An automated prognosis system for estrogen hormone status assessment in breast cancer tissue samples


Sarıkoç F., KALINLI A., AKGÜN H., ÖZTÜRK F.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.21, sa.4, ss.1199-1221, 2013 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 21 Sayı: 4
  • Basım Tarihi: 2013
  • Doi Numarası: 10.3906/elk-1111-10
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.1199-1221
  • Anahtar Kelimeler: Image processing, nucleus classification, segmentation, functional trees, estrogen receptor status evaluation, breast cancer prognosis, Allred scoring, machine learning, IMAGE-ANALYSIS, RECEPTOR STATUS, QUANTITATIVE-ANALYSIS, PROTEIN EXPRESSION, HISTOLOGICAL GRADE, TEXTURE ANALYSIS, IMMUNOHISTOCHEMISTRY, QUANTIFICATION, MICROARRAYS, CARCINOMAS
  • Erciyes Üniversitesi Adresli: Evet

Özet

Estrogen receptor (ER) status evaluation is a widely applied method in the prognosis of breast cancer. However, testing for the existence of the ER biomarker in a patient's tumor sample mainly depends on the subjective decisions of the doctors. The aim of this paper is to introduce the usage of a machine learning tool, functional trees (FTs), to attain an ER prognosis of the disease via an objective decision model. For this aim, 27 image files, each of which came from a biopsy sample of an invasive ductal carcinoma patient, were scanned and captured by a light microscope. From these images, 5150 nuclei were segmented with image processing methods. Several attributes, including statistical, wavelet, cooccurrence matrix, and Laws' texture features, were calculated inside the border area of each nucleus. A FT was trained over the feature dataset using a 10-fold cross-validation and then the obtained model was tested on a separate dataset. The assessment results of the model were compared with those of 2 experts. Consequently, the weighted kappa coefficient indicated a very good agreement (kappa = 0.899 and kappa = 0.927, P < 0.001) and the Spearman's rank order correlation showed a high level of correlation (rho = 0.963 and rho = 0.943, P < 0.001) between the results of the FT and those of the observers. The Wilcoxon test revealed that there was no significant difference between the results of the experts and the model (P = 0.051 and P = 0.316). Finally, it was concluded from the results that the FT could be used as a tool to support the decision of doctors by indicating consistent outputs and hence contribute to the objectiveness and reproducibility of the assessment results.