Open Access

A genetic optimized neural network for image retrieval in telemedicine

EURASIP Journal on Image and Video Processing20142014:9

https://doi.org/10.1186/1687-5281-2014-9

Received: 1 March 2012

Accepted: 27 January 2014

Published: 11 February 2014

Abstract

Telemedicine integrates information and communication technologies in providing clinical services to health professionals in different places. Medical images are required to be transmitted for diagnosis and opinion as part of the telemedicine process. Thus, telemedicine challenges include limited bandwidth and large amount of diagnostic data. Content-based image retrieval is used in retrieving relevant images from the database, and image compression addresses the problem of limited bandwidth. This paper proposes a novel method to enable telemedicine using soft computing approaches. In the present study, images are compressed to minimize bandwidth utilization, and compressed images similar to the query medical image are retrieved using a novel feature extraction and a genetic optimized classifier. The effectiveness of compressed image retrieval on magnetic resonance scan images of stroke patients is presented in this study.

Keywords

TelemedicineFeature extractionImage retrievalClassificationNeural network

1. Introduction

Telemedicine integrates information and communication technologies in providing clinical services to health professionals in different places. It provides expert-based healthcare services to exchange information required for diagnosis, consultation, and referential purposes. Telemedicine not only includes diagnostic, remote monitoring, and interactive services but also drug evaluation, medical research, and training. People living in remote areas and isolated regions find telemedicine very helpful. It is also useful in critical care and emergency situations. The main challenges faced by telemedicine are limited bandwidth, large volume of data, and availability of expert opinion[1, 2]. With the progress of medical technologies, obtaining digital images of human anatomy through X-rays, magnetic resonance imaging (MRI), electrocardiography (ECG), and computed tomography (CT) has become a norm. The digital images are stored in databases and can be easily accessed through internet for training and diagnostic purposes. The difficulty of getting an expert either online or offline to advice on diagnosis based on the medical image is addressed by the use of content-based image retrieval (CBIR). CBIR can be used to retrieve diagnostic cases similar to the query medical image from the medical database[3, 4]. CBIR is of significance in medical image retrieval as the medical databases contain a huge amount of data in visual form, conventional method of retrieval based on semantics is not feasible, and image content is more versatile than the text. CBIR is increasingly applied in medical image applications; many CBIR algorithms, architectures, and systems are reviewed in the literature[5, 6].

Though medical image retrieval has been successfully implemented in nontelemedicine applications, the limited bandwidth and large amount of diagnostic data required to be transmitted are two of the major issues that need to be addressed in using CBIR in telemedicine. Transmitting compressed medical images can be an option for physical diagnosis by an expert; however, automated retrieval of compressed medical images has not been extensively studied. Image compression reduces data required to represent an image; it reduces the storage and transmission requirements. Redundancies in the image are removed during the compression process to yield a compact representation of the image. Lossless compression techniques are used when the original image is to be perfectly recovered, and lossy compression techniques are used when a high compression rate is required with minor loss in details. Limited techniques for compressed medical image retrieval have been proposed in[79]. Compression techniques using lossless methods have been studied in[10, 11] where attempts have been made to propose encoding techniques that showed improvements over existing techniques including Huffman coding. As image transmission is part of telemedicine, wavelet-based coding has been found to be robust for compressed image transmission and has proved to be efficient at low bit rates[12].

This work focuses on compressed medical image retrieval. CBIR has been successfully applied in classifying MRI brain images. Studies in[1315] show feature extraction techniques and classification algorithm for stroke identification and classification in uncompressed images. Cocosco et al.[16] proposed techniques for feature extraction which showed robustness against variability in MRI image quality. Lahmiri and Boukadoum[17] proposed a feature extraction technique using discrete wavelet transform (DWT) and obtained good classification accuracies using a probabilistic neural network (PNN) algorithm. El-dahshan et al.[18] presented techniques for feature reduction using principal component analysis (PCA) of the features extracted using DWT. Using k-nearest neighbor (k-NN) and feedforward back propagation-artificial neural network (FP-ANN) classifications, accuracies of 95.6% and 98.6% were obtained. Bagher-Ebadian et al.[19] proposed a method to study ischemic stroke using ANN. The method identifies the extent of ischemic lesion recovery. Experiments using new datasets showed that the prediction made by ANN had an excellent overall performance and was very well correlated to the 3-month ischemic lesion on the T2-weighted image. Stroke classification using various feature techniques and classifiers has been proposed in[2022].

