Dania Daye and colleagues collected dynamic contrast-enhanced breast MRI images from 61 women diagnosed with estrogen-receptor-positive/node-negative invasive breast cancer. The women had Oncotype DX (GenomicHealth) tumor profiling.
Two readers assessed the following tumor-specific features: disease multifocality, lesion size, lesion shape, margin morphology, enhancement amount, enhancement morphology, and associated nonmass enhancement. Daye's team used multiclass linear discriminant analysis to assess any link between tumor features and the Oncotype DX recurrence risk category.
Lesions that were multifocal and larger tended to have an increased recurrence risk, leading Daye's team to conclude that MRI tumor features can help clinicians predict the recurrence risk category as determined by the Oncotype DX assay.
