Figure 1 | Scientific Reports

Figure 1

From: Privacy-preserving distributed learning of radiomics to predict overall survival and HPV status in head and neck cancer

Figure 1

Scheme of the distributed model training. Model training was divided into two parts: feature selection and model fitting. In both parts local statistics were computed at the local repositories and sent to the central server. In the central server the global statistics were estimated and sent back to the local repositories. Finally, the model was tested in a validation cohort.

Back to article page