TY - GEN
T1 - Scoring of breast tissue microarray spots through ordinal regression
AU - Amaral, Telmo
AU - McKenna, Stephen
AU - Robertson, Katherine
AU - Thompson, Alastair
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2009
Y1 - 2009
N2 - Breast tissue microarrays (TMA5) facilitate the study of very large numbers of breast tumours in a single histological section, but their scoring by pathologists is time consuming, typically highly quantised, and not without error. This paper compares the results of different classification and ordinal reression algorithms trained to predict the scores of immunostained breast TMA spots, based on spot features obtained in previous work by the authors. Despite certain theoretical advantages, Gaussian process ordinal regression failed to achieve any clear performance gain over classification using a multi-layer perceptron. The use of the entropy of the posterior probability distribution over class labels for avoiding uncertain decisions is demonstrated.
AB - Breast tissue microarrays (TMA5) facilitate the study of very large numbers of breast tumours in a single histological section, but their scoring by pathologists is time consuming, typically highly quantised, and not without error. This paper compares the results of different classification and ordinal reression algorithms trained to predict the scores of immunostained breast TMA spots, based on spot features obtained in previous work by the authors. Despite certain theoretical advantages, Gaussian process ordinal regression failed to achieve any clear performance gain over classification using a multi-layer perceptron. The use of the entropy of the posterior probability distribution over class labels for avoiding uncertain decisions is demonstrated.
KW - Breast tissue microarrays
KW - Immunohistochemistry
KW - Ordinal regression
KW - Scoring
UR - http://www.scopus.com/inward/record.url?scp=70349267653&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70349267653&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:70349267653
SN - 9789898111692
T3 - VISAPP 2009 - Proceedings of the 4th International Conference on Computer Vision Theory and Applications
SP - 243
EP - 248
BT - VISAPP 2009 - Proceedings of the 4th International Conference on Computer Vision Theory and Applications
T2 - 4th International Conference on Computer Vision Theory and Applications, VISAPP 2009
Y2 - 5 February 2009 through 8 February 2009
ER -