BFO – AIS: A Framework for Medical Image Classification Using Soft Computing Techniques

International Journal on Soft Computing (IJSC) Vol.8, No. 1, February 2017
DOI:10.5121/ijsc.2017.8102 13
BFO – AIS: A FRAME WORK FOR MEDICAL IMAGE
CLASSIFICATION USING SOFT COMPUTING
TECHNIQUES
D. Chitra and M. Karthikeyan
Assistant Professor, Dept. of Computer Science, Govt. Arts College (A), Salem-7,
Tamil Nadu, India
ABSTRACT
Medical images provide diagnostic evidence/information about anatomical pathology. The growth in
database is enormous as medical digital image equipment’s like Magnetic Resonance Images (MRI),
Computed Tomography (CT), and Positron Emission Tomography CT (PET-CT) are part of clinical work.
CT images distinguish various tissues according to gray levels to help medical diagnosis. Ct is more
reliable for early tumours and haemorrhages detection as it provides anatomical information to plan radio
therapy. Medical information systems goals are to deliver information to right persons at the right time and
place to improve care process quality and efficiency. This paper proposes an Artificial Immune System
(AIS) classifier and proposed feature selection based on hybrid Bacterial Foraging Optimization (BFO)
with Local Search (LS) for medical image classification.
KEYWORDS
Computed Tomography (CT), Feature Selection, Artificial immune classifier, Correlation based Feature
Selection (CFS), Bacterial Foraging Optimization (BFO), Local Search (LS)
1. INTRODUCTION
Medical images classification is fundamental in different applications in medical image retrieval
systems [1]. Due to medical image data’s high variability it is important to use correct models in
classification. Various medical image classification methods are discussed in literature.
Voluminous medical images generated daily have valuable information useful for medical
diagnosis, treatment, research, and education. Automatic image annotation extracts symbolic
knowledge from images to facilitate text-based retrieval of relevant images having specific
disease abnormalities. Image based Computer Aided Diagnosis (CAD) uses images and serves as
a second source of opinion for clinicians on abnormality detection and pathological classification
[2].The task of automated knowledge extraction from medical image databases remains a big
technological challenge.
CAD systems assist radiologists and increase diagnosis accuracy. Medical images are from varied
modalities like Magnetic Resonance Images (MRI), Computed Tomography (CT), and Positron
Emission Tomography CT (PET-CT) and Ultrasound. CT is a reliable technique for detection of
abnormalities like tumours and haemorrhages [3] providing anatomical information to plan radio

14
therapy. For such reasons, this research presents an abnormality detection method and
classification for CT brain images.
Medical images classification is a manual process [4]. The voluminous amount of medical images
produced and limitations of current healthcare technologies in using an automatic classification
method highlights the need for consistency in classification. This helps process a huge amount of
images easily as this is costly when done manually.
Generally, images have color, shape, texture, edge, shadows, and temporal features. Most
promising features are color, texture and edge for the following reasons [5]:
Color: Egeria occurs in two colors – black and pink (rusty rose)
Texture: Texture is a neighbourhood feature; a region or block. Each pixels variation regarding its
neighbouring pixels defines texture.
Edge: Edge is a large frequency change.
Feature extraction in image processing is a dimensionality reduction form. When an algorithm’s
input data is too large to be processed and is supposed to be notoriously redundant (much data,
but not information) then input data is transformed to a reduced representation features set
(named feature vector).Transforming input data to a feature set is feature extraction. If extracted
features are carefully chosen it is expected that features set will extract relevant information from
input data to perform the desired task using less representation instead of full-size input. Image
texture is an image area with repeated pixel intensities patterns arranged in some structural way.
Textures are prominent in natural images (grasslands, brick walls, fabrics) and properties for
interpretation and image description are revealed through texture observation and analysis like
granularity, periodicity, coarseness, geometric structure, smoothness and orientation [6, 7].
Feature selection has two approaches. One is forward selection where a process begins with no
attributes/features which are added one by one. At every step, feature which decreases most error
is added and process continues till features addition does not decrease the error [8]. The Second
approach is backward selection where the idea is to start with all attributes/features and remove
them one by one. The feature removed at every step is that which decreases error the most. The
process continues till any further removal increases error greatly.
Feature selection methods are classified into filter, wrapper, and hybrid approaches. A filter
approach is applied to data before classification where features are evaluated by heuristics based
on general data characteristics. In a wrapper approach, features are evaluated using classification
algorithms. Features in a Hybrid approach are evaluated using filter and wrapper approaches [9].
Feature selection seeks an optimal set of d features out of m. Many methods were previously used
for feature selection on training/testing data. Among various methods proposed for FS,
population-based optimization algorithms like Genetic Algorithm (GA) and Ant Colony
Optimization (ACO) attracted attention. In the new feature reduction system, an evolutionary
hybrid feature selection algorithm based on swarm intelligence called Bacteria Foraging
Optimization [10] is used.

