A Discriminative Distance Learning-Based CBIR Framework for Characterization of Indeterminate Liver Lesions

In this paper we propose a novel learning---based CBIR method for fast content---based retrieval of similar 3D images based on the intrinsic Random Forest (RF) similarity. Furthermore, we allow the combination of flexible user---defined semantics (in the form of retrieval contexts and high---level concepts) and appearance---based (low---level) features in order to yield search results that are both meaningful to the user and relevant in the given clinical case. Due to the complexity and clinical relevance of the domain, we have chosen to apply the framework to the retrieval of similar 3D CT hepatic pathologies, where search results based solely on similarity of low---level features would be rarely clinically meaningful. The impact of high---level concepts on the quality and relevance of the retrieval results has been measured and is discussed for three different set---ups. A comparison study with the commonly used canonical Euclidean distance is presented and discussed as well.

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

[2]  Steve Horvath,et al.  Tumor classification by tissue microarray profiling: random forest clustering applied to renal cell carcinoma , 2005, Modern Pathology.

[3]  Hans-Peter Kriegel,et al.  Combined semantic and similarity search in medical image databases , 2011, Medical Imaging.

[4]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Horst Bunke,et al.  Non-Euclidean or Non-metric Measures Can Be Informative , 2006, SSPR/SPR.

[6]  Z. Stojiljkovic,et al.  Object recognition by invariants , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[7]  Yanjun Qi,et al.  Random Forest Similarity for Protein-Protein Interaction Prediction from Multiple Sources , 2004, Pacific Symposium on Biocomputing.

[8]  S. Horvath,et al.  Unsupervised Learning With Random Forest Predictors , 2006 .

[9]  Dorin Comaniciu,et al.  Learning distance function for regression-based 4D pulmonary trunk model reconstruction estimated from sparse MRI data , 2011, Medical Imaging.

[10]  Horst Bischof,et al.  On-line Random Forests , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[11]  Carlo Bartolozzi,et al.  Focal liver lesions : detection, characterization, ablation , 2004 .

[12]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[13]  Geoff Holmes,et al.  New Options for Hoeffding Trees , 2007, Australian Conference on Artificial Intelligence.

[14]  Stuart J. Russell,et al.  Experimental comparisons of online and batch versions of bagging and boosting , 2001, KDD '01.

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

[16]  Alexey Tsymbal,et al.  Learning Discriminative Distance Functions for Case Retrieval and Decision Support , 2010, Trans. Case Based Reason..

[17]  Carlo Bartolozzi,et al.  Focal Liver Lesions , 2005 .

[18]  A. Hudak,et al.  Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDAR data , 2008 .

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  J. Spencer,et al.  Indeterminate lesions in cancer imaging. , 2008, Clinical radiology.

[21]  Howard Y. Chang,et al.  Decoding global gene expression programs in liver cancer by noninvasive imaging , 2007, Nature Biotechnology.

[22]  Edwin R. Hancock,et al.  Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop, SSPR&SPR 2010, Cesme, Izmir, Turkey, August 18-20, 2010. Proceedings , 2010, SSPR/SPR.