Quantitative assessment of distant recurrence risk in early stage breast cancer using a nonlinear combination of pathological, clinical and imaging variables. Issue 10 (3rd August 2020)

• Record Type: Journal Article
• Authors: Nichols, Brandon S.; Chelales, Erika; Wang, Roujia; Schulman, Amanda; Gallagher, Jennifer; Greenup, Rachel A.; Geradts, Joseph; Harter, Josephine; Marcom, Paul K.; Wilke, Lee G.; Ramanujam, Nirmala
• Is Part Of: Journal of biophotonics. Volume 13:Issue 10(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-08-03
• Subjects: breast density -- breast neoplasms -- genomics -- neoplasm recurrence -- neural networks; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.201960235
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: Use of genomic assays to determine distant recurrence risk in patients with early stage breast cancer has expanded and is now included in the American Joint Committee on Cancer staging manual. Algorithmic alternatives using standard clinical and pathology information may provide equivalent benefit in settings where genomic tests, such as OncotypeDx, are unavailable. We developed an artificial neural network (ANN) model to nonlinearly estimate risk of distant cancer recurrence. In addition to clinical and pathological variables, we enhanced our model using intraoperatively determined global mammographic breast density (MBD) and local breast density (LBD). LBD was measured with optical spectral imaging capable of sensing regional concentrations of tissue constituents. A cohort of 56 ER+ patients with an OncotypeDx score was evaluated. We demonstrated that combining MBD/LBD measurements with clinical and pathological variables improves distant recurrence risk prediction accuracy, with high correlation ( r = 0.98) to the OncotypeDx recurrence score. Abstract : The inclusion of global breast density (obtained via mammography) as well as the inclusion of local variations in breast density (obtained via optical spectral imaging) improve OncotypeDx prediction when combined with clinicopathological variables. The relationship between these input variables is inherently nonlinear, thus the use of artificial neural networks improves OncotypeDx prediction compared wth linear methods.