Title :
Determining features for discriminating PTB and normal lungs using phase congruency model
Author :
Rijal, Omar Mohd ; Ebrahimian, Hossien ; Noor, Norliza Mohd
Author_Institution :
Inst. of Math. Sci., Univ. of Malaya, Kuala Lumpur, Malaysia
Abstract :
The appearance of the infected zone on the digital chest X-ray image for pulmonary tuberculosis (PTB) does not conform to standard shape, size or configuration. This study uses phase congruency (PC(x)) values to gather information from transition of adjacent pixel values that may be used as features to represent known disease type. The feature vector consisting of the average, variance, coefficient of variation and maximum PC(x)-values was found to be able to detect PTB with high accuracy.
Keywords :
diagnostic radiography; diseases; lung; medical image processing; PTB discrimination; adjacent pixel value; coefficient of variation; digital chest X-ray image; feature determination; feature vector; infected zone appearance; normal lungs; phase congruency model; phase congruency value; pulmonary tuberculosis; Biomedical imaging; Image edge detection;
Conference_Titel :
Biomedical and Health Informatics (BHI), 2012 IEEE-EMBS International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4577-2176-2
Electronic_ISBN :
978-1-4577-2175-5
DOI :
10.1109/BHI.2012.6211583