DSpace JSPUI
DSpace preserves and enables easy and open access to all types of digital content including text, images, moving images, mpegs and data sets
Learn More
Please use this identifier to cite or link to this item:
http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/3412| Title: | Selection of Suitable Moment Invariant Features For Mycobacterium Tuberculosis Detection in Ziehl Neelsen Stained Tissue Images |
| Authors: | edy, victor haryanto |
| Keywords: | Mycobacterium Tuberculosis, region base skeleton, performance 0 |
| Issue Date: | 15-Feb-2020 |
| Publisher: | The Mattingley Publishing Co., Inc. |
| Series/Report no.: | th5;7890 - 7904 |
| Abstract: | Tuberculosis is a contagious disease between humans and a disease that causes death, this disease is infected by bacteria called Mycobacterium, in this paper comparing the performance of moment invariant features through region base and skeleton, the method used in this study is Hu, Zernike and Affine, and the results obtained, the best Zernike moment invariant in detection Mycobacterium Tuberculosis with above 80%. |
| Description: | Tuberculosis, also known as TB, is an infectious disease caused by the bacteria called Mycobacterium tuberculosis. The bacteria typically attack the lungs and referred as pulmonary TB (PTB) disease. However, it can also affect other parts of the human body such as lymph nodes, skeletal system, central nervous system, liver and pancreas, resulting in the extra-pulmonary TB (EPTB) disease. TB is a curable disease. The disease can be cured in most people with appropriate antibiotic treatment. Unfortunately, the disease remains the second leading cause of death from an infectious disease worldwide after HIV / AIDS [1] [2]. The World Health Organization (WHO) declared TB disease as a global public health problem in 1993, as nearly 7 – 8 million cases and 1.3 – 1.6 million deaths from TB were recorded every year. In 2010, there were an estimated 8.5 – 9.2 million cases of TB and 1.2 – 1.5 million deaths worldwide [2]. In Malaysia, TB incidence showed increasing trend to 19,337 cases (67/100,000 population) in 2010, compared to the previous year [3]. Early diagnosis of TB disease is important to ensure prompt treatment and control the spread of the disease. Currently, the diagnosis of TB disease is based on finding the presence of Mycobacterium tuberculosis in a clinical specimen of sputum or organ with suspected TB. A number of methods for TB diagnosis have been developed such as chest x- ray, culture and molecular diagnosis, but the most commonly used method is through visual identification of the bacilli using a microscope [4] [5]. The difficulties in EPTB diagnosis through visual assessment of tissue sections and the rise of EPTB incidence rate has driven this research to focus on developing a computer-aided diagnosis for this disease. The main objective of this research is to automate the detection of TB bacilli in tissue sections using image processing techniques and neural network. The automated detection system is based on light-microscope images, as it is the most common method for clinical diagnosis of EPTB disease. |
| URI: | http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/3412 |
| ISSN: | 0193-4120 |
| Appears in Collections: |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Selection of suitable moment invariant features for mycobacterium tuberculosis detection in ziehl neelsen stained tissue images.pdf | 773.28 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.