Communications of the ACM
Machines See the Future for Patients Diagnosed With Brain Tumors
Researchers at Emory and Northwestern universities have developed artificial intelligence software that can predict the survival of patients diagnosed with glioma by examining data from tissue biopsies.
Credit: Ryan Kelly/Moment/Getty Images
Researchers at Emory University and Northwestern University have created artificial intelligence (AI) software that forecasts the survival of glioma patients by examining tissue biopsy data, in work the researchers say suggests AI could transform medicine sooner than anticipated.
Using deep learning, the team trained the software to learn visual patterns associated with patient survival using microscopic images of brain tumor tissue samples.
The breakthrough stemmed from combining this advanced technology with traditional methods that statisticians use to assess patient outcomes. Software trained with both images and genomic data made survival predictions that were more accurate than those of human pathologists.
The study used public data from the National Cancer Institute's Cancer Genome Atlas project to build and evaluate the algorithm.
The researchers hope to conduct future studies to determine whether the software can help improve outcomes for newly-diagnosed patients.
From Northwestern Now
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found