fuzzy c-means clustering with spatial information for image segmentation”. Computerized Medical Imaging and Graphics, vol.30, pp.9–15.2006.

[21].

[7].

Felzenszwalb, P. F., Huttenlocher, D. P.,“Efficient graphbased image segmentation”. International Journal of Computer Vision, vol.59,pp. 1–26, 2004.

C. Li, R. Chiao, “Multiresolution genetic clustering algorithm for texture segmentation”, Image and Vision Computing, vol. 21, pp.955–966, 2003.

[22].

Grau, V., Mewes, A. U. J., Alcaniz, M., Kikinis, R.,Wardield, S. K.,” Improved watershed transform for medical image segmentation using prior information”. IEEE Transactions on Medical Imaging, vol.23, pp.447–458, 2004.

K. E. Melkemi, M. Batouche, S. Foufou, “A multiagen system approach for image segmentation using genetic algorithms and extremal optimization heuristics”, Pattern Recognition Letters, vol. 27, pp.1230– 1238, 2006.

[23].

Karayiannis, N. B.,Pai, P.-I., “Segmentation of magnetic resonance image using fuzzy algorithms for learning vector quantization”. IEEE Transactions on Medical Imaging, vol.18, pp.172–180, 1999.

K. E. Melkemi, M. Batouche, S. Foufou, “A multiagen system approach for image segmentation using genetic algorithms and extremal optimization heuristics”, Pattern Recognition Letters, vol. 27, pp.1230– 1238, 2006.

[24].

[10].

Maulik, U., Banyopadhyay, S.,“Genetic algorithm-based clustering technique. Pattern Recognition”, vol.33, pp.1455– 1465, 2000.

C. C. Lai and C. Y. Chang, “A hierarchical evolutionary algorithm for automatic medical image segmentation”, Expert Systems with Applications, 2007.

[25].

[11].

Sammouda, R., Niki, N., &Nishitani, H.,“Hopfield neural network for the multichannel segmentation of magnetic resonance cerebral images”. Pattern Recognition, vol.30,pp. 921–927, 1997.

K. Karteeka Pavan, V. Sesha Srinivas, A. SriKrishna and B. Eswara Reddy, 2012. Automatic Tissue Segmentation in Medical Images using Differential Evolution”, Journal of Applied Sciences, 12, pp.587-592, 2012.

[26].

Sarkar, M., Yegnanarayana, B.,Khemani, D.,“A clustering algorithm using an evolutionary programming-based approach”. Pattern Recognition Letters, vol.18, pp.975–986, 1997.

M. Karman, S. Lee, “Advanced classification using genetic algorithm and image segmentation for Improved FD”, Second International Conference on Computer Research and Development, pp.364-368, 2010.

[27].

Xu, Y., Olman, V., Uberbacher, E. C.,“A segmentation algorithm for noisy images: Design and evaluation”. Pattern Recognition Letters, vol.19, 1213, pp.1224, 1998.

M. Talebi, A. Ayatollahi, A. Kermani, “Medical ultrasound image segmentation genetic active countor”, J. Biomedical Science and Engineering4, pp.105-109,2011.

[28].

[14].

Yan, P., Kassim, A. A.,“Medical image segmentation using minimal path deformable models with implicit shape priors”. IEEE Transactions on Information Technology B, vol.10, pp.677–684, 2006.

Chih-Chin Lai a, Chuan-Yu Chang, “A hierarchical evolutionary algorithm for automatic medical image segmentation”, Expert Systems with Applications 36, 248– 259, 2009.

[29].

[15].

Coleman, G. B., Andrews, H. C.,“Image segmentation by clustering”. Proceedings oF IEEE, vol. 67, pp.773–785, 1979.

H. Wang, B.J. Zhang, X.Z. Liu, D.Z. Luo, S.B. Zhong, “Image segmentation method based on improved genetic algorithm and fuzzy clustering”, Advanced Materials Research379, pp. 143-144, 2011.

[16].

Singh, M., Patel, P., Khosla, D., Kim, T.,“Segmentation of functional MRI by K-means clustering”. IEEE Transactions on Nuclear Science, vol.43,pp. 2030–2036, 1996.

[30].

P. Jaccard, "The distribution of the flora in the alpine zone". New phytol., vol. 11, no. 2, pp. 37 50,1912.

[31].

L. Dice, "Measures of the amount of ecologic association between species", Ecology vol.26, pp. 297-302, 1945

[32].

A. P. Zijdenbos, “MRI segmentation and the quantification of white matter lesion”, PhD thesis, Vanderbilt University, Electrical Engineering Department, Nashville Tennessee; December 1994.

[8].

[9].

[12].

[13].

[17].

E.A.Zanaty, Ahmed S. Ghiduk, “A novel approach for medical image segmentation based on genetic and seed region growing algorithms”, Journal of Computer Science and Information Systems ComSIS Vol. 10, No. 3, pp.13191342, 2013.

©JGRCS 2010, All Rights Reserved

7