TY - GEN
T1 - X-ray image categorization and retrieval using patch-based visual words representation
AU - Avni, U
AU - Greenspan, H
AU - Sharon, M
AU - Konen, E
AU - Goldberger, J
N1 - Place of conference:USA
PY - 2009
Y1 - 2009
N2 - 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.organ-level discrimination,pathology-level categorization
AB - 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.organ-level discrimination,pathology-level categorization
UR - https://scholar.google.co.il/scholar?q=X-ray+image+categorization+and+retrieval+using+patch-based+visual+words+representation&btnG=&hl=en&as_sdt=0%2C5
M3 - Conference contribution
BT - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
PB - IEEE
ER -