IMAGE PROCESSING
Contents
4.1 Image to be Processed Reading to MATLAB.. 4
1.0 Introduction
Image processing is the process of performing manipulations on an image that is desired so that we can get an improved image and also obtain relevant data from it. Furthermore, image processing can be described as the use of computer algorithms to make, process and consequently display digital images. Image processing can be categorized as either being an analogue or digital image processing. The former type of image processing is basically essential for the case of hard copies like printouts and photographs. On the other hand, digital image processing involves the use of computer software in order to manipulate the digital images accordingly by use of computers.
In our day to day activities, image processing is an integral aspect of our lives, this is because it forms part and parcel in a wide variety of fields such as science and technology and precisely in applications such as robotics, remote sensing, medical diagnosis and many more. Image processing finds its suitability in health care systems, this is attributed to the fact that it is very extensive, and the obtained result is very reliable. Image processing for medical diagnosis is vital as it can lessen the effect of noise, better the image and improve its quality. The digitally processed medical images can precisely help focus on the disease and visually communicate medical and pathological information of the image.
This report will primarily focus on digital image processing using MATLAB simulation. MATLAB toolbox for medical image processing will be effectively used for medical image analysis in this report due to robustness as well as its ability to acquire, recognize and process the images. Another good feature with MATLAB is its ability in writing function files, or script files to perform the desired operations. The written scripts will be essential for documentation purposes, these written files form a formal record for image processing used and will guarantee that the final results can be openly tested and replicated by others should the need arise.
- Literature Review
In this section, literature review of digital image processing and medical applications of image processing is going to be explored using MATLAB software.
The earliest advancements in the field of image processing goes back in time to the early sixties. The developed methods of digital image processing were initially made at the Jet Propulsion Industry in 1960s at Massachusetts Institute of Technology by Bell Laboratories. Among the earliest researches conducted were the application to satellite images, medical imaging, character recognition and so forth. or digital picture processing as it often was called, were developed in the 1960s at the Jet Propulsion Laboratory, Massachusetts Institute of Technology, Bell Laboratories, University of Maryland. A few researches such as application to satellite images, wire-photo standards conversion, medical imaging, videophone, character recognition, and photograph enhancement were also carried out [1].
With the passing of time, image processing research advanced and Shanhui Sun Christian Bauer et al [13] presented a fully automated approach for segmentation of lungs in CT datasets for Medical purposes. The technique that was developed was purposely designed to clearly section lungs with cancerous masses. The methodical steps that were followed mainly consisted of three processing steps. First and foremost, a ribcage detection algorithm was used then a robust active shape model matching approach was applied to roughly segment the outline of the lungs. Finally, the outline of the matched model was further adapted to the image data by means of an optimal surface finding approach.
Weixingwang et al [16] also conducted research on image processing and he presented the newly developed ridge detection algorithm to diagnose indeterminate nodules correctly, this allowed for curative resection of early-stage malignant nodules and also avoiding the morbidity and mortality of surgery for benign nodules. The algorithm was compared to some traditional image segmentation algorithms. All the results are satisfactory for diagnosis.
Ashraf Anwar et al [33] introduced an inexpensive, user friendly general-purpose image processing tool and visualization program specifically designed in MATLAB to detect much of the brain disorders as early as possible. The application provided clinical and quantitative analysis of medical images. Minute structural difference of brain gradually results in major disorders such as schizophrenia, Epilepsy, inherited speech and language disorder, Alzheimer’s dementia etc. Here the main focusing is given to diagnose the disease related to the brain and its psychic nature (Alzheimer’s disease). Medical imaging is expensive and very much sophisticated because of proprietary software and expert personalities.
ShiruiGao [46] emphasized the MATLAB based medical image processing tools. It includes the theoretical background and examples. Through MATLAB this paper made the introduction of the post-imaging quality in medical technology and medical imaging. It also introduces the medical image processing technology and describes the image processing and processing technologies, including the organ contours, interpolation, filtering, and segmentation techniques. In medicine, the DICOM image data processing using MATLAB is also widely used in this type of image processing.