15
In the study, CT images classification based on feature extraction using Gaussian wavelet and
Gray Level Co-occurrence Matrix (GLCM) is used. Feature selection is by wrapper technique
using Correlation based Feature Selection (CFS) and hybrid Bacterial Foraging Algorithm.
Section 2 reviews related work, section 3 describes methodology, section 4 discusses
experimental results and section 5 concludes the work.
2. RELATED WORK
Efficient implementations of curve let transform for denoising and medical image segmentation
was presented by Al Zubiet al., [11]. A comparison study was carried out between different
transforms revealing that curvelet transform showed optimal region of interest (ROI)
representation with better accuracy and less noise.
An adaptive fusion algorithm of CT and MRI medical images based on NSCT was presented by
Dai et al., [12]. Source images were decomposed multi-directionally using non-sub sampled
pyramids (NSP) and non-sub sampled directional filter banks (NSDFBs). Combining adjustable
parameter and adaptive fusion rules objective evaluation index were used for low-frequency sub-
band fusion. The experiment verified the method’s feasibility regarding visual quality and
objective evaluation criteria, standard deviation, entropy, space-frequency, and mutual-
information.
A low-dose scan protocol and an associated reconstruction algorithm allowing triple phase-
correlated in vivo imaging of perfusion and associated processes was proposed by Sawallet al.,
[13]. The new reconstruction method keeps administered radiation dose as low as 500 mGy
reducing metabolic inference to an animal ensuring longitudinal studies. It provided the first
approach to phase-correlated perfusion CT imaging in mice, boosting preclinical research with
new possibilities.
A method called Feature Selection based on the Compactness Measure from Scatter plots
(FSCoMS) to select best features from medical images to improve CBIR effectiveness was
proposed by Humpire-Mamaniet al., [14]. The algorithm has a scatter plots compactness analysis
to locate most relevant features with high separability abilities. A scatterplot’s high relevance
value means better predictability among classes based on two features. This information
generates a feature ranking for usefulness. This method was compared to 2 known feature
selection methods using 3 real medical datasets. All were compared regarding final feature vector
and retrieval effectiveness dimensionality measured by precision and recall graphs. Experiments
show that the new method not only got the highest retrieval performance but also achieved
smallest number of demanded features (dimensionality) than other analyzed methods.
A method, to choose an optimal subset of statistical texture descriptors inefficient representation
and ultrasound medical images retrieval, was presented by Sohail et al., [15]. The new feature
selection based approach of image annotation and retrieval was tested with a database of 679
ultrasound ovarian images. Retrieval performance achieved was satisfactory. Also, ultrasound
medical image retrieval performance with/without applying feature selection based image
annotation technique was compared.
A colon biopsy image classification technique, where 2 novel structural feature types: white run-
length features and percentage cluster area features were introduced and proposed by Rathore et

