Assessment of soft-tissue sarcomas perfusion using data-driven techniques

The present study aims 1. to automatically classify the heterogeneously perfused tumors using dynamic contrast-enhanced (DCE) MRI data from two patients diagnosed with malignant peripheral nerve sheath tumor (MPNST), 2. to compare the differences between the two cases, and 3. to detect the possible presence of hypoxia. A pattern recognition (PR) algorithm has been applied to the data resulting in the identification of areas with different perfusion. The algorithm was proven to be robust since the intensity curves of the PR classified pixels had similar shapes with the curves of the PR identified patterns and were in line with the theoretically expected enhancement patterns of the DCE time-signal curves.