Elizabeth J. Sutton MD, Presenter: Nothing to Disclose

Jung Hun Oh PhD, Abstract Co-Author: Nothing to Disclose

Brittany Dashevsky MD, DPhil, Abstract Co-Author: Nothing to Disclose

Harini Veeraraghavan, Abstract Co-Author: Nothing to Disclose

Joseph Owen Deasy PhD, Abstract Co-Author: Nothing to Disclose

Elizabeth A. Morris MD, Abstract Co-Author: Nothing to Disclose

Aditya Prakash Apte PhD, Abstract Co-Author: Nothing to Disclose

Girard Gibbons BA, Abstract Co-Author: Nothing to Disclose

Oncotype Dx® Breast Cancer 21-gene Assay Recurrence Score (RS) is used clinically in early stage estrogen receptor (ER) positive breast cancer to quantify (range 0-100) the likelihood (increased with score) of recurrence and magnitude of chemotherapy benefit. The purpose of this study was to investigate the association between Oncotype Dx® RS and texture features extracted from magnetic resonance imaging (MRI).

This retrospective study received institutional review board approval and need for informed consent waived. Between 2006-2012, we identified women with: a) ER+, progesterone receptor positive (PR+) and HER2 negative invasive ductal carcinoma (IDC); b) Preoperative breast MRI; c) Oncotype Dx® RS. Clinical and pathologic data were collected. Tumors were contoured on the fat-suppressed T1-weight pre- and three post-contrast images. Shape-, texture- and histogram-based features were extracted using in-house software (Computational Environment for Radiological Research). Linear regression analysis was performed to investigate the association between Oncotype Dx® RS and different clinical, pathologic and imaging features.

Ninety-five ER+, PR+ and HER2- patients were included in the study sample with a median Oncotype Dx® RS of 16 (range 0–45). The median follow-up time was 33.3 months (range: 0.2-57.3 months) and at the end of follow-up, no patients had recurred or died. In univariate linear regression analysis, three features significantly correlated with Oncotype Dx® RS: nuclear grade and two kurtosis features with p=0.0105, 0.0056, and 0.0005, respectively. Using these three features, multiple linear regression analysis was performed, resulting in significant correlation with Oncotype Dx® RS with R-squared = 0.228 (p = 0.0002) and Spearman’s rank correlation coefficient = 0.485 (p < 0.0001). 

IDC computer-derived imaging features correlate with Oncotype Dx® RS suggesting, that these are image-based biomarkers that reflect the likelihood of recurrence and magnitude of chemotherapy benefit. Further investigation on larger datasets is necessary to validate this observation. 

Computer-derived imaging features significantly correlate with Oncotype Dx® RS, which is a clinically validated genetic test that directs treatment.

Sutton, E, Oh, J, Dashevsky, B, Veeraraghavan, H, Deasy, J, Morris, E, Apte, A, Gibbons, G, Association between Oncotype Dx® Breast Cancer 21-gene Assay Recurrence Score and Computer-derived Imaging Features.  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14011991.html