Dr. Pollack on the Role of Radiomics in Sarcoma

Seth M. Pollack, MD
Published Online: Monday, Dec 12, 2016



Seth M. Pollack, assistant professor, Division of Oncology, University of Washington, and attending physician, Seattle Cancer Care Alliance, discusses the role of radiomics in the treatment landscape of sarcoma.

Radiomics, which is a fairly new field of study, quantifies complex aspects of tumor images related to tumor biology. Prior research has validated its use in predicting patient outcomes in lung and head and neck cancers.

According to Pollack, sarcoma may be an ideal treatment landscape in which to study radiomics because so many patients with this disease already undergo MRIs as part of their overall treatment. This essentially provided the rationale for examining radiomics in this particular patient population.

In his research, Pollack found that, after patients' tumor images were analyzed through a list of radiomic features, the model that was made to predict outcomes was extremely accurate. In fact, it was found to be more accurately predictive than other standard factors, such as those based on tumor grade, tumor size, and other clinical features.

Next steps, says Pollack, should move to validate these data in other patient cohorts.


Seth M. Pollack, assistant professor, Division of Oncology, University of Washington, and attending physician, Seattle Cancer Care Alliance, discusses the role of radiomics in the treatment landscape of sarcoma.

Radiomics, which is a fairly new field of study, quantifies complex aspects of tumor images related to tumor biology. Prior research has validated its use in predicting patient outcomes in lung and head and neck cancers.

According to Pollack, sarcoma may be an ideal treatment landscape in which to study radiomics because so many patients with this disease already undergo MRIs as part of their overall treatment. This essentially provided the rationale for examining radiomics in this particular patient population.

In his research, Pollack found that, after patients' tumor images were analyzed through a list of radiomic features, the model that was made to predict outcomes was extremely accurate. In fact, it was found to be more accurately predictive than other standard factors, such as those based on tumor grade, tumor size, and other clinical features.

Next steps, says Pollack, should move to validate these data in other patient cohorts.



View Conference Coverage
Online CME Activities
TitleExpiration DateCME Credits
Medical Crossfire®: Optimizing Treatment and Management of Soft Tissue Sarcoma in Community OncologyNov 30, 20171.5
Moving Forward From the Status Quo for the Treatment of Soft Tissue Sarcoma: Key Questions & New Answers to Optimize OutcomesAug 16, 20181.5
Publication Bottom Border
Border Publication