Though good classification accuracy has been demonstrated in the literature, a detailed study of compressed MRI stroke image retrieval which is crucial for telemedicine has not been studied extensively to the best of our knowledge. This work focuses on compressed image retrieval for the classification of stroke and nonstroke MRI images. The proposed method is subdivided to the following techniques comprising compression, feature extraction, and classification. Haar wavelet for decomposition and Huffman encoding have been used to compress the images. The main contributions of this study are listed as

  • A novel feature extraction technique using the proposed image retrieval-specific fast Fourier transform (IRS-FFT)

  • An improved neural network classifier, genetic optimized parallel neural network (GOP-parallel NN).

2. Proposed feature extraction

The proposed IRS-FFT for feature extraction can be derived as given in[2325]. Feature extraction was performed on diffusion weighted imaging (DWI) scan images showing stroke.

Fast Fourier transform has the tendency to produce large values which may introduce an artifact. In order to overcome the issue of artifact, a normalization procedure is proposed and integrated with Fast Fourier transform. The proposed normalization model is shown in Equations 1 and 2.

Consider a matrix U of dimension N × N with its (m, n)th element defined as in Equations 1 and 2:
u m , n u N mn = e - j 2 Π / N mn
(1)
where (m, n = 0, 1, 2,…, N - 1).
u N 1 N e - j 2 Π / N .
(2)
The IRS-FFT can be defined as in Equation 3:
X irs n = - α n 1 2 Π σ 2 e - n - μ 2 2 σ 2 X n ,
(3)
where X[n] and μ is given as in Equations 4 and 5:
X n = u 0 , 0 u 0 , 1 u 0 , N - 1 u 1 , 0 u 1 , 1 u 1 , N - 1 .... u N - 1 , 0 u N - 1 , 1 u N - 1 , N - 1 x 0 x 1 x N - 1
(4)
and
μ = 1 N 0 n - 1 X n .
(5)
Sample images after feature extraction is given in Figure 1.
Figure 1

Sample Images after feature extraction.

The proposed feature extraction technique produces a large number of feature vectors. Information gain (IG) is used to reduce the feature vectors by selecting the top ranked features. The information gain that has to be computed for an attribute A whose class attribute B is given by the conditional entropy of B given A, H(B|A) is
I B ; A = H B - H B | A .
The conditional entropy of B given A is
H B | A = - i = 1 j = 1 P A = a j H B | A = a j .

3. Proposed genetic optimized parallel MLP neural network

Neural network are modeled similar to the neurons in the brain. The proposed neural network genetic optimized parallel multilayer perceptron neural network (GOP-MLP NN) is an extension of the existing multilayer perceptron (MLP) model. Unlike the MLP, full interconnectivity between the layers is not achieved. The network processing the input signals uses several parallel MLPs as it reduces the number of weights required, and hence, the training time for the network is reduced over the traditional MLP network. The block diagram of the proposed GOP MLP neural network is shown in Figure 2.
Figure 2

Block diagram of the proposed GOP MLP neural network.

It could be observed from Figure 2 that the proposed neural network consists of two parallel MLPs with each performing different subtasks. Each MLP consists of two layers. The first submodule MLP uses the first 50% of the attributes, and the remaining are used by the second submodule. The number of weights is reduced by 50% using this process.

