Uses of Image Processing in Medical Report Generation | IEC College | Blog

Uses of Image Processing in Medical Report Generation


Uses of Image Processing in Medical Report Generation

By: SatyaPrakash, IEC Group
The medical images such as Positron Emission Tomography-Computed Tomography (PET-CT), Positron Emission Tomography (PET), Magnetic Resonance Imaging (MRI), Computerized Axial Tomography (CAT) and X-ray etc are used to retrieve complementary information from fusion of multimodal medical images. The goal of image fusion is to combine information from two or more images of a scene into a single composite image that is more informative and is more suitable for visual perception or computer processing. CT scanner is used to produce a detailed image of structures inside the human body and it is useful for obtaining images of soft Tissues, the Pelvis, Blood Vessels, Brain, Abdomen, Bones and Lungs. PET scanner is used to make a diagnosis or to get more data about a health condition or finding out how effective current treatment is. It also reveals how a part of the patient’s body is functioning. The MRI scanner is used to provide information about interactions with nearby atoms with chemical structure of organic molecules. It provides images from different angles and construct a three dimensional image. As we know that the key point of multi-focus image fusion is to decide which portion of each image are in better focus than their respective counterparts in the associated images and then combine these regions to construct a well-focused image by certain fusion rules, which play an important role in different fusion strategies. A large number of research works have been done in the area of image fusion. Garg et. al. proposed a multilevel medical image fusion using wavelet transform. In the proposed method regions are used as basic features for representation and retrieval of information among medical images and it uses a region competition based level set segmentation rather than wavelet transform because coefficients of wavelet transform does not preserve information about edges and boundaries. Also it avoids direct use of edge detection algorithms such as sobel or canny as they give much importance to the edges.
Feature level image fusion algorithms have been also implemented by Kor and Tiwary as well as by Calhoun and Adall. In a fusion of features like edges and boundaries of input images has been done that is extracted using wavelet transform maxima criterion. The proposed method gives better result for image fusion as image contrast, average information content and detail information of fused images are increased. Calhoun proposed a method that describes how function and structure are related in the same region of the brain and tried to retrieve complementary information by utilizing temporal EEG information and spatial fMRI (Functional Magnetic Resonance Imaging). Piella and Heijmans gave a multi-resolution fusion algorithm that combines pixel and region based fusion. In this method multi-resolution decompositions are used to represent the input images at different scales and multimodal segmentation is done to partition the input images at these scales.
Wavelet transforms and Independent Component analysis has been used for better multimodal medical image fusion. In, Multimodal medical image fusion using redundant Discrete Wavelet Transform has been proposed. This method presents a fusion algorithm that combine pairs of multispectral magnetic resonance imaging such as T1, T2 and Proton Density brain images. This algorithms utilizes different features of redundant discrete wavelet transform, mutual information based non-linear registration and entropy information to improve performance. This algorithm preserves edge and component information and provides improved performance compared to existing discrete wavelet transform based fusion algorithms. Cui et. al. used both wavelet transform and independent component analysis. In this method each of CT images were decomposed by discrete wavelet transform and then ICA (Independent Component Analysis) were used to analyze the wavelet coefficients in different level for acquiring independent component analysis. At last fusion of CT images is done that provides more detailed information about soft tissues such as muscles and blood vessels. This method is more efficient than weighted average and laplacian pyramid method in image fusion. Apart from the fusion of medical images there are a number of methodologies that deals with the fusion of one dimensional medical signal with one or two dimensional medical signals. Kannathal, et. al. has proposed data fusion of cardiovascular and hemodynamic signals for cardiac health diagnosis. In the proposed method, fusion of ECG, blood pressure, saturated oxygen content and respiratory data has been done for achieving improved clinical diagnosis of patients in cardiac care units. This method uses fuzzy logic based data fusion and provides a better diagnosis of cardiac diseases than by using ECG only. Correa et. al. presented a fusion algorithm that uses fMRI, sMRI and EEG data. These modalities record brain structure and function at different scales and fusing information from such complementary modalities promises to provide additional information across brain network and changes due to disease. This method uses multimodal canonical correlation analysis (mCCA).

