MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer.

BACKGROUND: To use clinical and MRI radiomic features coupled with machine learning to assess HER2 expression level and predict pathologic response (pCR) in HER2 overexpressing breast cancer patients receiving neoadjuvant chemotherapy (NAC). METHODS: This retrospective study included 311 patients. pCR was defined as no residual invasive carcinoma in the breast or axillary lymph nodes (ypT0/isN0). Radiomics/statistical analysis was performed using MATLAB and CERR software. After ROC and correlation analysis, selected radiomics parameters were advanced to machine learning modelling alongside clinical MRI-based parameters (lesion type, multifocality, size, nodal status). For predicting pCR, the data was split into a training and test set (80:20). FINDINGS: The overall pCR rate was 60.5% (188/311). The final model to predict HER2 heterogeneity utilised three MRI parameters (two clinical, one radiomic) for a sensitivity of 99.3% (277/279), specificity of 81.3% (26/32), and diagnostic accuracy of 97.4% (303/311). The final model to predict pCR included six MRI parameters (two clinical, four radiomic) for a sensitivity of 86.5% (32/37), specificity of 80.0% (20/25), and diagnostic accuracy of 83.9% (52/62) (test set); these results were independent of age and ER status, and outperformed the best model developed using clinical parameters only (p=0.029, comparison of proportion Chi-squared test). INTERPRETATION: The machine learning models, including both clinical and radiomics MRI features, can be used to assess HER2 expression level and can predict pCR after NAC in HER2 overexpressing breast cancer patients. FUNDING: NIH/NCI (P30CA008748), Susan G. Komen Foundation, Breast Cancer Research Foundation, Spanish Foundation Alfonso Martin Escudero, European School of Radiology.

Gene expression profiling of lobular carcinoma in situ reveals candidate precursor genes for invasion.

PURPOSE: Lobular carcinoma in situ (LCIS) is both a risk indicator and non-obligate precursor of invasive lobular carcinoma (ILC). We sought to characterize the transcriptomic features of LCIS and ILC, with a focus on the identification of intrinsic molecular subtypes of LCIS and the changes involved in the progression from normal breast epithelium to LCIS and ILC. METHODS: Fresh-frozen classic LCIS, classic ILC, and normal breast epithelium (N) from women undergoing prophylactic or therapeutic mastectomy were prospectively collected, laser-capture microdissected, and subjected to gene expression profiling using Affymetrix HG-U133A 2.0 microarrays. RESULTS: Unsupervised hierarchical clustering of 40 LCIS samples identified 2 clusters of LCIS distinguished by 6431 probe sets (p < 0.001). Genes identifying the clusters included proliferation genes and other genes related to cancer canonical pathways such as TGF beta signaling, p53 signaling, actin cytoskeleton, apoptosis and Wnt-Signaling pathway. A supervised analysis to identify differentially expressed genes (p < 0.001) between normal epithelium, LCIS, and ILC, using 23 patient-matched triplets of N, LCIS, and ILC, identified 169 candidate precursor genes, which likely play a role in LCIS progression, including PIK3R1, GOLM1, and GPR137B. These potential precursor genes map significantly more frequently to 1q and 16q, regions frequently targeted by gene copy number alterations in LCIS and ILC. CONCLUSION: Here we demonstrate that classic LCIS is a heterogeneous disease at the transcriptomic level and identify potential precursor genes in lobular carcinogenesis. Understanding the molecular heterogeneity of LCIS and the potential role of these potential precursor genes may help personalize the therapy of patients with LCIS.