16
al., [16] were calculated for each colon biopsy image. Features were reduced using PCA. The
new technique was evaluated on 174 colon biopsy images, and promising performance was
observed regarding various well-known performance measures like accuracy, sensitivity and
specificity. The new technique also proved to be better compared to earlier published techniques
in the experimental section. Further, classifiers performance was evaluated using ROC curves,
and area under the curve (AUC). Rotation boost classifier with PCA based feature selection
showed better classification results compared to other classifiers.
The ability to decompose 5 materials using energy discriminating detectors and multiple
discriminant analysis (MDA) was investigated by Leeet al., [17]. A small field-of-view multi-
energy CT system was built. Linear attenuation coefficient was considered a feature of multi-
energy CT. MDA decomposes 5 materials with 6 measurements of energy dependent linear
attenuation coefficients. The results showed that a CdTe detectors based CT system with MDA
can decompose 5 materials.
A new method for lung-motion tracking from 4-dimensional X-ray computed tomographic (4D-
CT) images proposed by Kubota et al., [18] uses an enhanced 3D-KLT tracker. The feature point
extraction algorithm is image gradients based. The new method adopted pyramidal image
structure based hierarchical tracking. The proposed method’s performance for artificial 4D-CT
images described quantification results of real 4D-CT images. Results showed that lung
movement is not modelled by simple translation but by oval pattern.
A new algorithm for medical image segmentation with reference to abdominal aortic aneurysm
and degraded human brain imaging was presented by Pham et al., [19]. The new algorithm’s
development was based on theoretic distance matrix implementation with spatial semi-variances.
An alternative, approach to use energy sensitive CT imaging techniques, was proposed by
Ghadiriet al., [20]. To accurately validate the new method, a new bone model based on cortical
and marrow mixtures was proposed. A two-step energy mapping algorithm was implemented.
Phantom tomographic projections in 5 energy bins were acquired and reconstructed for
validation. The new energy mapping technique estimated LAC of different bone tissues at 511
keV. The results had 1.1% error maximum compared to true values. To test precision, 10%
variation’s effect on effective energy was investigated.
Medical image fusion for merging complementary diagnostic content using PCA and Wavelets
was carried out by Krishnet al., [21]. The new fusion approach involved sub-band decomposition
using 2D-Discrete Wavelet Transform (DWT) to preserve spectral and spatial information. Also,
PCA was applied on decomposed coefficients to maximize spatial resolution. An optimal variant
of daubechies wavelet family was selected for better results. Simulation showed improved visual
quality in the fused image compared to other state-of-art fusion approaches.
An automated tibial eminence extraction in MDCT image using shape matching was proposed by
Uozumi et al., [22]. The new method evaluated 6 patients (Age 27 ± 7, four males / two females).
Hence, the new method automatically extracted an eminence shape for all patients.
3. METHODOLOGY
This study uses classification process for CT images based on feature extraction using Gaussian
wavelet and GLCM. The features extracted are reduced using Information Gain and CFS [32].

17
The Hybrid bacterial foraging optimization (HBFO) is proposed in this paper for feature selection
and the selected features are classified using artificial immune classifier. The proposed HBFO for
feature selection and artificial immune classifier are discussed in this section.
3.1 Proposed hybrid Bacterial Foraging Optimization (BFO)
Global optimization combines a fast local optimization method with an initial search phase,
showing improved robustness compared to local search strategies [26]. It uses randomization and
local search to solve an optimization problem. Different meta-heuristic approaches solve the same
optimization problem differently [27]. BFO algorithm is a new evolutionary computation
algorithm based on Escherichia coli (E. coli) bacteria’s foraging behaviour in the human intestine.
The BFO algorithm is a biologically inspired computing technique mimicking E.coli bacteria’s
foraging behaviour [28].Natural selection removes animals with poor foraging strategies
favouring the circulation of genes of animals with successful foraging strategies, as they are more
likely to enjoy reproductive success. After generations, poor foraging strategies are removed or
shaped into good ones. Foraging is used in optimization which is explained below:
Chemotaxis: This simulates movement of an E.coli cell by swimming and tumbling via flagella.
Biologically, an E.coli bacterium moves in two ways. It can swim in the same direction or
tumble, or alternate between these two modes for an entire lifetime.
Swarming: Interesting group behaviour was observed in many mobile bacteria species including
E.coli and S. typhimurium, where stable spatio-temporal patterns (swarms) are formed in a
semisolid nutrient medium [29].
Reproduction: least healthy bacteria eventually die while healthier bacteria (those yielding higher
fitness function values) asexually split into two bacteria in the same location keeping the swarm
size constant.
Elimination and dispersal: Gradual / sudden changes in environment where a bacterium
population lives occurs for various reasons; e.g. significant rise in local temperature may kill a
group of bacteria that are in a region with a high nutrient gradients concentration. Events take
place so that all bacteria in a region are killed, or a group disperses to new locations. To simulate
this, some bacteria are liquidated at random with very small probability while new replacements
randomly initialize over search space.
Chemotaxis is the basis for local search, and reproduction speeds up convergence simulated by a
classical BFO. To a large extent, Chemotaxis and reproduction are not enough for global optima
searching. As bacteria may get stuck in initial positions or local optima, it is possible for BFO
diversity to change gradually or suddenly to eliminate being trapped in local optima [30].
Dispersion in BFO happens after certain reproduction processes. Then some bacteria are chosen,
according to a preset probability Ped, to be killed and moved to another position in the
environment.
The algorithm’s steps are as follows [31]:

18

19
Table 1 BFO Parameters
Parameter
Name
Description
Jcc Cost function value
Health
Ji
Health of bacterium i
L Counter for elimination- dispersal step
Ped Probability of occurrence of elimination-dispersal
events
S Population of the E. coli bacteria
ωattract Width of attractant
ωrepellant Width of repellent
The BFO algorithm has some drawbacks concerning complexity, possibility of being locked up
by a local solution. These are overcome by Local search. It is an iterative algorithm moving from
one solution S to another S’ according to a neighbourhood structure. Local search procedure has
the following steps.
1. Initialization. Choose initial schedule S to be current solution and compute value of the
objective function F(S).
2. Neighbour Generation. Select a neighbour S’ of current solution S and compute F(S’).
3. Acceptance Test. Test whether to accept move from S to S’. If accepted, then S’ replaces
S as current solution; otherwise S is the current solution.
4. Termination Test. Test whether algorithm should terminate. If so, output best solution
generated; otherwise, return to neighbour generation step.

20
3.2 Artificial Immune System (AIS)
Artificial immune system (AIS) information is introduced to explain the design and
implementation of an immune algorithm and Background information on immune system
metaphors to understand AIS classifiers concepts. AIS are a new computational intelligence
process inspired by a biology immune system. Immune systems regulate defence mechanism of
innate and adaptive immune response. The latter is more important as it has metaphors like
diversity, recognition, memory acquisition and self-regulation [23]. Of various mechanisms in a
biological immune system that are explored, clonal selection, negative election and immune
network model are most discussed.AIS’ key features like feature extraction, recognition, and
learning are used in classification and clustering tasks. AIS’s advantage is that it requires positive
examples and patterns, it has learnt, are explicitly examined. Also as it is self-organizing, no
effort is needed to optimize system parameters.
AIRS is a popular immune classification system whose aim is to develop a set of memory cells to
classify data. Memory cells are evolved from an artificial recognition balls (ARBs) population.
An ARB represents many identical ARB cells and reduces duplication. It dictates survival in a
population [24]. The AIRS maintain a memory cells population and ARBs for each class of
antigen (AG).The algorithm’s first stage is determining the affinity (based on Euclidean distance)
of memory cells to each AG of a specific class. The next stage is identifying strongest ARBs,
based on affinity to a training instance. They create an established memory set for classification.
This is achieved through a resource allocation mechanism.
An important problem of most current artificial immune classifiers is the antibody population,
which is the classifier, is generated randomly. Clonal selection classification algorithm (CSCA)
uses antibody pruning to remove bad antibodies with low fitness scores, to improve classification
performance [25]. But, there are high affinity antibodies in the antibody population in CSCA,
which decreases fitness scores of high quality antibodies and results in high quality antibodies
being pruned. Also, there are no mechanisms to guide antibody generation, which may affect
classification performance negatively.
4. EXPERIMENTAL RESULTS
In this investigation, Wavelet and GLCM are used for feature extraction after. Features are
selected by Correlation Feature Selection (CFS), Information Gain (IG), proposed BFO and
hybrid BFO.
Table 2 Classification Accuracy
Techniques
AIS
classifier
Ripper OneR
Proposed
AIS classifier
Feature selection using CFS 89.2 84.53 85.47 93.13
Feature selection using IG 94.13 86.87 87.6 94.87
Feature selection using proposed
CFS -BFO
95.13 87.87 89.2 96.07
CFS -HBFO
95.93 89.13 91.13 97.07

21
The experimental results with the different classifiers and various feature selection methods are
obtained as above.
Figure 1 Classification Accuracy
The Ripper classifier with HBFO improved the classification accuracy by 5.2977% when
compared with the Ripper with using CFS method. The proposed AIS classifier with HBFO
improved the classification accuracy by 4.143% when compared with the proposed AIS classifier
with using CFS method.
Table 3 Precision
Techniques
AIS
classifier
Ripper OneR
Proposed
AIS
classifier
Feature selection using
proposed CFS -BFO
0.9517 0.8824 0.8918 0.9609
proposed CFS -HBFO
0.9596 0.893 0.9119 0.971
Precision is a measure of classifiers exactness. It is the number of positive predictions divided by
the total number of positive class values predicted. The precision for the different techniques used
is depicted in the above table.

