A Bayesian Hierarchical Model for Learning Natural Scene Categories
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Overview of the ImageCLEF 2007 Object Retrieval Task
Advances in Multilingual and Multimodal Information Retrieval
Sampling strategies for bag-of-features image classification
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Hierarchical spatial matching for medical image retrieval
MMAR '11 Proceedings of the 2011 international ACM workshop on Medical multimedia analysis and retrieval
| Hi-index | 0.00 |
We present an efficient image categorization and retrieval system applied to medical image databases, in particular large radiograph archives. The methodology presented is based on local patch representation of the image content and a bag-of-features approach for defining image categories, with a kernel based SVM classifier. In a recent international competition the system was ranked as one of the top schemes in discriminating orientation and body regions in x-ray images, and in medical visual retrieval. A detailed description of the method (not previously published) is presented, along with its most recent results. In addition to organ-level discrimination, we show initial results of pathology-level categorization of chest x-ray data. On a set of 102 chest radiographs taken from routine hospital examination, the system detects pathology with sensitivity of 94% and specificity of 91%. We view this as a first step towards similarity-based categorization with clinical importance in computer-assisted diagnostics.