TY - GEN
T1 - Supervised in-vivo plaque characterization incorporating class label uncertainty
AU - Van Engelen, Arna
AU - Niessen, Wiro J.
AU - Klein, Stefan
AU - Groen, Harald C.
AU - Verhagen, Hence J.M.
AU - Wentzel, Jolanda J.
AU - Van Der Lugt, Aad
AU - De Bruijne, Marleen
PY - 2012/7/12
Y1 - 2012/7/12
N2 - We segment atherosclerotic plaque components in in-vivo MRI and CT data using supervised voxelwise classification. The most reliable ground truth can be obtained from histology sections, however, it is not straightforward to use this for classifier training as the registration with in-vivo data often shows misalignments. Therefore, for training we incorporate uncertainty in the ground truth via "soft" labels that indicate a probability for each class. Soft labels are created by Gaussian blurring of the original hard segmentations, and weighted by the registration accuracy. Classification is evaluated on the relative volumes for fibrous, lipid-rich necrotic and calcified tissue. Using conventional "hard" labels, the differences between the ground truth and classification result per subject are 0.4±3.6% for calcification, 7.6±14.9% for fibrous and 7.2±14.5% for necrotic tissue. Using the new approach accuracy is improved: for calcification 0.6±1.6%, fibrous 3.6±16.8% and necrotic tissue 2.9±16.1%.
AB - We segment atherosclerotic plaque components in in-vivo MRI and CT data using supervised voxelwise classification. The most reliable ground truth can be obtained from histology sections, however, it is not straightforward to use this for classifier training as the registration with in-vivo data often shows misalignments. Therefore, for training we incorporate uncertainty in the ground truth via "soft" labels that indicate a probability for each class. Soft labels are created by Gaussian blurring of the original hard segmentations, and weighted by the registration accuracy. Classification is evaluated on the relative volumes for fibrous, lipid-rich necrotic and calcified tissue. Using conventional "hard" labels, the differences between the ground truth and classification result per subject are 0.4±3.6% for calcification, 7.6±14.9% for fibrous and 7.2±14.5% for necrotic tissue. Using the new approach accuracy is improved: for calcification 0.6±1.6%, fibrous 3.6±16.8% and necrotic tissue 2.9±16.1%.
UR - http://www.scopus.com/inward/record.url?scp=84864829962&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2012.6235530
DO - 10.1109/ISBI.2012.6235530
M3 - Conference proceeding
AN - SCOPUS:84864829962
SN - 9781457718588
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 246
EP - 249
BT - 2012 9th IEEE International Symposium on Biomedical Imaging
T2 - 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012
Y2 - 2 May 2012 through 5 May 2012
ER -