TY - GEN
T1 - Breast masses classification using a sparse representation
AU - Narváez, Fabián
AU - Rueda, Andrea
AU - Romero, Eduardo
PY - 2011
Y1 - 2011
N2 - Breast mass detection and classification in mammograms is considered a very difficult task in medical image analysis. In this paper, we present a novel approach for classification of masses in digital mammograms according with their severity (benign or malign). Unlike other approaches, we do not segment masses but instead, we attempt to describe entire regions of interest (RoIs) based on a sparse representation. A set of patches selected by a radiologist in a RoI are characterized by their projection onto learned dictionaries, constructed previously from classified regions. Finally, the region class was identified using a decision rule algorithm. The strategy was assessed in a set of 80 masses with different shapes extracted from the DDSM database. The classification was compared with a ground truth already provided in the data base, showing an average accuracy rate of 70%.
AB - Breast mass detection and classification in mammograms is considered a very difficult task in medical image analysis. In this paper, we present a novel approach for classification of masses in digital mammograms according with their severity (benign or malign). Unlike other approaches, we do not segment masses but instead, we attempt to describe entire regions of interest (RoIs) based on a sparse representation. A set of patches selected by a radiologist in a RoI are characterized by their projection onto learned dictionaries, constructed previously from classified regions. Finally, the region class was identified using a decision rule algorithm. The strategy was assessed in a set of 80 masses with different shapes extracted from the DDSM database. The classification was compared with a ground truth already provided in the data base, showing an average accuracy rate of 70%.
UR - http://www.scopus.com/inward/record.url?scp=79960679403&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:79960679403
SN - 9789898425386
T3 - Proceedings of the 2nd International Workshop on Medical Image Analysis and Description for Diagnosis Systems, MIAD 2011, in Conjunction with BIOSTEC 2011
SP - 26
EP - 33
BT - Proceedings of the 2nd International Workshop on Medical Image Analysis and Description for Diagnosis Systems, MIAD 2011, in Conjunction with BIOSTEC 2011
T2 - 2nd International Workshop on Medical Image Analysis and Description for Diagnosis Systems, MIAD 2011, in Conjunction with BIOSTEC 2011
Y2 - 28 January 2011 through 29 January 2011
ER -