International Journal on Soft Computing (IJSC)
The Ripper with HBFO improved the
using CFS method. The proposed
when compared with the proposed AIS classifier
Techniques
Feature selection using CFS
Feature selection using IG
CFS -BFO
CFS -HBFO
Recall is the measure of classifiers completeness. It is the number of True Positives divided by
the number of True Positives and the number of False Negatives. The table above depicts the
recall values obtained for the different techniques applied in this research.
0.78
0.8
0.82
0.84
0.86
0.88
0.9
0.92
0.94
0.96
0.98
1
Feature selection
using CFS
AIS classifier
Figure 2 Precision
The Ripper with HBFO improved the precision by 5.4645% when compared with the Ripper with
The proposed AIS classifier with HBFO improved the precision
proposed AIS classifier with using CFS method.
Table 4 Recall
AIS
classifier
Ripper OneR
Proposed
AIS
classifier
0.9517 0.8824 0.8918 0.9609
selection using proposed
0.9596 0.893 0.9119 0.971
recall values obtained for the different techniques applied in this research.
Feature selection Feature selection
using IG
Feature selection
using proposed CFS
-BFO
Feature selection
using proposed CFS
-HBFO
Techniques
AIS classifier Ripper OneR Proposed AIS classifier
22
% when compared with the Ripper with
by 4.1417%
Feature selection
using proposed CFS
HBFO
Proposed AIS classifier

International Journal on Soft Computing (IJSC)
The Ripper with HBFO improved the recall by 5.2977% when compared with the Ripper with
using CFS method. The proposed AIS classifier
compared with the proposed AIS classifier with using CFS method.
Techniques
Feature selection using CFS
Feature selection using IG
proposed CFS -BFO
proposed CFS -HBFO
0.78
0.8
0.82
0.84
0.86
0.88
0.9
0.92
0.94
0.96
0.98
1
CFS
AIS classifier
Figure 3 Recall
using CFS method. The proposed AIS classifier with HBFO improved the recall by 4.143% when
compared with the proposed AIS classifier with using CFS method.
Table 5 F Measure
AIS
classifier
Ripper OneR
Proposed
AIS classifier
0.9515 0.8805 0.8919 0.9608
0.9594 0.8921 0.9116 0.9708
IG
proposed CFS -BFO
proposed CFS
Techniques
Ripper OneR Proposed AIS classifier
23
with HBFO improved the recall by 4.143% when
proposed CFS -HBFO
Proposed AIS classifier

24
F-measure is the measure of a test’s accuracy. It is interpreted as the average mean of Precision
and Recall. F-measure reaches its best value at 1 and worst at 0. Here, the highest F-measure is
obtained with the proposed AIS classifier.
Figure 4 F Measure
The Ripper with HBFO improved the f measure by 5.3755% when compared with the Ripper
with using CFS method. The proposed AIS classifier with HBFO improved the f measure by
4.1426% when compared with the proposed AIS classifier with using CFS method.
5. CONCLUSION
Medical images classification in different applications is basic in medical image retrieval
systems. Bio-medical devices use imaging techniques like Computed Tomography (CT), and
Magnetic Resonance Imaging (MRI), which are important diagnostic factors. Due to medical
image data’s high variability, correct classification models must be used. CT modality is applied
to clinical diagnosis to help radiologists detect/locate pathological changes accurately. This paper
used an AIS classifier with hybrid BFO for medical images classification. Results proved that the
new method improved performance over other classifiers and feature selection methods.