A genetic optimization function is introduced in the second hidden layer of the proposed network to find the best learning rule and momentum. The GOP-MLP NN proposed in this paper uses the criteria specified in Table 1.
Table 1

Parameters for the proposed GOP-MLP NN

Parameter

Value/description

Output neuron

2

Number of hidden layer

2

Number of processing elements

 

Upper

4

Lower

4

Transfer function of hidden layer

 

Upper

tan h

Lower

Sigmoid

Learning rule of hidden layer

Momentum with genetic optimization

Step size

0.1

Momentum

0.7

Transfer function of output layer

tan h

Learning rule of output layer

Momentum

Step size

0.1

Momentum

0.7

The learning capability and the generalization capability of the proposed neural network model are calculated using the performance measure of the mean square error (MSE). The MSE is given as
MSE = j = 0 E i = 0 N o ij - y ij 2 EN ,
(6)
where E is the number of processing elements, N is the number of exemplars, o is the desired output for exemplar i at processing element j, y is the obtained output for exemplar i at processing element j; tan h will squash the range of each neuron to between -1 and 1, and its activation function is given as
tan h i = e i - e - i e i + e - i ,
(7)

where i is the sum of the input patterns.

Genetic optimization is used in the hidden layer of the network. Genetic algorithms (GA) are a class of optimization algorithms inspired by evolution. The steps in GA include reproduction, crossover, and mutation to evolve better solutions. Generally, the solutions available are evaluated using fitness function. Based on the fitness function, the evolutionary process is iterated till an ideal solution is reached or a specific number of generations has occurred. The proposed neural network architecture is optimized for ideal momentum value using GA with the following parameters specified in Table 2.
Table 2

Genetic optimization parameters

Parameter

Value/description

Number of iterations

500

Population size

10

Maximum generations

100

Momentum optimization lower bound value

0.05

Momentum optimization upper bound value

0.95

Encoder mechanism

Roulette

Crossover type

One point

Crossover probability

0.75

Mutation

Uniform

Mutation probability

0.02

The flow diagram of the proposed GOP MLP neural network is presented in Figure 3.
Figure 3

Flow diagram of the proposed GOP MLP neural network.

The genetic algorithm iterates and evolves the population, forming a new population at each step. The genetic algorithm iteration consists of the following steps:
  1. 1.

    Selection. The first step consists of selecting individuals/chromosomes for reproduction. Fitness value plays an important role in this selection and is completed randomly. Individuals with better fitness value are chosen more often for reproduction than poor ones.

     
  2. 2.

    Reproduction. Offspring are produced by the selected individuals. Both recombination and mutation techniques are used in generating new chromosomes.

     
  3. 3.

    Evaluation. The fitness of the new chromosomes is then evaluated.

     
  4. 4.

    Replacement. During the last step, individuals from the old population are removed and replaced by the new ones.

     
In the present design, the MSE is evaluated as the fitness function with a total of 100 generations. The MSE was found to decrease, and no significant change was observed as presented in Figure 4.
Figure 4

Best fitness versus generation obtained.

4. Experimental results and discussions

In order to test the effectiveness of our approach, a set of 52 DWI scan images consisting of 25 positive stroke patients was used. These images were provided by the MRI Department of Vijaya Health Centre in India. The MRI images were reviewed by an expert in the radiology department for a precise classification of patients with positive stroke. Figure 5 shows some of the stroke images used in the present study. Experiments were performed on the uncompressed and the compressed images to show the effectiveness of compressed images for image retrieval.
Figure 5

Sample DWI images of stroke patients.

4.1 Experiment 1 for uncompressed images

The following are the steps in experiment 1 for uncompressed images:
  1. 1.

    Preprocessing of the image using a median filter for noise removal

     
  2. 2.

    Extracting of features using IRS-FFT

     
  3. 3.

    Feature reduction using Information gain

     
  4. 4.

    Classification using the proposed genetic optimized parallel neural network for 20, 40, 60, 80, and 100 features

     
  5. 5.

    Performance evaluation of the proposed system with the MLP neural network.

     

4.2 Experiment 2 for compressed images

The following are the steps in experiment 2 for compressed images:
  1. 1.

    Preprocessing of the image using a median filter

     
  2. 2.

