Optoacoustic Imaging and Gray-Scale US Features of Breast Cancers: Correlation with Molecular Subtypes

Background: Optoacoustic imaging can assess tumor hypoxia coregistered with US gray-scale images. The combination of optoacoustic imaging and US may have a role in distinguishing breast cancer molecular subtypes. Purpose: To investigate whether optoacoustic US feature scores correlate with breast cancer molecular subtypes. Materials and Methods: A total of 1972 women (with a total of 2055 breast masses) underwent prebiopsy optoacoustic US in a prospective multi-institutional study between December 2012 and September 2015. Seven readers blinded to pathologic diagnosis scored gray-scale US and optoacoustic US features of the known cancers. Optoacoustic US features within (internal) and outside of the tumor boundary (external) were scored. Immunohistochemistry findings were obtained from pathology reports. Multinomial logistic regression analysis was used to fit the US scores, adding optoacoustic US features to the model to investigate the incremental benefit of each feature. Kruskal-Wallis tests were used to analyze the relationship between molecular subtypes and feature scores. Results: Among 653 invasive cancers identified in 629 women, a total of 532 cancers in 519 women, all of which had molecular markers available, were included in the analysis. Mean age +/- standard deviation was 57.9 years +/- 12.6. Mean total external optoacoustic US feature scores of luminal (A and B) breast cancers were higher (9.9 vs 8.8; P < .05) and total internal scores were lower(6.8 vs 7.7; P < .001) than those of triple-negative and human epidermal growth factor receptor 2-positive (HER2+) cancers. A multinomial logistic regression model showed that optoacoustic internal vessel (odds ratio [OR], 0.6; 95% confidence interval [CI]:0.5, 0.8; P = .002), optoacoustic internal blush (OR, 0.7; 95% CI: 0.5, 0.9; P = .02), and optoacoustic internal hemoglobin (OR,0.6; 95% CI: 0.5, 0.8; P = .001) were associated with classification of luminal versus triple-negative and HER2+ cancer subtypes. Conclusion: Combined optoacoustic US imaging and gray-scale US features may help distinguish luminal breast cancers from triple-negative and human epidermal growth factor receptor 2-positive cancers. (C) RSNA, 2019