A Context Based ROI Classification Method in Medical Images
GUO Qiao-Jin, LI Ning, XIE Jun-Yuan
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023 Department of Computer Science and Technology, Nanjing University, Nanjing 210023
Abstract Region of interest (ROI) classification is the last and very important step in the process of computer-aided diagnosis with medical images. Traditional methods only employ local visual features of ROI for classification. Thus, the accurate classification can not be achieved under some circumstances. To improve the classification accuracy, the context information is extracted from regions around ROI. A latent Dirichlet allocation classification (LDAC) model based on LDA is proposed, which utilizes LDA to capture contextual information of ROI from surrounding regions. The proposed model is applied to mammograms and experimental results show that the classification accuracy is improved.
[1] Sahiner B, Chan H P, Petrick N, et al. Classification of Mass and Normal Breast Tissue: A Convolution Neural Network Classifier with Spatial Domain and Texture Images. IEEE Trans on Medical Imaging, 1996, 15(5): 598-610 [2] Moayedi F, Azimifar Z, Boostani R, et al. Contourlet-Based Mammography Mass Classification // Proc of the 4th International Confe-rence on Image Analysis and Recognition. Montreal, Canada, 2007: 923-934 [3] Surendiran B, Vadivel A. Feature Selection Using Stepwise ANOVA Discriminant Analysis for Mammogram Mass Classification. International Journal on Recent Trends in Engineering & Technology, 2010, 3(2): 55-57 [4] Engeland S V, Varela C, Timp S, et al. Using Context for Mass Detection and Classification in Mammograms. Proceeding of SPIE, 2005, 5749: 94-102 [5] Wolf L, Bileschi S. A Critical View of Context. International Journal of Computer Vision, 2006, 69(2): 251-261 [6] Su Y, Jurie F. Visual Word Disambiguation by Semantic Contexts // Proc of the IEEE International Conference on Computer Vision. Barcelona, Spain, 2011: 311-318 [7] Ding Y Y, Xiao J. Contextual Boost for Pedestrian Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2012: 2895-2902 [8] Wang X Y, Yang M, Cour T, et al. Contextual Weighting for Vocabulary Tree Based Image Retrieval // Proc of the IEEE International Conference on Computer Vision. Barcelona, Spain, 2011: 209-216 [9] Wainwright M J, Jordan M I. Graphical Models, Exponential Families, and Variational Inference. Foundations and Trends in Machine Learning, 2008, 1(1/2): 1-305 [10] Niu Z X, Hua G, Gao X B, et al. Context Aware Topic Model for Scene Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2012: 2743-2750 [11] Myeong H, Chang J Y, Lee K M. Learning Object Relationships via Graph-Based Context Model // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2012: 2727-2734 [12] Heesch D, Petrou M. Learning Markovian Dependencies from Annotated Images // Proc of the IEEE Workshop on Machine Lear-ning for Signal Processing. Thessaloniki, Greece, 2007: 111-116 [13] Gould S, Rodgers J, Cohen D, et al. Multi-class Segmentation with Relative Location Prior. International Journal of Computer Vision, 2008, 80(3): 300-316 [14] Monay F, Gatica-Perez D. On Image Auto-annotation with Latent Space Models // Proc of the 11th ACM International Conference on Multimedia. Berkeley, USA, 2003: 275-278 [15] Blei D M, Jordan M I. Modeling Annotated Data // Proc of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Toronto, Canada, 2003: 127-134 [16] Shi Y G, Tu Z W, Reiss A L, et al. Joint Sulcal Detection on Cortical Surfaces with Graphical Models and Boosted Priors. IEEE Trans on Medical Imaging, 2009, 28(3): 361-373 [17] Bugatti P H, Ponciano-Silva M, Traina A J M, et al. Content-Based Retrieval of Medical Images: From Context to Perception // Proc of the 26th IEEE International Symposium on Computer-Based Medical Systems. Albuquerque, USA, 2009: 1-8 [18] Hupse R, Karssemeijer N. Use of Normal Tissue Context in Computer-Aided Detection of Masses in Mammograms. IEEE Trans on Medical Imaging, 2009, 28(12): 2033-2041 [19] Cao L L, Li F F. Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes // Proc of the 11th IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil, 2007: 1-8 [20] Rose C, Turi D, Williams A, et al. Web Services for the DDSM and Digital Mammography Research // Proc of the 8th International Workshop on Digital Mammography. Manchester, UK, 2006: 376-383
2014, Vol. 27 