    Compression of images using Haar wavelet with Huffman encoding

     
  3. 3.

    Extracting of features using IRS-FFT

     
  4. 4.

    Feature reduction using information gain

     
  5. 5.

    Classification using the proposed genetic optimized parallel neural network for 20, 40, 60, 80, and 100 attributes

     
  6. 6.

    Performance evaluation of the proposed system with MLP neural network.

     
It is evident in Table 3 that the proposed GOP NN shows a higher degree of precision and classification accuracy compared to the MLP NN. It is observed that classification accuracy decreases when the number of features extracted is 60.
Table 3

Classification parameters for uncompressed and compressed images

Number of features

Parameters

Classifiers

Uncompressed

Compressed

   

Feature extraction using FFT

Feature extraction using the proposed IRS-FFT

Feature extraction using FFT

Feature extraction using proposed IRS-FFT

20

Classification accuracy

MLP NN

88.46

92.31

90.38

92.31

GOP NN

92.31

94.23

94.23

98.08

Precision

MLP NN

0.92

0.96

0.86

1

GOP NN

0.96

1

1

1

Recall

MLP NN

0.85

0.89

1

0.86

GOP NN

0.89

0.89

0.89

0.96

40

Classification accuracy

MLP NN

90.38

94.23

92.31

94.23

GOP NN

94.23

96.15

94.23

98.08

Precision

MLP NN

0.96

0.96

1

1

GOP NN

1

1

1

1

Recall

MLP NN

0.86

0.92

0.86

0.89

GOP NN

0.89

0.93

0.89

0.96

60

Classification accuracy

MLP NN

88.46

90.38

92.31

94.23

GOP NN

92.31

94.23

92.31

98.08

Precision

MLP NN

0.92

0.96

1

1

GOP NN

1

1

1

1

Recall

MLP NN

0.85

0.86

0.86

0.89

GOP NN

0.86

0.89

0.86

0.96

80

Classification accuracy

MLP NN

90.38

94.23

92.31

94.23

GOP NN

94.23

96.15

98.08

98.08

Precision

MLP NN

0.96

0.96

1

1

GOP NN

1

1

1

1

Recall

MLP NN

0.86

0.92

0.86

0.89

GOP NN

0.89

0.93

0.96

0.96

100

Classification accuracy

MLP NN

90.38

94.23

92.31

94.23

GOP NN

94.23

96.15

98.08

98.08

Precision

MLP NN

0.96

0.96

1

1

GOP NN

1

1

1

1

Recall

MLP NN

0.86

0.92

0.86

0.89

  

GOP NN

0.89

0.93

0.96

0.96

This seems to be a minor abnormality which could be associated with the data used as 40 and 80 features show linear approach. The classification accuracy, precision, and recall are computed as
Classification accuracy = Number of correctly classified samples Total number of tested samples × 100 Precision = Number of relevent images retrived Total number of images retrieved Recall = Number of relevent images retrived Total number of relevent images in the database .

Further, the accuracy of the proposed feature extraction technique is higher with a minimum of 40 feature vectors.

The graphs depicted in Figure 6 shows the classification accuracy of the proposed and existing MLP neural network using conventional FFT and the proposed IRS-FFT for both compressed and uncompressed images. It is seen that the classification accuracy of the compressed images are better than that of the uncompressed images, thereby utilizing the bandwidth effectively and justifying its applicability in a telemedicine scenario.
Figure 6

Classification accuracy. (a) Classification accuracy for MLP NN using FFT and IRS-FFT on uncompressed images. (b) Classification accuracy for GOP NN using FFT and IRS-FFT on uncompressed images. (c) Classification accuracy for MLP NN using FFT and IRS-FFT on compressed images. (d) Classification accuracy for GOP NN using FFT and IRS-FFT on compressed images. (e) Classification accuracy of the proposed GOP NN on uncompressed and compressed images. (f) Classification accuracy of the proposed MLP on uncompressed and compressed images.

