Penn Medicine Researchers Forecast 10-Year Breast Cancer Recurrence with MRI Scan

Penn Medicine Researchers Forecast 10-Year Breast Cancer Recurrence with MRI Scan

Penn Medicine researchers are utilizing Magnetic Resonance Imaging (MRI) and an emerging field of medicine known as radiomics—which uses algorithms to extract a large amount of features from medical images—to improve characterization of the heterogeneity of cancer cells within a tumor while allowing for superior understanding of the causes and progression of an individual’s disease.

Why is this Important?

Diverse diseases such as breast cancer present challenges for clinicians, specifically on a cellular level. For example, one patient tumor may differ from another’s, the cells within the tumor of a single patient can vary greatly—which represents a potentially problematic situation when we consider that an examination of a tumor usually relies on a biopsy, which only captures a small sample of cells. Penn Medicine’s novel advancements uses imaging to characterize the genetic makeup of tumors, paving the way for individualized, non-invasive treatment.

The Study

The recent study findings, published in Clinical Cancer Research, focused on how the researchers could use imaging and radiomics of more personalized tumor characterization. Using MRI, the team extracted 60 radiomic features, or biomarkers, from 95 women and primary invasive breast cancer. After following up with the patients a decade later, the group found that a scan that showed high tumor heterogeneity at the time of diagnosis—meaning a high diversity of cells—could successfully predict a cancer recurrence.

The research team retrospectively analyzed patient scans from a 2002-2006 clinical trial conducted at Penn Medicine. For each women, the team generated a “signal enhancement ration” (SER) map and from it, extracted various imaging features in order to understand the relationship between those features and conventional biomarkers (such as gene mutations or hormone receptor status) and patient outcomes.

The Finding

The study team’s algorithm was able to successfully predict recurrence-free survival after a decade. To validate their findings, the group compared their results to an independent sample of 163 patients with breast cancer from the publicly available Cancer Imaging Archive.

Investigator Comment

Despina Kontos, PhD, associate professor of Radiology in the Perelman School of Medicine at the University of Pennsylvania, “If we’re only taking out a little piece of a tissue from one part of a tumor, that doesn’t give the full picture of a person’s disease and of his or her response to specific therapies.” We know that in a lot of instances, patients are over-treated, getting therapy that may not be beneficial. Or, conversely, patients who need more aggressive therapy may not end up receiving it. The method we currently have for choosing the appropriate treatment for patients with breast cancer is not perfect, so the more steps we can take toward more personalized treatment approaches, the better.

Lead Research/Investigator

Despina Kontos, PhD 

Rhea Chitalia

Call to Action: Kontos reports, “We’ve just touched the tip of the iceberg. “Our results and the validation study give us confidence that there are many opportunities for these markers to be used in a prognostic and potentially a predictive setting.”