Abstract  Image  segmentation  techniques  have  been  an  invaluab le  task  in  many  domains  such  as  quantification  of  tissue  volumes,  medical  diagnosis,  anatomical  structure  st udy,  treatment  planning,  etc.  Image  segmentation  is   still  a  debatable  problem  due  to  some  issues.  Firstly,  most  image  seg mentation  solutions  are  problem-based.  Secondly,  medical  image  segmentation methods generally have restrictions be cause medical images have very similar gray level and texture among the  interested  objects.  The  goal  of  this  work  is  to  des ign  a  framework  to  extract  simultaneously  several  o bjects  of  interest  from  Computed  Tomography  (CT)  images  by  using  some  prior i-knowledge.  Our  method  used  properties  of  agent  in  a  multi-agent  environment. The input image is divided into severa l sub-images, and each local agent works on a sub-i mage and tries to mark  each  pixel  as  a  specific  region  by  means  of  given  p riori-knowledge.  During  this  time  the  local  agent  m arks  each  cell  of  sub- image  individually.  Moderator  agent  checks  the  outc ome  of  all  agents’  work  to  produce  final  segmented  image.  The  experimental results for CT images demonstrated seg mentation accuracy around 91% and efficiency of 7 seconds.    

References

[1] Benamrane N. and Nassane S., Medical Image Segmentation by a Multi-Agent System Approach, in Proceedings of the 5 th German Conference on Multiagent System Technologies , Germany, pp. 49-60, 2007.

[2] Boucher A. and Garbay C., A Multi-Agent System to Segment Living Cells, in Proceedings of the 13 th International Conference on Pattern Recognition , Austria, vol. 3, pp. 558-562, 1996.

[3] Boucher A., A Society of Goal-Oriented Agents for the Analysis of Living Cells, Artificial Intelligence in Medicine , vol. 14, no. 1-2, pp. 183-196, 1998.

[4] Chitsaz M. and Woo C., The Rise of Multi- Agent and Reinforcement Learning Segmentation Methods for Biomedical Images, in Proceedings of the 4 th Malaysian Software Engineering Conference , Malaysia, pp. 5-8, 2008.

[5] Chitsaz M. and Woo C., Software Agent with Reinforcement Learning Approach for Medical Image Segmentation, Journal of Computer Science and Technology , vol. 26, no. 2, pp. 247- 255, 2011.

[6] Chitsaz M., Image Segmentation using Reinforcement Learning Agent in Multi-Agent System, Theses MS , University of Malaya, 2009.

[7] Crevier D. and Lepage R., Knowledge-Based Image Understanding Systems: A Survey, Computer Vision and Image Understanding , vol. 67, no. 2, pp. 161-185, 1996.

[8] DICOMsample, DICOM Files, available at: http://pubimage.hcuge.ch:8080, last visited 2008.

[9] Duchesnay E., Montois J., and Jacquelet Y., Cooperative Agents Society Organized as an Irregular Pyramid: A Mammography Segmentation Application, Pattern Recognition Letters , vol. 24, no. 14, pp. 2435-2445, 2003.

[10] Duchesnay E., An Agent-Based Implementation of Irregular Pyramid for Distributed Image Segmentation, in Proceedings of the 8 th International Conference on Emerging Technologies and Factory , France, pp. 409-415, 2001.

[11] Germond L., A Cooperative Framework for Segmentation of MRI Brain Scan, Artificial Intelligence in Medicine , vol. 20, no. 1, pp. 77- 93, 2000.

[12] Jennings N., Sycara K., and Wooldridge M., A Roadmap of Agent Research and Development, International Journal of Autonomous Agents and Multi-Agent Systems , vol. 1, no. 1, pp. 7-38, 1998.

[13] Kagawa H., Kinouchi M., and Hagiwara M., Image Segmentation by Artificial Life Approach using Autonomous Agents, in Proceedings of International Joint Conference on Neural Networks , USA, pp. 4413-4418 , 1999.

[14] Liu J. and Tang Y., Adaptive Image Segmentation with Distributed Behaviour-Based Agents, IEEE Transaction on Pattern Analysis and Machine Intelligence , vol. 21, no. 6, pp. 544- 551, 1999.

[15] Liu J., Synergistic Hybrid Image Segmentation: Combining Model and Image-Based Startegies, Theses PhD , University of Pennsylvania, 2006.

[16] Pham D., Xu C., and Prince J., A Survey of Current Methods in Medical Image Segmentation, Annual Review of Biomedical Engineering , vol. 2, pp. 315-337, 2000.

[17] Rares A., Reinders M., and Hendriks E., Mapping Image Analysis Problems on Multi- Agent Systems, Technical Report, MCCWS Project Information and Communication Theory Group, 1999.

[18] Richard N., Dojat M., and Garbay C., Automated Segmentation of Human Brain MR Images using a Multi-Agent Approach, Artificial Intelligence in Medicine , vol. 30, no. 2, pp. 75-153, 2004.

[19] Spinu C., Garbay C., and Chassery J., A Multi- Agent Approach to Edge Detection as a Distributed Optimization Problem, in Proceedings of the 13 th International Conference on Pattern Recognition , Austria, vol. 2, pp. 81- 85, 1996.

[20] Udupa J., A framework for evaluating image segmentation algorithms Computerized Medical Imaging and Graphics , vol. 30, no. 2, pp. 75-87, 2006.

[21] Wooldridge M., Agent-Based Software Engineering, IEE Proceedings on Software Engineering , vol. 144, no. 1, pp. 26-37, 1997. Medical Image Segmentation using a Multi-Agent System Approach 229

[22] Wooldridge M. and Jennings N., Intelligent Agents: Theory and Practice, The Knowledge Engineering Review , vol. 10, no. 2, pp. 115-152, 1995.

[23] Zhang Y., A Review of Recent Evaluation Methods for Image Segmentation, in Proceedings of the 6 th International Symposium on Signal Processing and its Applications , Malaysia, vol. 1, pp. 148-151, 2001. Mahsa Chitsaz received her BS in computer engineering from Shiraz University in 2006. She obtained her MSc from University of Malaya in 2010 under the guidance of Woo Chaw Seng in the area of reinforcement learning in medical image segmentation. Chitsaz s research interest is in artificial intelligence and real-time systems, main ly in the areas of machine learning and dynamic processes . She also works at the intersection of learning and topics as varied as medical image segmentation, telemedicine, and head-mounted display. Woo Chaw Seng is a senior lecturer at the Faculty of Computer Science and Information Technology, University of Malaya. His research interests include image processing and mobile applications.