DocumentCode :
2210774
Title :
Extraction of sputum cells using thresholding techniques for lung cancer detection
Author :
Taher, Fatm ; Werghi, Naoufel ; Al-Ahmad, Hussain
Author_Institution :
Dept. of Electron. & Comput. Eng., Khalifa Univ., Sharjah, United Arab Emirates
fYear :
2012
fDate :
18-20 March 2012
Firstpage :
36
Lastpage :
41
Abstract :
This paper deals with an improved version of a filtering thresholding algorithm for extracting the sputum cell from the raw sputum image for lung cancer early detection. In this method the problem is viewed as a segmentation problem focusing on the extraction of such sputum cells from the images. This will be done by segmenting the image into sputum cell region which includes the nuclei, cytoplasm and the background that includes all the rest. These cells can then be analyzed to see if they are cancerous or not. A database with hundred of sputum color images from normal and abnormal subjects that prepared by the Papanicalaou standard staining method were used. These images were used in testing the new algorithm and the results were compared with the ground truth image of extracted sputum cells. It was noted that the new algorithm offered better extraction results than the previous work. It succeeded in extracting the nuclei and cytoplasm regions. Moreover, it succeeded in determining the best range of thresholding values.
Keywords :
cancer; cellular biophysics; filtering theory; image segmentation; lung; medical image processing; Papanicalaou standard staining method; cytoplasm region; filtering thresholding algorithm; image segmentation problem; lung cancer early detection; nuclei region; raw sputum image; segmentation problem; sputum cell extraction; sputum color images; Accuracy; Cancer; Filtering; Filtering algorithms; Image segmentation; Lungs; Sensitivity; Image Segmentation; Lung Cancer Detection; Sputum Cellse; Threshold Filtering Algorithm;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Innovations in Information Technology (IIT), 2012 International Conference on
Conference_Location :
Abu Dhabi
Print_ISBN :
978-1-4673-1100-7
Type :
conf
DOI :
10.1109/INNOVATIONS.2012.6207770
Filename :
6207770
Link To Document :
بازگشت