Authors: Xiaolei Huang; Yaoyao Zhu; Hongsheng Li; Haiying Guan; Vaclav Potesil; Yulin Song; Toshiro Kubota; Xiang Sean Zhou
Addresses: Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA. ' Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA. ' Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA. ' Communications Engineering Branch, National Library of Medicine, Bethesda, MD 20892, USA. ' Department of Engineering Science, University of Oxford, Oxford, OX1 3PJ, UK. ' Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, NY 10021, USA. ' Department of Mathematical Sciences, Susquehanna University, Selinsgrove, PA 17870, USA. ' CAD Solutions Group, Siemens Medical Solutions, Malvern, PA 19355, USA
Abstract: We propose a new method for automated delineation of tumour boundaries by using joint information from whole-body PET and diagnostic CT images. Due to varying levels of FDG uptake in different organs, we apply locally adaptive thresholds of SUV to acquire an initial estimate of hot spot locations and shape in PET images. The hot spot boundaries are further improved by applying Competition Diffusion (CD) and Mode-Seeking Region Growing (MSRG) algorithms. These hot spots seen in PET are then confirmed and more accurately segmented considering CT information, through the Joint Likelihood Ratio Test technique for probabilistic integration. Experiments show that the proposed multi-modal method achieves more accurate and reproducible tumour delineation than using PET or CT alone.
Keywords: tumour delineation; image segmentation; PET scans; CT images; HMM; hidden Markov model; whole body; information fusion; region growing; likelihood ratio test; biomedical engineering; computed tomography; medical imaging; cancerous tissue; lung cancer; liver cancer.
International Journal of Biomedical Engineering and Technology, 2012 Vol.8 No.2/3, pp.182 - 199
Available online: 18 Mar 2012 *Full-text access for editors Access for subscribers Purchase this article Comment on this article