A study from researchers at Penn Medicine revealed that MRI and an algorithm-based field of medicine called radiomics could help characterize the heterogeneity of cancer cells in a tumor and allow for better understanding of the causes and progression of individual diseases.
The study, published in Clinical Cancer Research, examines radiomics, which uses algorithms to extract features from medical images, according to a news release.
Using MRI, the researchers extracted 60 radiomic features (biomarkers) from 95 women with primary invasive breast cancer. At 10-year follow-up, the data showed that a scan that showed high tumor heterogeneity at the time of diagnosis could successfully predict a cancer recurrence.
Retrospectively analyzed scans from a clinical trial conducted from 2002 to 2006 showed that the algorithm was able to successfully predict recurrence-free survival after 10 years. For each woman, a “signal enhancement ratio” map was generated, offering imaging features that helped understand the relationship between those features, conventional biomarkers and patient outcomes.
The research group validated its findings by comparing the results to an independent sample of 163 patients with breast cancer from the Cancer Imaging Archive.
According to the study, imaging may not completely replace the need for tumor biopsies. However, the new methods may augment the current standard of care by offering more detail for a patient’s disease and guiding personalized treatment. The research group plans to expand the analysis to a larger number of patients and explore which markers are more predictive of particular outcomes.
“If we’re only taking out a little piece of a tissue from one part of a tumor, that does not give the full picture of a person’s disease and of his or her response to specific therapies,” associate professor of radiology at the Perelman School of Medicine at the University of Pennsylvania and principal investigator Despina Kontos said in the release. “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.”
“Our study shows that imaging has the potential to capture the whole tumor’s behavior without doing a procedure that is invasive or limited by sampling error,” added the study’s lead author Rhea Chitalia, a PhD candidate in the School of Engineering and Applied Science at the University of Pennsylvania. “Women who had more heterogeneous tumors tended to have a greater risk of tumor recurrence.”
“We’ve just touched the tip of the iceberg,” Kontos said. “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.”