MedicalResearch.com Interview with:
Dr. Pallavi Tiwari PhD
Assistant Professor biomedical engineering
Case Western Reserve University
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: One of the biggest challenges in neuro-oncology currently is distinguishing radionecrosis, a side-effect of aggressive radiation, from tumor recurrence on imaging. Surgical intervention is the only means of definitive diagnosis, but suffers from considerable morbidity and mortality. The treatments for radionecrosis and cancer recurrence are very different. Early identification of the two conditions can help speed prognosis, therapy, and improve patient outcomes.
The purpose of this feasibility study was to evaluate the role of machine learning algorithms along with computer extracted texture features, also known as radiomic features, in distinguishing radionecrosis and tumor recurrence on routine MRI scans (T1w, T2w, FLAIR). The radiomic algorithms were trained on 43 studies from our local collaborating institution – University Hospitals Case Medical Center, and tested on 15 studies at a collaborating institution, University of Texas Southwest Medical Center. We further compared the performance of the radiomic techniques with two expert readers.
Our results demonstrated that radiomic features can identify subtle differences in quantitative measurements of tumor heterogeneity on routine MRIs, that are not visually appreciable to human readers. Of the 15 test studies, the radiomics algorithm could identify 12 of 15 correctly, while expert 1 could identify 7 of 15, and expert 2, 8 of 15.
MedicalResearch.com: What should readers take away from your report?
Response: The take-away message for this work is that the computer extracted radiomic features may provide complementary information regarding tumor heterogeneity and breakdown in architecture on MRI; features that can assist in distinction of radionecrosis from tumor recurrence on routinely acquired MRI scans (T1w, T2w, and FLAIR), and may not be visually discernible to expert readers.
MedicalResearch.com: What recommendations do you have for future research as a result of this study?
Response: Our future study would be based on performing a joint assessment of the radiomic features along with the diagnostic reads from expert radiologists as a part of a prospective clinical study. This will allow us to understand the added value of radiomic features over and above the diagnostic reads from routine imaging scans. We are also currently working on evaluating the stability and efficacy of radiomic features across studies from multiple-institutions in distinguishing radionecrosis from tumor recurrence.
MedicalResearch.com: Is there anything else you would like to add?
Response: While the radiomic features outperformed human reads in this feasibility study, we envision the radiomic analysis to be used as a decision support to assist neuroradiologists in improving their confidence in identifying a suspicious lesion as radiation necrosis or cancer recurrence.
We would also like to mention the contributions of all the co-authors including Prateek Prasanna, who is a graduate student in the lab and the clinical collaborators both at University Hospitals and University of Texas Southwest Medical Center who provided the data and the clinical supervision for this work.
MedicalResearch.com: Thank you for your contribution to the MedicalResearch.com community.
P. Tiwari, P. Prasanna, L. Wolansky, M. Pinho, M. Cohen, A.P. Nayate, A. Gupta, G. Singh, K. Hattanpaa, A. Sloan, L. Rogers, and A. Madabhushi. Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study. American Journal of Neuroradiology, September 2016 DOI: 10.3174/ajnr.A4931
Note: Content is Not intended as medical advice. Please consult your health care provider regarding your specific medical condition and questions.
More Medical Research Interviews on MedicalResearch.com