Combined Density, Texture and Shape Features of Multi-phase Contrast-Enhanced CT Images for CBIR of Focal Liver Lesions: A Preliminary Study

Recently, content-based image retrieval (CBIR) in medical applications has attracted a lot of attentions. In this paper, we present a preliminary study on CBIR of focal liver lesions based on combined density, texture and shape features of multi-phase contrast-enhanced CT volumes. We improve the existing method from following two aspects: (1) in order to improve the retrieval accuracy, we propose a novel 3D shape feature for CBIR of liver lesions in addition to conventional density and texture features; (2) in order to reduce the computation time, we propose an improved local binary pattern, which is called imLBP, as the 3D texture feature. The effectiveness of our proposed method has been validated with real clinical datasets.

[1]  H. Greenspan,et al.  Automated retrieval of CT images of liver lesions on the basis of image similarity: method and preliminary results. , 2010, Radiology.

[2]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[3]  M. Topi,et al.  Robust texture classification by subsets of local binary patterns , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[4]  Michael S. Brown,et al.  Three-Dimensional Spatiotemporal Features for Fast Content-Based Retrieval of Focal Liver Lesions , 2014, IEEE Transactions on Biomedical Engineering.

[5]  Yen-Wei Chen,et al.  A knowledge-based interactive liver segmentation using random walks , 2015, 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[6]  Qianjin Feng,et al.  Content-Based Retrieval of Focal Liver Lesions Using Bag-of-Visual-Words Representations of Single- and Multiphase Contrast-Enhanced CT Images , 2012, Journal of Digital Imaging.

[7]  Hayit Greenspan,et al.  Content-Based Image Retrieval in Radiology: Current Status and Future Directions , 2010, Journal of Digital Imaging.

[8]  Yanling Chi,et al.  Content-based image retrieval of multiphase CT images for focal liver lesion characterization. , 2013, Medical physics.

[9]  Hanqing Lu,et al.  A New Texture Feature Based on PCA Pattern Maps and Its Application to Image Retrieval , 2003 .

[10]  Christos Faloutsos,et al.  QBIC project: querying images by content, using color, texture, and shape , 1993, Electronic Imaging.

[11]  Alex Pentland,et al.  Photobook: Content-based manipulation of image databases , 1996, International Journal of Computer Vision.