5. Conclusions

In this paper, a modified IRS-FFT-based feature extraction technique was proposed. The basic idea of the proposed algorithm is to squash the values of FFT, thereby reducing noise and improving the classification accuracy. A novel neural network with parallel perceptrons to reduce the weights along with genetic optimization to find the ideal momentum was proposed. A two-class problem on MRI stroke images was used in evaluating the proposed feature extraction and classifier. Experiments were conducted using uncompressed and compressed images. IG was used to rank the extracted features, and the experiments were conducted with varying numbers of features. Multilayer perceptron neural network and the proposed NN architecture with genetic optimization classified the images based on the selected features. Results show the improvement in precision for the compressed images using the proposed system.

The proposed CBIR system achieves satisfactory retrieval accuracy for compressed medical images. An average compression ratio of 35.84 was achieved which translates to proportional savings in bandwidth critical for a telemedicine application. Compressing images for transmission in limited bandwidth is a norm in telemedicine. The proposed method efficiently extracts features and retrieves relevant images from compressed images which will be a good support for telemedicine applications. The proposed method can further be investigated for various types of medical images and also validated for a multiclass problem.

Declarations

Acknowledgements

We would like to express our sincere gratitude to Dr. Ezhilarasu, Consultant Radiologist, Vijay Health Centre, India for providing us the database necessary to perform the experiments.

