Radiogenomics analysis identifies correlations of digital mammography with clinical molecular signatures in breast cancer

• Published in: PloS one 2018-03, Vol.13 (3), p.e0193871-e0193871
• Main Authors: Tamez-Peña, Jose-Gerardo, Rodriguez-Rojas, Juan-Andrés, Gomez-Rueda, Hugo, Celaya-Padilla, Jose-Maria, Rivera-Prieto, Roxana-Alicia, Palacios-Corona, Rebeca, Garza-Montemayor, Margarita, Cardona-Huerta, Servando, Treviño, Victor
• Format: Article
• Language: English
• Subjects: Biology and Life Sciences; Biomarkers; Biopsy; Breast cancer; Cancer; Care and treatment; Correlation; Correlation analysis; Correlation coefficient; Correlation coefficients; Diagnosis; Digital signatures; DNA microarrays; Fractal models; Gene expression; Generalized linear models; Genetic aspects; Genomics; Health aspects; Health risks; Image coding; Mammography; Medical screening; Medicine and Health Sciences; Multivariate analysis; NMR; Nuclear magnetic resonance; Phenotypes; Physical Sciences; Physiological aspects; Progesterone; Research and Analysis Methods; Signal distribution; Survival analysis; Tumors; Wavelet transforms
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0193871

In breast cancer, well-known gene expression subtypes have been related to a specific clinical outcome. However, their impact on the breast tissue phenotype has been poorly studied. Here, we investigate the association of imaging data of tumors to gene expression signatures from 71 patients with breast cancer that underwent pre-treatment digital mammograms and tumor biopsies. From digital mammograms, a semi-automated radiogenomics analysis generated 1,078 features describing the shape, signal distribution, and texture of tumors along their contralateral image used as control. From tumor biopsy, we estimated the OncotypeDX and PAM50 recurrence scores using gene expression microarrays. Then, we used multivariate analysis under stringent cross-validation to train models predicting recurrence scores. Few univariate features reached Spearman correlation coefficients above 0.4. Nevertheless, multivariate analysis yielded significantly correlated models for both signatures (correlation of OncotypeDX = 0.49 ± 0.07 and PAM50 = 0.32 ± 0.10 in stringent cross-validation and OncotypeDX = 0.83 and PAM50 = 0.78 for a unique model). Equivalent models trained from the unaffected contralateral breast were not correlated suggesting that the image signatures were tumor-specific and that overfitting was not a considerable issue. We also noted that models were improved by combining clinical information (triple negative status and progesterone receptor). The models used mostly wavelets and fractal features suggesting their importance to capture tumor information. Our results suggest that molecular-based recurrence risk and breast cancer subtypes have observable radiographic phenotypes. To our knowledge, this is the first study associating mammographic information to gene expression recurrence signatures.