Pseudo-domains in imaging data improve prediction of future disease status in multi-center studies
This addresses data heterogeneity issues in multi-center clinical trials for liver disease prediction, but it is incremental as it builds on existing domain adaptation methods.
The paper tackled the problem of predicting future disease status from heterogeneous multi-center imaging data by clustering sites into pseudo-domains and training domain-specific models, resulting in improved prediction accuracy for steatosis after 48 weeks.
In multi-center randomized clinical trials imaging data can be diverse due to acquisition technology or scanning protocols. Models predicting future outcome of patients are impaired by this data heterogeneity. Here, we propose a prediction method that can cope with a high number of different scanning sites and a low number of samples per site. We cluster sites into pseudo-domains based on visual appearance of scans, and train pseudo-domain specific models. Results show that they improve the prediction accuracy for steatosis after 48 weeks from imaging data acquired at an initial visit and 12-weeks follow-up in liver disease