Imperial Journal of Interdisciplinary Research (IJIR) Vol-3, Issue-2, 2017 ISSN: 2454-1362, http://www.onlinejournal.in
Medical Ultrasound Image Sharpening Using Intuitive Wet Drizzle Varinder Singh1, Anil Sagar2, Baljinder Singh3 1
2,3
Student, Beant College of Engineering & Technology, Gurdaspur.(India) Assistant Professor, Dept of Computer Science & engineering, Beant college of engineering & Technology, Gurdaspur.(India),
Abstract: The main aim of image enhancement is to enhance the quality and visual appearance of an image, or to provide a better transform representation for future automated image processing. Many images like medical images, satellite, aerial images and also real life photographs suffer from poor and bad contrast and noise. It is necessary to enhance the contrast and remove the noise to increase image quality. One of the most important stages in medical images detection and analysis is Image Enhancement Techniques. It improves the clarity of images for human viewing, removing blurring and noise, increasing contrast, and revealing details. In our research, we will proposes a Intuitive wet Drizzle (IWD) based sharpening technique (ST) for contrast enhancement ultrasound sound (US) images. The proposed technique IWD is operated on the multi scale, multidirectional IWD decomposition of the underlying US image. The results are compared with contourlet transform(CT) with the proposed IWD. The parameters like enhancement measure, structural structural similarity and Peak signal to noise ratio evaluate the improved performances of the proposed technique. Keywords: Image Enhancement, IWD, ultrasound images, Contourlet Tranform.
1. Medical ultrasound imaging Medical ultrasonography is used in a wide range of areas of patient diagnosis, where maybe obstetrics (woman and unborn child during pregnancy) and cardiology (heart and blood vessels) are the most well known to the general public. The image quality varies greatly between patients and organs. Improved image quality enhances the diagnosis accuracy and has the potential to open up for increased use of ultrasound imaging e.g. in breast and prostate cancer diagnosis and screening. Conventional ultrasound imaging is based on the pulse-echo technique, which essentially relies on transmission of a pulse, receiving echoes and interpreting them to form an image. The image reconstruction is done assuming the speed of sound
Imperial Journal of Interdisciplinary Research (IJIR)
to be constant within the object. Measurement of the amplitude of the received echoes, while relating to their respective time-of- flight, makes it possible to map the position of back-scattering targets along the direction of the ultrasound beam.
Figure 1: Simulated transmit beam example for a 7.5MHz pulse excitation without apodization, from a focused circular transducer aperture with _=4.8mm. The mainlobe and the sidelobes of the beam are indicated. The beam pressure amplitude is shown in decibel. [4] Fig. 1 shows a transmit beam example, with its mainlobe and first side lobes indicated. The reciprocity of the linear wave-equation makes the receive beam equal to the transmit beam if the apertures and pulses are the same.The two-way beam for an imaging setup is the product of transmit and receive beams and indicates much of its lateral pulse-echo imaging properties. When the ultrasound receive transducer is divided into an array of elements, acquired receive signals from each element may be processed, e.g. by application of varying electronic focusing delays, before the total received signal is summed up. This allows use of dynamic aperture and dynamic focusing allowing the receive beam to be more narrow than the transmit beam. Dynamic focusing involves a dynamic variation of the electronic delays of the array elements in order
Page 1
Imperial Journal of Interdisciplinary Research (IJIR) Vol-3, Issue-2, 2017 ISSN: 2454-1362, http://www.onlinejournal.in to make the receive focus follow reflections from deeper and deeper depths. Application of dynamic aperture means that the number of active receive elements is increased with the imaging depth in order to keep the F-number, and hence the receive beam-width, uniform within the imaging depth window. 2.Spatial domain enhancement methods:.Spatial domain techniques are performed to the image plane itself and they are based on direct manipulation of pixels in an image. The operation can be formulated as g(x,y) = T[f(x,y)], where g is the output, f is the input image and T is an operation on f defined over some neighbor hood of (x,y). According to the operations on the image pixels, it can be further divided into 2 categories: Point operations and spatial operations (including linear and non- linear operations).
3. Frequency methods:
domain
enhancement
These methods enhance an image f(x,y) by convoluting the image with a linear, position invariant operator. The 2D convolution is performed in frequency domain with DFT. Spatal domain:
g(x,y)=f(x,y)*h(x,)
Frequency domain: G(w1,w2)=F(w1,w2)H(w1,w2)
4. Enhancement by point processing: These processing methods are based only on the intensity of single pixels. Image negatives: Negatives of digital images are useful in numerous applications, such as displaying medical images and photographing a screen with monochrome positive film with the idea of using the resulting negatives as normal slides.
Special case: If r1=r2=0, s1=0 and s2=L-1, then it is actually a thresholding that creates a binary images.
