Automated Tubule Nuclei Quantification and Correlation with Oncotype DX risk categories in ER+ Breast Cancer Whole Slide Images

• DOI: 10.1038/srep32706
• Publication Date: 2016-09-07T10:04:52Z
• Authors: David Romo-Bucheli; Andrew Janowczyk; Hannah Gilmore; Eduardo Romero; Anant Madabhushi
• Keywords: Grading (engineering)

Abstract Early stage estrogen receptor positive (ER+) breast cancer (BCa) treatment is based on the presumed aggressiveness and likelihood of recurrence. Oncotype DX (ODX) other gene expression tests have allowed for distinguishing more aggressive ER+ BCa requiring adjuvant chemotherapy from less cancers benefiting hormonal therapy alone. However these are expensive, tissue destructive require specialized facilities. Interestingly grade has been shown to be correlated with ODX risk score. Unfortunately Bloom-Richardson (BR) determined by pathologists can variable. A constituent category in BR grading tubule formation. This study aims develop a deep learning classifier automatically identify nuclei whole slide images (WSI) BCa, hypothesis being that ratio overall number (a formation indicator - TFI) correlates corresponding categories. correlation was assessed 7513 fields extracted 174 WSI. The results suggests low ODX/BR cases larger TFI than high ( p < 0.01). also presented obtained rest 0.05). Finally, significantly smaller