25
REFERENCES
[1] Keysers, D., Gollan, C., & Ney, H. (2004), “Classification of medical images using non-linear
distortion models”, In BildverarbeitungfürdieMedizin pp. 366-370, Springer Berlin Heidelberg.
[2] Dinh, T. A., Silander, T., Su, B., Gong, T., Pang, B. C., Lim, C. T.,& Leong, T. Y. (2013),
“Unsupervised medical image classification by combining case-based classifiers”, In MedInfo,
pp. 739-743.
[3] Ramteke, R. J., &KhachaneMonali, Y, (2012), “Automatic Medical Image Classification and
Abnormality Detection Using K-Nearest Neighbour”, International Journal of Advanced
Computer Research, 2(4).
[4] Uwimana, E., & Ruiz, M. E. (2008, September), “Automatic classification of medical images
for Content Based Image Retrieval Systems (CBIR)”, In Proceedings of the Human Factors
and Ergonomics Society Annual Meeting(Vol. 52, No. 12, pp. 788-792, SAGE Publications.
[5] Foschi, P. G., Kolippakkam, D., Liu, H., &Mandvikar, A. (2002, October), “ Feature
Extraction for Image Mining” ,In Multimedia Information Systems, pp. 103-109.
[6] Rathi, V. P., & Palani, S. (2012), “Brain tumor MRI image classification with feature selection
and extraction using linear discriminant analysis”, arXiv preprint arXiv:1208.2128.
[7] Baaziz, N., Abahmane, O., & Missaoui, R. (2010), “Texture feature extraction in the spatial-
frequency domain for content-based image retrieval”, arXiv preprint arXiv:1012.5208.
[8] Khan, M., & Quadri, S. M. K, “Effects of Using Filter Based Feature Selection on the
Performance of Machine Learners Using Different Datasets”, Our Indexing at International
Level, 597.
[9] Lavanya, D., & Rani, D. K. U. (2011), “Analysis of feature selection with classification: Breast
cancer datasets”, Indian Journal of Computer Science and Engineering (IJCSE), 2(5), pp 756-
763.
[10] Jakhar, R., Kaur, N., & Singh, R. (2011), “ Face Recognition Using Bacteria Foraging
Optimization-Based Selected Features.”, International Journal of Advanced Computer Science
and Applications.
[11] AlZubi, S., Sharif, M. S., Islam, N., & Abbod, M. (2011, May), “ Multi-resolution analysis
using curvelet and wavelet transforms for medical imaging”, In Medical Measurements and
Applications Proceedings (MeMeA), pp. 188-191, IEEE.
[12] Dai, W., Tan, L., & Yang, A. (2013, May), “Adaptive fusion algorithm of CT and MRI
medical images based on NSCT”, 25th Chinese Control and Decision Conference (CCDC), pp.
3797-3801, IEEE.
[13] Sawall, S., Kuntz, J., Socher, M., Bartling, S., Knaup, M., & Kachelrieß, M. (2012, October),
“Cardiac perfusion imaging of small rodents using cone-beam micro-CT”, In Nuclear Science
Symposium and Medical Imaging Conference (NSS/MIC), pp. 2425-2428, IEEE.
[14] Humpire-Mamani, G., Traina, A. J. M., & Traina, C. (2012, September), “ FSCoMS: Feature
Selection of Medical Images Based on Compactness Measure from Scatterplots”, Second
International Conference on Healthcare Informatics, Imaging and Systems Biology (HISB),
pp. 86-95, IEEE.
[15] Sohail, A. S. M., Bhattacharya, P., Mudur, S. P., & Krishnamurthy, S. (2011, March),
“Selection of optimal texture descriptors for retrieving ultrasound medical images”,
International Symposium on Biomedical Imaging: From Nano to Macro, pp. 10-16, IEEE.
[16] Rathore, S.; Iftikhar, M.A.; Hussain, M.; Jalil, A., (2013), "Classification of colon biopsy
images based on novel structural features, " IEEE 9th International Conference on Emerging
Technologies (ICET), , vol., no., pp.1-6
[17] Lee, W. J., Kim, D. S., Kang, S. R., Woo, S. Y., & Yi, W. J. (2014, August), “ Material
classification of multi-energy CT images using multiple discriminant analysis”, 36th Annual
International Conference of the IEEE In Engineering in Medicine and Biology Society
(EMBC), pp. 1103-1106, IEEE.

