Cui Hui, Wang Xiuying, Feng Dagan
Biomedical and Multimedia Information Technology (BMIT) research group, School of Information Technologies, The University of Sydney, Australia.
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:5384-7. doi: 10.1109/EMBC.2012.6347211.
Positron emission tomography - computed tomography (PET-CT) plays an essential role in early tumor detection, diagnosis, staging and treatment. Automated and more accurate lung tumor detection and delineation from PET-CT is challenging. In this paper, on the basis of quantitative analysis of contrast feature of PET volume in SUV (standardized uptake value), our method firstly automatically localized the lung tumor. Then based on analysing the surrounding CT features of the initial tumor definition, our decision strategy determines the tumor segmentation from CT or from PET. The algorithm has been validated on 20 PET-CT studies involving non-small cell lung cancer (NSCLC). Experimental results demonstrated that our method was able to segment the tumor when adjacent to mediastinum or chest wall, and the algorithm outperformed the other five lung segmentation methods in terms of overlapping measure.
