TY - GEN
T1 - Breast tissue density and CAD cancer detection in digital mammography
AU - Li, Hua
AU - Wu, Zuobao
AU - Chen, Li
AU - George, Florence
AU - Chen, Zhao
AU - Salem, Angela
AU - Kallergi, Maria
AU - Berman, Claudia
PY - 2005
Y1 - 2005
N2 - This study is part of the research of improving early detection of breast cancer in screening mammograms by focusing on computerized analysis and detection of cancers missed by radiologists. It is directed to the analysis of breast density in missed cancer cases and the effect of tissue density on cancer detection. A total of 100 missed cancer cases were collected which were used to generate three different datasets including mammograms with missed cancer, mammograms with screening-detected cancer and normal mammograms. A statistical-based method was applied to segment the breast density tissue. The percentage of the segmented density tissue area out of the whole breast area is calculated as the index of breast density. A set of tests was applied to examine (1) the differences in density between the mammograms at the detected stage and that at missed stage, (2) the density difference between the normal mammograms and the cancerous mammograms; (3) the effect of breast density on CAD cancer detection. The results demonstrate that (1) no significant difference in breast density between the detected and missed stages; (2) the density of cancerous mammograms is significantly higher than normal mammograms; (3) similar to mammogram screening by radiologists, the lesions occurred in dense breasts are more likely to be missed in CAD detection especially at their early stage.
AB - This study is part of the research of improving early detection of breast cancer in screening mammograms by focusing on computerized analysis and detection of cancers missed by radiologists. It is directed to the analysis of breast density in missed cancer cases and the effect of tissue density on cancer detection. A total of 100 missed cancer cases were collected which were used to generate three different datasets including mammograms with missed cancer, mammograms with screening-detected cancer and normal mammograms. A statistical-based method was applied to segment the breast density tissue. The percentage of the segmented density tissue area out of the whole breast area is calculated as the index of breast density. A set of tests was applied to examine (1) the differences in density between the mammograms at the detected stage and that at missed stage, (2) the density difference between the normal mammograms and the cancerous mammograms; (3) the effect of breast density on CAD cancer detection. The results demonstrate that (1) no significant difference in breast density between the detected and missed stages; (2) the density of cancerous mammograms is significantly higher than normal mammograms; (3) similar to mammogram screening by radiologists, the lesions occurred in dense breasts are more likely to be missed in CAD detection especially at their early stage.
UR - http://www.scopus.com/inward/record.url?scp=33846926822&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33846926822&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:33846926822
SN - 0780387406
SN - 9780780387409
T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
SP - 3253
EP - 3256
BT - Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
T2 - 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
Y2 - 1 September 2005 through 4 September 2005
ER -