[1]. Hong ZHENG, Dequen ZHENG Yanxianag HU, Sheng Li. Study on the Optimal Parameters of Image Fusion Based on Wavelet Transform[J]. Journal of Computational Information Systems (2010) 131-137.
[2]. Smt. G. Mamatha, L. Gayatri, “An Image Fusion Using Wavelet And Curvelet Transforms”, Global Journal of Advanced EngineeringTechnologies, Vol1, Issue-2, 2012, ISSN: 2277-6370.
[3]. R. K. Sharma, “Probabilistic Model-based Multi-sensor Image Fusion”, PhD thesis, Oregon 2001. Graduate Institute of Science and Technology, Portland, Oregon, 1999.
[4]. S. Li, J. T. Kwok, and Y. Wang, “Combination of images with diverse focuses using the spatial frequency,”Information Fusion 2, pp. 169–176,
[5]. S. Kor and U. Tiwary, “Feature level fusion of multimodal medical images in lifting wavelet transform domain” IEEE International Conference of the Engineering in Medicine and Biology Security, pp. 1479–1482, 2004.
[6]. A. H. Gunatilaka and B. A. Baertlein, “Feature-level and decision-level fusion of non coincidently sampled sensors for land mine detection” IEEE Transactions on Pattern Analysis and Machine Intelligence 23(6), pp. 577–589, 2001.
[7]. Daljit Kaur, P S Mann “Medical Image Fusion Using Gaussian Filter, Wavelet Transform and Curvelet Transform Filtering” International Journal of Engineering Science & Advanced Technology, Volume-4, Issue-3, 252-256 ISSN: 2250-3676.
[8]. MiloudChikr El-Mezouar, NasreddineTaleb, KidiyoKpalma, and Joseph Ronsin “An IHS-Based Fusion for Color Distortion Reduction and Vegetation Enhancement in IKONOS Imagery”, IEEE Transactions on Geo-science And Remote Sensing, vol. 49, No. 5, May 2011
[9]. Chetan K. Solanki, Narendra M. Patel, ―Pixel based and Wavelet based Image fusion Methods with their Comparative Study”, National Conference on Recent Trends in Engineering & Technology.
[10]. RudraPratap Singh Chauhan,RajivaDwivedi and Sandeep Negi “ Comparative Evaluation of DWT and DT-CWT for Image Fusion and De-noising”, International Journal of Applied Information Systems (IJAIS) – ISSN : 2249-0868 Foundation of Computer Science FCS, New York, USA Volume 4– No.2, September 2012
[11]. Ajeesh P Sasi, Dr. LathaParameswaran, “Image Fusion Technique using DT-CWT”, in proceeding of IEEE
[12]. KanisettyVenkataSwathi, CH.HimaBindu “Modified Approach of Multimodal Medical Image Using Daubechies Wavelet Transform” International Journal of Advanced Research in Computer and Communication Engineering Vol. 2, Issue 11, November 2013, ISSN (Print): 2319-5940.
[13]. J. Srikanth*, C.N Sujatha “Image Fusion Based on Wavelet Transform for Medical Diagnosis”, Int. Journal of Engineering Research and Applications, ISSN: 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.252-256.
[14]. Ch.Bhanusree, P. Aditya RatnaChowdary “A Novel Approach of image fusion MRI and CT image using Wavelet family”, International Journal of Application or Innovation in Engineering & Management (IJAIEM), Volume 2, Issue 8, August 2013, ISSN 2319 – 4847.
[15]. Kanaka Raju Penmetsa, V.G.PrasadNaraharisetti, N.Venkata RAO “An Image Fusion Technique For Colour Images Using Dual-Tree Complex Wavelet Transform”, International Journal of Engineering Research & Technology (IJERT) Vol. 1 Issue 8, October – 2012 ISSN: 2278-0181.
[16]. Patil Gaurav Jaywantrao, Shabahat Hasan, “Application of Image Fusion Using Wavelet Transform In Target Tracking System”, International Journal of Engineering Research & Technology (IJERT), ISSN: 2278-0181Vol. 1 Issue 8, October – 2012.
[17]. Pavithra C, Dr. S. Bhargavi, “Fusion of Two Images Based on Wavelet Transform”, International Journal of Innovative Research in Science, Engineering and Technology. 2, Issue 5, May 2013.
[18]. Singh, R., Khare, A. “Multimodal medical image fusion using daubechies complex wavelet transform”, Information & Communication Technologies (ICT), 2013 IEEE Conference on , April 2013 Page(s):869 – 873 Print ISBN:978-1-4673- 5759-3.
[19]. Bull, D.R. Canagarajah, C.N. Halliwell, M. Wells, P.N.T. and Nikolov S.G. “Image fusion using a 3-D wavelet transform”, Image Processing And Its Applications, 1999. Seventh International Conference on (Conf. Publ. No. 465) (Volume:1 ) Jul 1999, Page(s): 235 – 239 vol.1
20]. Ai Deng, Jin Wu, Shen Yang “An Image Fusion Algorithm Based on Discrete Wavelet Transform and Canny Operator” Advanced Research on Computer Education, Simulation and Modeling Communications in Computer and Information Science Volume 175, 2011, pp 32-38.

For a better career, come join IEC Group.
For admissions, mail us at

You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *