IJEEE, Vol. 1, Spl. Issue 1 (March 2014)
e-ISSN: 1694-2310 | p-ISSN: 1694-2426
Improved Segmentation Technique for Enhancement of Biomedical Images Abhishek Thakur1, Rajesh Kumar2, Amandeep Bath3, Jitender Sharma4 1,2,3,4
Electronics & Communication Engineering Department, Indo Global College of Engineering, Punjab, India
1 abhithakur25@gmail.com, 2errajeshkumar2002@gmail.com, amandeep_batth@rediffmail.com, 4er_jitender2007@yahoo.co.in
3
Abstract- The aim of this paper is to develop a fast and reliable segmentation method to segment the haemorrhage region from brain CT images. To calculate area of segmented hemorrhage region that could be useful for physicians or researchers involved in the treatment or investigation of intracranial brain haemorrhage. Thus improving the machine generated automated results and reducing the human effort for better segmentation and saving vital time for the treatment of a patient. Keywords- Magnetic resonance imaging (MRI) and Computed tomography (CT) scan also known as CAT (Computer Axial Tomography), IV’s (Intravenous therapy). I. INTRODUCTION Magnetic resonance imaging (MRI) and Computed tomography (CT) scan also known as CAT (Computer Axial Tomography) scan, are the two main ways by which physicians take a picture of brain. In CT scan, testing is fast and results are quick and thus making it exceptionally valuable when prompt diagnosis and treatment are critical. CT scan can be taken while patient is hooked up to IV’s (Intravenous therapy) or other medical equipment, unlike some other scanning methods. CT scans can disclose hematomas, hemorrhages, and skull fractures and thus providing exact information to neurologist, necessary for deciding whether emergency treatment is required. An MRI process can take about 30-45 minutes to complete while a CT scan may only take 5 to 10 minutes. So, a severe hemorrhage could kill patient in the time consumed to take pictures in MRI machine. Further, in some situations a CT scan can actually detect abnormalities more easily than an MRI like a CT scan is good at detecting acute haemorrhage and problems in bone, for example fractures. On the other hand, an MRI is best at detecting small or subtle lesions. CT scans deliver a relatively high dose of radiation to a patient in comparison to other diagnostic tests. This is not usually a problem for a single scan, but patients who need to undergo repeated tests can be subjected to a significant level of radiation, hence increasing their cancer risk. MRI makes use of powerful magnetic fields and the magnetic reaction of the body cells to construct crosssectional images is similar to CT scans. MRI does not use Xrays, so it can be safer than CT if multiple imaging sessions are expected. The variations of MRI technology can also examine brain functioning and identify injuries which are International Journal of Electrical & Electronics Engineering
4
not visible in CT scans. But even the detail available using MRI cannot detect mild concussions. In acute head injury cases, MRI is not often used. MRI has some drawbacks, although MRI images yield finer detail than CT scans. Some drawbacks include it takes longer to perform, it is not as readily available as a CT scanner in most hospitals, it is not practical for patients hooked up to medical equipment and it cannot be used if patient has metal embedded anywhere in the body. The greatest danger of an MRI is to those with metal in their bodies that could be moved around or heated up by the powerful magnetic force created by MRI machine. MRI scans also require that a patient stay very still for a long period of time, which may be difficult if a patient is confused or fidgety. Each type of scan is susceptible to different kinds of artefact i.e. blurring of the image. The definitive tool for accurate diagnosis of an intracranial hemorrhage is CT scan i.e. computed tomography as shown in fig1.1. Typically computed tomography scanning of head is used to detect infarction, tumors, calcifications, hemorrhage and bone trauma. Head CT is the mainstay of diagnosis in ICH. Acute bleeding appears hyper dense (whiter) on a CT, relative to the surrounding tissues as shown in figure:
Fig.1 CT scan of a spontaneous intracranial hemorrhage
Image segmentation is the process of partitioning an image into different segments. These segments often correspond to different tissue classes, organs, pathologies, or other biologically relevant structures in medical imaging. In medical image analysis, one fundamental problem is image segmentation which identifies the boundaries of objects such as organs or abnormal regions like tumors in images. Due to noise, low contrast and other imaging ambiguities medical image segmentation becomes difficult. It is possible with the segmentation results to have shape analysis, detecting volume change, and making a precise radiation therapy treatment plan. Segmentation is a low-level operation, which is www.ijeee-apm.com