The group showed that MRI-based data of tumor oxygen metabolism provide an excellent basis for differentiating tumors using neural networks. The combination of "oxygen metabolic radiomics" with analyses by an AI algorithm was clearly superior to evaluations by human experts in all essential criteria, the university said, in a news release issued on 18 January.

"Our approach succeeded in achieving better distinctions between the tumor types than human experts were able to achieve in comparison," said Prof. Andreas Stadlbauer, from the Institute of Medical Radiology. "In all important differentiation criteria such as accuracy, sensitivity, specificity, and precision, the evaluation of MR-based oxygen data by our special neural network was superior to radiologists."

This method was also better than the human evaluations in statistical evaluations such as the F-values and the AUROC, he added.

The study was published online on 14 December in Metabolites.