Authors’ Affiliations

(1)
Department of CSE, SKR Engineering College
(2)
Department of CSE, SVCE

References

  1. Singh S, Kumar V, Verma HK: Adaptive threshold block classification in medical image compression for teleradiology. Comput Biol Med 2007, 37: 811-819. 10.1016/j.compbiomed.2006.08.021View ArticleGoogle Scholar
  2. Bruckmann A, Uhl A: Selective Medical Image Compression techniques for telemedical and archiving application. Comput Biol Med 2000, 30(3):153-169. 10.1016/S0010-4825(00)00004-4View ArticleGoogle Scholar
  3. Lehmann TM, Schubert H, Keysers D, Kohnen M, Wein BB: The IRMA code for unique classification of medical image. Proceedings of the SPIE 5033 2003, 5033: 109-117. 10.1117/12.481942View ArticleGoogle Scholar
  4. Armato SG 3rd, McLennan G, McNitt-Gray MF, Meyer CR, Yankelevitz D, Aberle DR, Henschke CI, Hoffman EA, Kazerooni EA, MacMahon H, Reeves AP, Croft BY, Clarke LP, Lung Image Database Consortium Research Group: Lung image database consortium: developing a resource for the medical imaging research community. Radiology 2004, 232: 739-748. 10.1148/radiol.2323032035View ArticleGoogle Scholar
  5. Smeulders WM, Worring M, Santini S, Gupta A, Jain R: Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 2000, 22(12):1349-1380. 10.1109/34.895972View ArticleGoogle Scholar
  6. Muller H, Michoux N, Bandon D, Geissbuhler A: A review of content based image retrieval systems in medical applications—clinical benefits and future directions. Int J Med Inform 2004, 73: 1-23. 10.1016/j.ijmedinf.2003.11.024View ArticleGoogle Scholar
  7. Khapli VR, Bhalachandra AS: Performance evaluation of image retrieval using VQ for compressed and uncompressed images. In Proceedings of 2nd International Conference on Emerging Trends in Engineering and Technology ICETET, Nagpur, 16–18 Dec 2009. Piscataway: IEEE; 2009:885-888.View ArticleGoogle Scholar
  8. Liu MG, Jiang J, Hou CH: A combination of image retrieval and compression. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2002, 4: 13-17.Google Scholar
  9. Cerra D, Datcu M: Image retrieval using compression based techniques, in Proceedings of the International Conference on Source and Channel Coding (SCC), Siegen, 18–21 Jan 2010. IEEE: Piscataway; 2010:1-6.Google Scholar
  10. Pujar JH, Kadlaskar LM: A new lossless method of image compression and decompression using Huffman coding techniques. Journal of Theoretical and Applied Information Technology 15: 18-23.Google Scholar
  11. Yu Chen H, Chin-Chen C: A new lossless compression scheme based on Huffman coding scheme for image compression. Signal Processing, Image Communication 2000, 16(4):367-372. 10.1016/S0923-5965(99)00064-8View ArticleGoogle Scholar
  12. Vetterli M, Kovacevic J: Wavelets and Subband Coding. Englewood Cliffs NJ: Prentice Hall; 1995.MATHGoogle Scholar
  13. Shanthi D, Sahoo G, Saravanan N: Input feature selection using hybrid neuro-genetic approach in the diagnosis of stroke disease. IJCSNS 2008, 8(12):99-107.Google Scholar
  14. Othman MFB, Abdullah NB, Kamal NFB: MRI brain classification using support vector machine. In Proceedings of the 4th International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), Kuala Lumpur, 19–21 April 2011. Piscataway: IEEE; 2011:1-4.Google Scholar
  15. Dinh TA, Silander T, Tchoyoson Lim CC, Leong TY: A generative model based approach to retrieving ischemic stroke images. AMIA Annu Symp Proc 2011, 2011: 312-321.Google Scholar
  16. Cocosco CA, Zijdenbos AP, Evans AC: A fully automatic and robust brain MRI tissue classification method. Med Image Anal 2003, 7(4):513-527. 10.1016/S1361-8415(03)00037-9View ArticleGoogle Scholar
  17. Lahmiri S, Boukadoum M: Brain MRI classification using an ensemble system and LH and HL wavelet sub-bands features. In 2011 IEEE Third International Workshop on Computational Intelligence In Medical Imaging (CIMI), Paris, 11–15 April 2011. Piscataway: IEEE; 2011:1-7.Google Scholar
  18. El-dahshan E-SA, Salem E-BM, Younis TH: A hybrid technique for automatic MRI brain images classification. Studia Univ Babes Boloyai, Informatica 2009, 54: 55-67. 10.5038/1937-8602.54.1.11View ArticleGoogle Scholar
  19. Bagher-Ebadian H, Jafari-Khouzani K, Mitsias PD, Soltanian-Zadeh H, Chopp M, Ewing JR: Predicting final extent of ischemic infarction using an artificial neural network analysis of multiparametric MRI in patients with stroke. International Joint Conference on Neural Networks, Atlanta, 14–19 June 2009. Piscataway: IEEE; 2009:229-235.Google Scholar
  20. Kabir Y, Dojat M, Scherrer B, Garbay C, Forbes F: Multimodal MRI segmentation of ischemic stroke lesions. Conf Proc IEEE Eng Med Biol Soc 2007, 2007: 1595-1598.Google Scholar
  21. Gutierrez-Celaya JA, Leder R, Carrillo R, Hawayek A, Hernandez J, Sucar E: fMRI-based inverse analysis of stroke patients' motor functions. In 2011 Pan American Health Care Exchanges (PAHCE), Rio de Janiero, March 28 2011-April 1 2011. Piscataway: IEEE; 2011:1-6.Google Scholar
  22. Cherfa Y, Cherfa A, Kabir Y, Kassous S, Jaillard A, Dojat M, Garbay C: Segmentation of magnetic resonance brain images using edge and region cooperation characterization of stroke lesions. Int Arab J Inf Techn 2007, 4(3):281-288.Google Scholar
  23. Haar A: Zur Theorie der orthogonalen Funktionen systeme. Mathematics Annua 1910, 69(3):331-371. doi:10.1007/BF01456326 10.1007/BF01456326MATHMathSciNetView ArticleGoogle Scholar
  24. Talukder KH, Harada K: Haar wavelet based approach for image compression and quality assessment of compressed image. IAENG Int J Appl Math 36(1): IJAM_36_1_9Google Scholar
  25. Mohandass D, Janet J: Performance evaluation of compressed medical image classification for telemedicine. Eur J Sci Res 2011, 57: 286-292.Google Scholar

Copyright

© Divya et al.; licensee Springer. 2014

This article is published under license to BioMed Central Ltd. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.