Compression of dynamic range Sometimes the dynamic range of a processed image far exceeds the capability of the display device, in which case only the brightest parts of the images are visible on the display screen. An effective way to compress the dynamic range of pixel values is to perform the following intensity transformation function: where c is a scaling constant, and the logarithm function performs the desired compression. 5. Intuituive wet drizzle IWD algorithm is swarm based nature inspired optimization algorithm. This algorithm contains few essential elements of natural wet drizzles and actions and reactions that occurs between the river’s beds and the wet drizzles that flow within. The IWD algorithm may fall into the category of swarm intelligence and metaheuristic . Intrinsically, the IWD algorithm can be used for combinational optimization. However, it may be adapted for continuous optimization too. The IWD was first introduced for the travelling salesman problem in 2007. Since then, multitude of researchers has focused on improving the algorithm for different problems. Almost every IWD algorithm is composed of two parts: a graph that plays the role of distributed memory on which soils of different edges are preserved, and the moving part of the IWD algorithm, which is a few number of intuitive wet drizzles. These IWDs both compete and cooperate to find better solutions and by changing soils of the graph, the paths to better solutions become more reachable. It is mentioned that the IWD-based algorithms need at least two IWDs to work.
Transform function T: g(x,y)=L-f(x,y), where L is the maximum intensity.
6.
Problem Definition
Contrast stretching
Low-contrast images can result from poor illumination, lack of dynamic range in the image sensor, or even wrong setting of a lens aperture during image acquisition. The idea behind contrast stretching is to increase the dynamic range of the gray levels in the image being processed.
Imperial Journal of Interdisciplinary Research (IJIR)
It has been already explained that the principal objective of image enhancement is to process a given image so that the result is more suitable than the original image for a specific application. It accentuates or sharpens image features such as edges, boundaries, or contrast to make a graphic display more helpful for display and analysis. Our first problem is to study the image enhancement using the contourlet transform technique and need to compare the results with the implementation of IWD. Intuitive wet Drizzle (IWD)
Page 2
Imperial Journal of Interdisciplinary Research (IJIR) Vol-3, Issue-2, 2017 ISSN: 2454-1362, http://www.onlinejournal.in based Image Enhancement is a new technique and we expect the results of enhancement to be far better in comparison to the contourlet transform.
7.
Objectives
1. Study of Image Enhancement. 2. Study of Contourlet transform technique. 3. Pointing out the pros and cons of the Contourlet transform. 4. Study of IWD Implementation for the same purpose. 5. Implementation of IWD Image Enhancement. 6. Comparison of IWD Results with the Contourlet transform.
8.
[3] Om Prakash Verma, Puneet Kumar, Madasu Hanmandlu, Sidharth Chhabra, “High dynamic range optimal fuzzy color image enhancement using Artificial Ant Colony System” Applied Soft Computing, Volume 12, Issue 1, January 2012, Pages 394–404. [4] Jaspreet Kaur, Sukwinder Kaur and Maninder Kaur , “Image Enhancement Using Particle Swarm Optimization and Honey Bee” IJAIR, Vol. 2, Issue 2, 2013. [5] F. S. Foster, G. R. Lockwood, L. K. Ryan, K. A. Harasiewicz, L. Berube, and A. M. Rauth. Principles and applications of ultrasound backscatter microscopy. IEEE Trans. Ultrason., Ferroelect., Freq. Contr., 40(5):608–617, Sept. 1993.
Proposed Work
The present research work is proposed to be completed in three stages which have to be preceded in parallel fashion, as described below 1. Literature review 2 Core project work (MATLAB) 3. Documentation
9. Conclusion This paper presented a sharpening technique (ST) for ultrasound image enhancement for a good quality of visual perception. The proposed ST overcomes the problem of the classical ST that improves the noise while enhancing. The performances are evaluated using structural similarity (SSSIM), peak signal to noise ratio (PSNR) and enhancement measure (EME) parameters. The subjective and objective results illustrated that the proposed ST produces enhanced results in good quality with more similarity with the original image.
References [1] Ramirez Rivera, A.; Byungyong Ryu ; Oksam Chae; “Content-Aware Dark Image Enhancement Through Channel Division”, Image Processing, IEEE Transactions on image processing, Volume: 21 , Issue: 9 ,pp. 3967 – 3980, 2012.
[6] P. J. A. Frinking and N. de Jong. Acoustic modeling of shell-encapsulated gas bubbles. Ultrasound Med. Biol., 24:523–533, May 1998. [7] D. E. Goertz, M. E. Frijlink, N. de Jong, and A. F. W. van der Steen. Dual frequency microbubble imaging for high frequency ultrasound systems. In Proc. IEEE Ultrason. Symp., Vancouver, BC, Canada, Oct. 2006. [8] E. J. Gottlieb, J. M. Cannata, C.-H. Hu, and K. K. Shung. Development of a high-frequency (> 50MHz) copolymer annular-array, ultrasound transducer. IEEE Trans. Ultrason., Ferroelect., Freq. Contr., 53(5):1037–1045, May 2006. [9] R. Hansen. New techniques for Detection of Ultrasound Contrast Agents. PhD thesis, Norwegian University of Science and Technology, 2004. [10] G. R. Harris. Transient field of a baffled planar piston having an arbitrary vibration amplitude distribution . J. Acoust. Soc. Am., 70:186–204, July 1981.
[2] Zheng, H., Pan, L., Xiang, Yong, Wong, A. and Nahavandi, Saeid 2003, “Genetic image enhancement based on saturation feedback”, in Proceedings of the International Conference on Computational Intelligence, Robotics and Autonomous Systems : CIRAS 2001 : 28-30 November 2001, Singapore, CIRAS Organising Committee, Singapore.
Imperial Journal of Interdisciplinary Research (IJIR)
Page 3