TY - GEN
T1 - Classification of breast-tissue microarray spots using colour and local invariants
AU - Amaral, Telmo
AU - McKenna, Stephen
AU - Robertson, Katherine
AU - Thompson, Alastair
N1 - Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
PY - 2008
Y1 - 2008
N2 - Breast tissue microarrays facilitate the survey of very large numbers of tumours but their scoring by pathologists is time consuming, typically highly quantised and not without error. Automated segmentation of cells and intra-cellular compartments in such data can be problematic for reasons that include cell overlapping, complex tissue structure, debris, and variable appearance. This paper proposes a computationally efficient approach that uses colour and differential invariants to assign class posterior probabilities to pixels and then performs probabilistic classification of TMA spots using features analogous to the Quickscore system currently used by pathologists. It does not rely on accurate segmentation of individual cells. Classification performance at both pixel and spot levels was assessed using 110 spots from the Adjuvant Breast Cancer (ABC) Chemotherapy Trial. The use of differential invariants in addition to colour yielded a small improvement in accuracy. Some reasons for classification results in disagreement with pathologist-provided labels are discussed and include noise in the class labels.
AB - Breast tissue microarrays facilitate the survey of very large numbers of tumours but their scoring by pathologists is time consuming, typically highly quantised and not without error. Automated segmentation of cells and intra-cellular compartments in such data can be problematic for reasons that include cell overlapping, complex tissue structure, debris, and variable appearance. This paper proposes a computationally efficient approach that uses colour and differential invariants to assign class posterior probabilities to pixels and then performs probabilistic classification of TMA spots using features analogous to the Quickscore system currently used by pathologists. It does not rely on accurate segmentation of individual cells. Classification performance at both pixel and spot levels was assessed using 110 spots from the Adjuvant Breast Cancer (ABC) Chemotherapy Trial. The use of differential invariants in addition to colour yielded a small improvement in accuracy. Some reasons for classification results in disagreement with pathologist-provided labels are discussed and include noise in the class labels.
KW - Biological tissues
KW - Image texture analysis
UR - http://www.scopus.com/inward/record.url?scp=51049094185&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=51049094185&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2008.4541167
DO - 10.1109/ISBI.2008.4541167
M3 - Conference contribution
AN - SCOPUS:51049094185
SN - 9781424420032
T3 - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI
SP - 999
EP - 1002
BT - 2008 5th IEEE International Symposium on Biomedical Imaging
T2 - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI
Y2 - 14 May 2008 through 17 May 2008
ER -