A methodology for automatic classification of breast cancer immunohistochemical data using semi-supervised Fuzzy c-means

Lai, Daphne; Garibaldi, Jonathan; Soria, Daniele; Roadknight, Christopher
September 2014
Central European Journal of Operations Research;Sep2014, Vol. 22 Issue 3, p475
Academic Journal
Previously, a semi-manual method was used to identify six novel and clinically useful classes in the Nottingham Tenovus Breast Cancer dataset. 663 out of 1,076 patients were classified. The objectives of our work is three folds. Firstly, our primary objective is to use one single automatic method (post-initialisation) to reproduce the six classes for the 663 patients and to classify the remaining 413 patients. Secondly, we explore using semi-supervised fuzzy c-means with various distance metrics and initialisation techniques to achieve this. Thirdly, the clinical characteristics of the 413 patients are examined by comparing with the 663 patients. Our experiments use various amount of labelled data and 10-fold cross validation to reproduce and evaluate the classification. ssFCM with Euclidean distance and initialisation technique by Katsavounidis et al. produced the best results. It is then used to classify the 413 patients. Visual evaluation of the 413 patients' classifications revealed common characteristics as those previously reported. Examination of clinical characteristics indicates significant associations between classification and clinical parameters. More importantly, association between classification and survival based on the survival curves is shown.


Related Articles

  • A novel approach to cutting decision trees. Üney-Yüksektepe, Fadime // Central European Journal of Operations Research;Sep2014, Vol. 22 Issue 3, p553 

    In data mining, binary classification has a wide range of applications. Cutting Decision Tree (CDT) induction is an efficient mathematical programming based method that tries to discretize the data set on hand by using multiple separating hyperplanes. A new improvement to CDT model is proposed...

  • The Discovery of Novel Biomarkers Improves Breast Cancer Intrinsic Subtype Prediction and Reconciles the Labels in the METABRIC Data Set. Milioli, Heloisa Helena; Vimieiro, Renato; Riveros, Carlos; Tishchenko, Inna; Berretta, Regina; Moscato, Pablo // PLoS ONE;7/1/2015, Vol. 10 Issue 7, p1 

    Background: The prediction of breast cancer intrinsic subtypes has been introduced as a valuable strategy to determine patient diagnosis and prognosis, and therapy response. The PAM50 method, based on the expression levels of 50 genes, uses a single sample predictor model to assign subtype...

  • Breast cancer genome anatomy: correlation of morphological changes in breast carcinomas with expression of the novel gene product Di12. Burger, Angelika; Li, Hua; Zhang, Xian-Kui; Pienkowska, Malgorzata; Venanzoni, Marco; Vournakis, John; Papas, Takis; Seth, Arun // Oncogene;1/22/98, Vol. 16 Issue 3, p327 

    To determine which genes may be activated or inactivated during breast cancer development, we employed two cloning strategies (subtractive hybridization and differential display) using RNA samples from a human breast tumor and its matching normal breast cell line. Of 950 clones isolated, 102...

  • A role for BRCA1 in sporadic breast cancer. Fraser, J.A.; Reeves, J.R.; Stanton, P.D.; Black, D.M.; Going, J.J.; Cooke, T.G.; Bartlett, J.M.S. // British Journal of Cancer;4/22/2003, Vol. 88 Issue 8, p1263 

    To test the hypothesis that altered expression of BRCA1 protein may play an important role in sporadic breast cancer development, 50 randomly selected primary breast cancers (frozen sections, 5 years' median follow-up) were immunolabelled with two monoclonal BRCA1 antibodies (MS110 and MS13)....

  • Elevated expression of eIF4E and FGF-2 isoforms during vascularization of breast carcinomas. Nathan, Cherie-Ann; Carter, Peggy; Liu, Li; Li, Benjamin DL; Abreo, Fleurette; Tudor, Ann; Zimmer, Stephen G; De Benedetti, Arrigo // Oncogene;8/28/97, Vol. 15 Issue 9, p1087 

    The translation initiation factor eIF4E is a novel proto-oncogene found over expressed in most breast carcinomas (Kerekatte et al., 1995), but the pathology where this elevation is initially manifested and its possible role in cancer progression are unknown. We report that eIF4E is markedly...

  • 17 β -Hydroxysteroid dehydrogenase type 1 and type 2 in human breast carcinoma: a correlation to clinicopathological parameters. Suzuki, T; Moriya, T; Ariga, N; Kaneko, C; Kanazawa, M; Sasano, H // British Journal of Cancer;2/1/2000, Vol. 82 Issue 3, p518 

    The expression of 17β-hydroxysteroid dehydrogenase (17β-HSD) type 1 and type 2 was examined immunohistochemically in 111 invasive ductal carcinomas, and correlated with various clinicopathological parameters. This study investigates local regulatory mechanisms of oestrogens in human breast...

  • CGH analysis of ductal carcinoma of the breast with basaloid/myoepithelial cell differentiation. Jones, C; Nonni, A V; Fulford, L; Merrett, S; Chaggar, R; Eusebi, V; Lakhani, S R // British Journal of Cancer;8/1/2001, Vol. 85 Issue 3, p422 

    2-18% of ductal carcinoma-No Special Type (NST) are reported to express basal cell keratin 14 and such tumours may have a different metastatic pattern and prognosis. We performed immunohistochemistry for cytokeratins 19 (luminal) and 14 (basal) on 92 ductal carcinoma-NST. Those tumours showing...

  • E-cadherin as a prognostic indicator in primary breast cancer. Parker, C; Rampaul, R S; Pinder, S E; Bell, J A; Wencyk, P M; Blamey, R W; Nicholson, R I; Robertson, J F R // British Journal of Cancer;12/15/2001, Vol. 85 Issue 12, p1958 

    Epithelial cadherin (E-CD) is a member of the cadherin family of cell adhesion molecules and has been implicated as an invasion suppressor molecule in vitro and in vivo. We analysed 174 breast tumours from the Nottingham/Tenovus Breast Cancer Series immunohistochemically for E-CD expression...

  • Prognostic importance of survivin in breast cancer. Kennedy, S M; O'Driscoll, L; Purcell, R; Fitz-simons, N; McDermott, E W; Hill, A D; O'Higgins, N J; Parkinson, M; Linehan, R; Clynes, M // British Journal of Cancer;4/7/2003, Vol. 88 Issue 7, p1077 

    Survivin is a member of the inhibitor of apoptosis (IAP) family, and is also involved in the regulation of cell division. Survivin is widely expressed in foetal tissues and in human cancers, but generally not in normal adult tissue. This study examined the expression of surviving protein in a...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics