MICCAI 2013 - LNCS 8149-8151

Similarity Guided Feature Labeling for Lesion Detection

Yang Song¹, Weidong Cai¹, Heng Huang², Xiaogang Wang³, Stefan Eberl⁴, Michael Fulham^4,5, and Dagan Feng¹

¹BMIT Research Group, School of IT, University of Sydney, Australia

²Computer Science and Engineering, University of Texas at Arlington, USA

³Department of Electronic Engineering, Chinese University of Hong Kong, China

⁴Department of PET and Nuclear Medicine, Royal Prince Alfred Hospital, Australia

⁵Sydney Medical School, University of Sydney, Australia

Abstract. The performance of automatic lesion detection is often affected by the intra- and inter-subject feature variations of lesions and normal anatomical structures. In this work, we propose a similarity-guided sparse representation method for image patch labeling, with three aspects of similarity information modeling, to reduce the chance that the best reconstruction of a feature vector does not provide the correct classification. Based on this classification model, we then design a new approach for detecting lesions in positron emission tomography – computed tomography (PET-CT) images. The approach works well with simple image features, and the proposed sparse representation model is effectively applied for both detection of all lesions and characterization of lung tumors and abnormal lymph nodes. The experiments show promising performance improvement over the state-of-the-art.

LNCS 8149, p. 284 ff.

Full article in PDF | BibTeX