3.0 Application
The quality of an image is very vital health care systems due to the imaging aspects that is required to provide a dependable image of an organ or a bone so that accurate diagnosis and treatment can be administered. The application choice for this report was a fractured bone.
4.0 MATLAB Simulation
In the last several decades, medical imaging systems have advanced in a dynamic progress. There have been substantial improvements in characteristics such as sensitivity, resolution, and acquisition speed. New techniques have been introduced and, more specifically, analogue images have been substituted by digital ones. As a result, issues related to the digital images’ quality has emerged. The quality of acquired images is degraded by both physical factors, such as Compton scattering and photon attenuation, and system parameters, such as intrinsic and extrinsic spatial resolution of the gamma camera system. These factors result in blurred and noisy images. Most times, the blurred images present artefacts that may lead to a fault diagnosis. In order the images to gain a diagnostic value for the physician, it is compulsory to follow a specific series of processing.
Medical Image processing techniques include all the possible tools used to change or analyze an image according to individuals’ needs. There are a number of graphical user interface tools used but, in this project, I used image tool (imtool) this allows one to interact with the image of interest that is to be processed.
Often some images may contain large data which may result to memory shortage, image may fail to load and slow in zooming. To enable handling of this data we use blockproc processing directory which facilitates high resolution processing of the images. The sequential steps followed in the project were as follows.
4.1 Image Reading to MATLAB
First use the directory (imread) function to access the data that is the medical image being processed which in my case was processing a fractured bone. >> x=imread(‘bones.png’);
>> imshow(x)
Figure 1: Medical Image of a bone to be processed
To analyze the fractured bone, the image tool (imtool) was used, with this tool a doctor can analyze the fracture and get to know the actual length of the crack before doing an operation. a particular region of interest is selected and the following techniques are carried out.
5.0 Results
5.1 Image Interpolation
This is done to resample the image and come up with a new one based on the existing one which enhances the image quality. In interpolation one is required to resize an image using (imresize).
z = imresize(Image, scale, method);
in this project we were able to find the length and width of the fracture.
>> x=imread(‘bones.png’);
>> imshow(x)
>> imtool(x)
Figure 2: Interpolated Image of a fractured bone
5.2 Contrast enhancement
Image contrast in image processing is the variance in intensity corresponding to different concentration of activity in the patient. For high diagnostic accuracy, nuclear medical images must be of high contrast. This explains the contrast enhancement that was done for our simulation. Contrast enhancement was done to improve the visual clarity of the fracture bone using the command (imadjust) or new image=imcomplement(x);
5.3 Image filtering
Image filtering is applied for the purpose of noise removal and resolution enhancement and it compensates for loss of detail in an image while reducing noise. By carrying out filtering, the image will be of greater resolution and the degradation of the image will be limited. Image filtering is a mathematical processing for noise removal and resolution recovery. The goal of the filtering is to compensate for loss of detail in an image while reducing noise. Filters suppressed noise as well as deblurred and sharpened the image. Bearing this in mind, the chances of faulty diagnosis will be low.
Figure 3:Image filtering to improve resolution
The filter mask is a matrix of odd usually size which is applied directly on the original data of the image. The mask is centered on each pixel of the initial image. For each position of the mask the pixel values of the image are multiplied by the corresponding values of the mask.
The products of these multiplications are then added and the value of the central pixel of the original image is replaced by the sum. This must be repeated for every pixel in the image.
6.0Conclusion
Image processing can be applied for health care systems images for diagnosis and treatment administration. The main importance attributed to this is the improvement in the acquired image qualitatively as well as quantitative information data useful in patient’s therapy and care. With the use of MATLAB and Image Processing Toolbox, it is possible to provide quantitative analysis and visualization of Medical images.
The objectives of carrying out this report were achieved. It was possible to carry out MATLAB simulation by ensuring the image processing steps were followed. The image that was used for the study was a fractured bone and all image processing steps were applied that produced image of greater quality and higher resolution which aided the diagnosis process.