Machine Learning Enhances Ability To Predict Survival From Brain Tumors

MedicalResearch.com Interview with:

Lee Cooper, Ph.D. Assistant Professor of Biomedical Informatics Assistant Professor of Biomedical Engineering Emory University School of Medicine - Georgia Institute of Technology

Dr. Cooper

Lee Cooper, Ph.D.
Assistant Professor of Biomedical Informatics
Assistant Professor of Biomedical Engineering
Emory University School of Medicine – Georgia Institute of Technology

MedicalResearch.com: What is the background for this study? What are the main findings? 

Response: Gliomas are a form of brain tumor that are often ultimately fatal, but patients diagnosed with glioma may survive as few as 6 months to 10 or more years. Prognosis is an important determinant in selecting treatment, that can range from simply monitoring the disease to surgical removal followed by radiation treatment and chemotherapy. Recent genomic studies have significantly improved our ability to predict how rapidly a patient’s disease will progress, however a significant part of this determination still relies on the visual microscopic evaluation of the tissues by a neuropathologist. The neuropathologist assigns a grade that is used to further refine the prognosis determined by genomic testing.

We developed a predictive algorithm to perform accurate and repeatable microscopic evaluation of glioma brain tumors. This algorithm learns the relationships between visual patterns presented in the brain tumor tissue removed from a patient brain and the duration of that patient’s survival beyond diagnosis. The algorithm was demonstrated to accurately predict survival, and when combining images of histology with genomics into a single predictive framework, the algorithm was slightly more accurate than models based on the predictions of human pathologists. We were also able to identify that the algorithm learns to recognize some of the same tissue features used by pathologists in evaluating brain tumors, and to appreciate their prognostic relevance.

MedicalResearch.com: What should readers take away from your report? 

Response: Our study demonstrates that deep learning methods can be combined with conventional statistical approaches to create accurate predictive models that learn the relationships between complex patterns in histology images and clinical outcomes. These predictions can be used to provide reliable and repeatable prognoses for patients diagnosed with glioma, and to identify patients where more aggressive treatment can extend life.

Histologic grading of gliomas incorporates many different and subtle visual cues, and human pathologists require considerable training to perform this task. Demonstrating that an adaptive algorithm can learn to effectively perform this task has significant implications for medicine and the practice of pathology, but also more broadly for artificial intelligence and its role in our society. Our study shows that the algorithm learns to recognize some of the same structures used by pathologists in evaluating brain tumor tissues, .

Finally, our study shows that histology contains tremendous information. Genomics and genomic classification of cancers will continue to revolutionize cancer treatment and research, but the inexpensive glass slides used by pathologists will likely continue to play an important role in the future.  

MedicalResearch.com: What recommendations do you have for future research as a result of this work? 

Response: We need to validate these results in larger cohorts, and prospectively where the grading performed by humans can be better standardized to form a basis for comparing algorithms and people. We also need to investigate if using this algorithm can improve patient outcomes in prospective studies, and determine how best to use this information to complement the judgement of the pathologists. 

Citations:

Predicting cancer outcomes from histology and genomics using convolutional networks
Pooya Mobadersany, Safoora Yousefi, Mohamed Amgad, David A. Gutman, Jill S. Barnholtz-Sloan, José E. Velázquez Vega, Daniel J. Brat and Lee A. D. Cooper
PNAS March 12, 2018. 201717139; published ahead of print March 12, 2018. https://doi.org/10.1073/pnas.1717139115

The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.

 

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.