Wednesday , June 20 2018

Medical Fusion Components for a Web Dedicated Application

Department of Communications, Technical University of Cluj-Napoca,
Cluj-Napoca, Romania

Loreta-A. SUTA
Department of Communications, Technical University of Cluj-Napoca
Cluj-Napoca, Romania

Mircea – F. VAIDA
Department of Communications, Technical University of Cluj-Napoca
Cluj-Napoca, Romania

Department of Oral Radiology, University of Medicine and Pharmacy Iuliu Hatieganu
Cluj-Napoca, Romania

Abstract: A web dedicated application is very useful for assisted diagnosis in healthcare domain. Medical images acquired with different medical image modalities contain important diagnostic information. The combination of complementary data from different images can lead to more important information. The fusion process allows combination of salient feature of these images. In this paper we present methods for medical image fusion, based on discrete wavelet transform. These methods are implemented in a web distributed application, using Java technology. The web dedicated application will integrate components able to be discovered in a ubiquitous computing system. The components are developed in dedicated Java packages that allow physicians to realize a fusion from a remote place. Considering radiology images we approve the functionality of the application by calculating significant quantitative parameters for fusion process evaluation.

Keywords: Image fusion, wavelet transform, distributed application, multi-resolution decomposition

>>Full text
Ligia D. CHIOREAN,  Loreta-A. SUTA, Mircea – F. VAIDA, Mihaela HEDESIU, Medical Fusion Components for a Web Dedicated Application, Studies in Informatics and Control, ISSN 1220-1766, vol. 19 (4), pp. 435-444, 2010.

1. Introduction

In recent years, medical imaging became very useful for assisted diagnosis process. There are many medical image modalities that give important information about different diseases. These equipments are accompanied by software applications which offer image processing facilities. Many of these modalities offer complementary information. For example, CT (Computer Tomography) provides best information about denser tissue and MRI (Magnetic Resonance Image) offers better information on soft tissue, [4]. These complementarities have led to the idea that by combining images acquired with different medical devices can be obtained a new image that can offer more useful information. In this way, the result image can be very useful in the diagnosis process, and that is the main motif why image fusion has become an important research field.

The fusion techniques can be classified in two main categories: for spatial domain and for transform domain. The reason of passing to the transform domain is the fact that salience characteristics of the image are observed more easier than in spatial domain, and this is important to recognize informational underlayer of the image for fusing them comparing with the independent “combination” of the pixels. Fusion based on transforms has some advantages over other simple methods, like: energy compaction, larger SNR (Signal-to-Noise Ratio), reduced features, etc. The transform coefficients are representative for image pixels.

In a few past years, researchers developed different medical applications including image fusion. All these applications offer local solutions for the image fusion.

We propose a web architecture based on a web server for medical purposes. Remote fusion facilities offer many advantages in managing images obtained with specific medical devices in different locations. The implemented application features different fusion techniques to allow medical image processing in order to facilitate a better and faster diagnosis. We chose wavelet based fusion methods, namely: DWT (Discrete Wavelet Transform), UDWT (UnDecimated Wavelet Transform) and SIDWT (Shift Invariant Discrete Wavelet Transform). These techniques have been structured in software packages that allow future development depending on the clients’ configuration (desktop, mobile, etc.) devices.


  1. AIAZZI, B., S. BARONTI, M. SELVA, Image Fusion Through Multiresolution Oversampled Decompositions, in T. Stathaki, Ed., Image fusion, Algorithms and applications, Elsevier Academic Press, UK, 2008, pp. 27-66.
  2. BEYERER, J., M. HEIZMANN, J. SANDER, I. GHETA, Bayesian Methods for Image Fusion, in T. Stathaki, Ed., Image fusion, Algorithms and applications, Elsevier Academic Press, UK, 2008, pp. 157-192.
  3. BURT, P. J., R. J. KOLCZYNSKI, Enhanced Image Capture through Fusion, Proceedings of the Fourth International Conference on Computer Vision, May 1993, Berlin, pp. 173-182.
  4. GUIHONG, Q., Z. DALI, Y. PINGFAN, Medical Image Fusion by Wavelet Transform Modulus Maxima, Optics Express, vol.9, no. 4, 2001, pp. 184-190.
  5. HILL, P., N. CANAGARAJAH, D. BULL, Image Fusion using Complex Wavelets, In Proceeding of the 13th British Machine Vision Conference BMVC 2002, September 2002, Cardiff, pp. 487-496.
  6. NIKOLOV, S., P. HILL, D. BULL, N. CANAGARAJAH, Wavelets for Image Fusion, in S. Petrosian and F. Meyer, Ed., Wavelets in signal and image analysis, Computational Imaging and Vision Series, Kluwer Academic Publishers, Dordrecht, The Netherlands, 2001, pp. 213-244.
  7. OTAZU, X., Theory and Implementation of Image Fusion Methods Based on the a Trous Algorithm, in T. Stathaki, Ed., Image fusion, Algorithms and applications, Elsevier Academic Press, UK, 2008, pp. 139-155.
  8. PIELLA, G., H. HEIJMANS, A New Quality Metric for Image Fusion, in Proceeding of International Conference on Image Processing, vol. 3, issue 2, September 2003, pp. 173-176.
  9. POP, F. C., M. F. VAIDA, M. CREMENE, M. RIVEILL, C. PUIA, Dynamic Service Composition for Plug-and-Play Medical Devices, International Conference on Advancements of Medicine and Health Care through Technology, IFMBE Proceedings, Meditech09, vol. 26, September 2009, pp. 57-62.
  10. ROCKINGER, O., Image Sequence Fusion Using a Shift Invariant Wavelet Transform, in Proceedings of the IEEE International Conference on Image Processing, vol.3, 1997, pp. 288-291.
  11. SASIKALA, M., N. KUMARAVEL, A Comparative Analysis of Feature Based Image Fusion Methods, Information Technology Journal, Asian Network for Scientific Information, vol. 6, issue 8, 2007, pp. 1124-1230.
  12. WANG, Q., Y. SHEN, J. JIN, Performance Evaluation of Image Fusion Techniques, in T. Stathaki, Ed., Image fusion, Algorithms and applications, Elsevier Academic Press, UK, 2008, pp. 469-492.
  13. WANK, Z., A. C. BOVIK, H. R. SHEIKH, E. P. SIMONCELLI, Image Quality Assessment: From Error Visibility to Structural Similarity, In Proceeding of Transaction on Image Processing vol. 3, issue 4, April 2004, pp. 600-612.