The researchers aimed to derive a methodology to combine multiple functional imaging techniques to identify high-risk tumour subregions in NSCLC patients treated with (chemo)radiotherapy. Therefore, we developed a data-driven clustering approach to correlate the subregions to patient prognosis using FDG PET/CT to quantify metabolic activity, HX4 PET/CT to visualize hypoxia, and dynamic contract-enhanced CT (DCE-CT) to assess tumor vasculature.

Researchers aimed to identify tumor subregions with characteristic phenotypes based on pre-treatment multi-parametric functional imaging and correlate these subregions to treatment outcome. The subregions were created using imaging of metabolic activity (FDG-PET/CT), hypoxia (HX4-PET/CT) and tumor vasculature (DCE-CT).

Thirty-six non-small cell lung cancer (NSCLC) patients underwent functional imaging prior to radical radiotherapy. Kinetic analysis was performed on DCE-CT scans to acquire blood flow (BF) and volume (BV) maps. HX4-PET/CT and DCE-CT scans were non-rigidly co-registered to the planning FDG-PET/CT.

Two clustering steps were performed on multi-parametric images: first to segment each a tumour into homogeneous subregions (i.e., supervoxels) and second to group the supervoxels of all tumors into phenotypic clusters. Patients were split based on the absolute or relative volume of supervoxels in each cluster; overall survival was compared using a log-rank test.

Unsupervised clustering of supervoxels yielded four independent clusters. One cluster (high hypoxia, high FDG, intermediate BF/BV) related to a high-risk tumor type: patients assigned to this cluster had significantly worse survival compared to patients, not in this cluster (p?=?0.035).

Researchers designed a data-driven methodology for the analysis of pre-treatment multi-parametric imaging data in NSCLC patients on a subregional level.

They showed that such an intra-tumor classification of heterogeneous subregions may allow predicting NSCLC patient prognosis after (chemo)radiation. This technique permits further insight into the underlying biological characteristics using an advanced analysis technique for multi-parametric functional images.