Segmentation of tuberculosis bacilli in Ziehl-Neelsen-stained tissue images based on K-mean clustering procedure

• Published in: 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010
• Main Author: Osman M.K.; Mashor M.Y.; Saad Z.; Jaafar H.
• Format: Conference paper
• Language: English
• Published: 2010
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-79952774655&doi=10.1109%2fICIAS.2010.5716207&partnerID=40&md5=7c89515f4e99e32194841954fb8d3d70

In this paper, an automatic k-mean clustering based on C-Y colour model was proposed. First, initial filter is used to remove the tissues images which remain blue after counterstaining process. Secondly, k-mean clustering using saturation component of C-Y colour model is used to segment the TB bacilli from its undesirable background which also remains red even after decolourization process. Thirdly, a 5 × 5 median filter and region growing was used to eliminate small regions and noises. The proposed methods have been analysed for several TB slide images under various conditions. The results show that the proposed techniques were successfully segment TB bacilli from its background. Hence, the resultant images would furnish more useful information for further analysis by pathologists.