26
[18] Kubota, Y., Aoki, K., Nagahashi, H., & Minohara, S. I. (2009, October),” Pulmonary motion
tracking from 4D-CT images using a 3D-KLT tracker”, In Nuclear Science Symposium
Conference Record (NSS/MIC), pp. 3475-3479, IEEE.
[19] Pham, T. D., Eisenblatter, U., Golledge, J., Baune, B. T., & Berger, K. (2009, November),
“Segmentation of medical images using geo-theoretic distance matrix in fuzzy clustering”,
16th IEEE International Conference on Image Processing (ICIP), pp. 3369-3372, IEEE.
[20] Ghadiri, H., Shiran, M. B., Ay, M. R., Soltanian-Zadeh, H., Rahmim, A., & Zaidi, H. (2011,
October), “A novel energy mapping approach in CT-based attenuation correction of PET data
using multi-energy CT imaging”, In Nuclear Science Symposium and Medical Imaging
Conference (NSS/MIC), pp. 2510-251. IEEE.
[21] Krishn, A., Bhateja, V., & Sahu, A. (2014, September), “Medical image fusion using
combination of PCA and wavelet analysis”, International Conference in Advances in
Computing, Communications and Informatics (ICACCI, 2014), pp. 986-991 IEEE.
[22] Uozumi, Y., Nagamune, K., Nakano, N., Nagai, K., Araki, D, Hosliino, Y. & Kurosaka, M.
(2014, August), “Automated extraction of tibial eminence in CT image using shape matching”,
In World Automation Congress (WAC), pp. 336-339 IEEE.
[23] Ye, L., Xing, Y. K., & Xiang, W. P. (2013), “ An Artificial Immune Classification Algorithm
based on Particle Swarm Optimization”, Journal of Computers, 8(3), 772-778.
[24] Dudek, G. (2012), “An artificial immune system for classification with local feature selection”,
Evolutionary Computation, IEEE Transactions on 16(6), 847-860.
[25] Deng, Z. L., Tan, G. Z., He, P., & Ye, J. X. (2013), “A decision hyper plane heuristic based
artificial immune network classification algorithm”, Journal of Central South University, 20,
1852-1860.
[26] Maes, F., Vandermeulen, D., & Suetens, P., (2003), “Medical image registration using mutual
information”, Proceedings of the IEEE, 91(10), 1699-1722.
[27] Sahoo, A., & Chandra, S. , (2014), “Meta-heuristic approaches for active contour model based
medical image segmentation”, International Journal of Advances in Soft Computing and Its
Applications, 6(2).
[28] Narendhar, S., &Amudha, T. , (2012), “A Hybrid Bacterial Foraging Algorithm For Solving
Job Shop Scheduling Problems”, arXiv preprint arXiv: 1211.4971.
[29] Biswas, A., Dasgupta, S., Das, S., & Abraham, A. (2007), “A synergy of differential evolution
and bacterial foraging optimization for global optimization”, Neural Network World, 17(6),
607.
[30] Chen, H., Zhu, Y., & Hu, K. (2009), “Cooperative bacterial foraging optimization”, Discrete
Dynamics in Nature and Society.
[31] Abharian, A., &Shakeri, E. (2011), “Bacteria Foraging Optimization Robust-RED for
AQM/TCP Network”, International Journal of Modeling and Optimization, 1-49.
[32] Chitra D, Nasira G.M, “Wrapper Based Feature Selection for CT Image”, ICTACT journals
in/paper/IJIVP_Paper_7, pp: 1096-1103 DOI: 10.21917/ijivp.2015.0160.
BIOGRAPHY
D. Chitra is Assistant Professor in the Department of Computer Science, Government Arts College
(Autonomous),Salem-7, Tamilnadu, India. Her research interests are Data Mining, Algorithms, Soft
Computing etc.
Dr. M. Karthikeyan is an Assistant Professor in the Department of Computer Science, Government Arts
College (Autonomous), Salem-7, Tamilnadu, India. His research interests are Mobile computing, Data
mining, Optimization Techniques.

BFO – AIS: A Framework for Medical Image Classification Using Soft Computing Techniques

More Related Content

What's hot (20)

Similar to BFO – AIS: A Framework for Medical Image Classification Using Soft Computing Techniques (20)

Recently uploaded (20)

BFO – AIS: A Framework for Medical Image Classification Using Soft Computing Techniques