Letter to the Editor: Breast cancer subtypes may obscure robust classification of breast tumors with brain metastases from other cancers

by Kadri Altundag (altundag66@yahoo.com)

Ortiz-Ramón, R., Larroza, A., Ruiz-España, S. et al. Eur Radiol (2018). https://doi.org/10.1007/s00330-018-5463-6

Dear Editor,

I want to congratulate Ortiz-Ramón and colleagues for their article [1] in which they investigated the capability of MRI texture analysis to differentiate the primary site of origin of brain metastases (BM) following a radiomics approach. They found that high accuracy was obtained when differentiating lung cancer BM from breast cancer BM and melanoma BM using the optimal datasets. However, classification of breast cancer and melanoma BM was unsatisfactory. Although the authors did not mention rate of each breast cancer subtypes with BM, I think that unsatisfactory results for breast cancer classification might come from different molecular subtypes of breast cancer that may obscure robust classification of breast tumors from others. For example, triple negative or HER-2 positive breast cancer with BM reflect high proliferative histopathological features with higher ki-67index compared to luminal breast tumors with lower proliferative caharacteristics which in turn might complicate classification of breast cancer from other tumors.