TY - JOUR
T1 - Veritas
T2 - Combining expert opinions without labeled data
AU - Cholleti, Sharath R.
AU - Goldman, Sally A.
AU - Blum, Avrim
AU - Politte, David G.
AU - Don, Steven
AU - Smith, Kirk
AU - Prior, Fred
PY - 2009/10
Y1 - 2009/10
N2 - We consider a variation of the problem of combining expert opinions for the situation in which there is no ground truth to use for training. Even though we do not have labeled data, the goal of this work is quite different from an unsupervised learning problem in which the goal is to cluster the data. Our work is motivated by the application of segmenting a lung nodule in a computed tomography (CT) scan of the human chest. The lack of a gold standard of truth is a critical problem in medical imaging. A variety of experts, both human and computer algorithms, are available that can mark which voxels are part of a nodule. The question is, how to combine these expert opinions to estimate the unknown ground truth. We present the Veritas algorithm that predicts the underlying label using the knowledge in the expert opinions even without the benefit of any labeled data for training. We evaluate Veritas using artificial data and real CT images to which synthetic nodules have been added, providing a known ground truth.
AB - We consider a variation of the problem of combining expert opinions for the situation in which there is no ground truth to use for training. Even though we do not have labeled data, the goal of this work is quite different from an unsupervised learning problem in which the goal is to cluster the data. Our work is motivated by the application of segmenting a lung nodule in a computed tomography (CT) scan of the human chest. The lack of a gold standard of truth is a critical problem in medical imaging. A variety of experts, both human and computer algorithms, are available that can mark which voxels are part of a nodule. The question is, how to combine these expert opinions to estimate the unknown ground truth. We present the Veritas algorithm that predicts the underlying label using the knowledge in the expert opinions even without the benefit of any labeled data for training. We evaluate Veritas using artificial data and real CT images to which synthetic nodules have been added, providing a known ground truth.
KW - Boosting
KW - Combining experts
KW - Interobserver variability
KW - Machine learning
KW - Medical images
UR - http://www.scopus.com/inward/record.url?scp=71049180673&partnerID=8YFLogxK
U2 - 10.1142/S0218213009000330
DO - 10.1142/S0218213009000330
M3 - Article
AN - SCOPUS:71049180673
SN - 0218-2130
VL - 18
SP - 633
EP - 651
JO - International Journal on Artificial Intelligence Tools
JF - International Journal on Artificial Intelligence Tools
IS - 5
ER -