A test of machine-learning algorithms shows promise for computer-aided prognosis of acute spinal cord injury, according to a recent study.
The study involved using semiautomated image analysis with machine-learning algorithms to assess the accuracy of axial T2-weighted radiomic features for classifying patients by degree of neurologic injury.
In the study, Jason Talbot, assistant professor of radiology at the University of California, San Francisco, tested several machine-learning algorithms for injury classification based on texture variables. For each trained model, the accuracy of predicting the testing set was recorded, as were variables important to the model, according to a media release from the American Roentgen Ray Society (ARRS).
This proof-of-principle study highlights the feasibility of applying a semiautomated MRI analysis pipeline for atlas-based texture feature extraction from T2-weighted MRI at the epicenter of acute spinal cord injury (SCI). The results show that exploratory application of five machine-learning algorithms integrated into the analysis pipeline can classify patients by degree of neurologic impairment with variable accuracy and identify potential prognostic texture features, the release explains.
The study will be presented at the upcoming ARRS 2018 Annual Meeting, April 22-27 in Washington, DC.
[Source(s): American Roentgen Ray Society, EurekAlert]