Fully Integrated Quantitative Multiparametric Analysis of Non-Small Cell Lung Cancer at 3-T PET/MRI Toward One-Stop-Shop Tumor Biological Characterization at the Supervoxel Level

Introduction The aim of this study was to study the feasibility of a fully integrated multiparametric imaging framework to characterize non-small cell lung cancer (NSCLC) at 3-T PET/MRI. Patients and Methods An F-18-FDG PET/MRI multiparametric imaging framework was developed and prospectively applied to 11 biopsy-proven NSCLC patients. For each tumor, 12 parametric maps were generated, including PET full kinetic modeling, apparent diffusion coefficient, T1/T2 relaxation times, and DCE full kinetic modeling. Gaussian mixture model-based clustering was applied at the whole data set level to define supervoxels of similar multidimensional PET/MRI behaviors. Taking the multidimensional voxel behaviors as input and the supervoxel class as output, machine learning procedure was finally trained and validated voxelwise to reveal the dominant PET/MRI characteristics of these supervoxels at the whole data set and individual tumor levels. Results The Gaussian mixture model-based clustering clustering applied at the whole data set level (17,316 voxels) found 3 main multidimensional behaviors underpinned by the 12 PET/MRI quantitative parameters. Four dominant PET/MRI parameters of clinical relevance (PET: k(2), k(3) and DCE: v(e), v(p)) predicted the overall supervoxel behavior with 97% of accuracy (SD, 0.7; 10-fold cross-validation). At the individual tumor level, these dimensionality-reduced supervoxel maps showed mean discrepancy of 16.7% compared with the original ones. Conclusions One-stop-shop PET/MRI multiparametric quantitative analysis of NSCLC is clinically feasible. Both PET and MRI parameters are useful to characterize the behavior of tumors at the supervoxel level. In the era of precision medicine, the full capabilities of PET/MRI would give further insight of the characterization of NSCLC behavior, opening new avenues toward image-based personalized medicine in this field.

Automated summary

This study developed a multiparametric imaging framework for NSCLC using PET/MRI, which successfully revealed the PET/MRI characteristics of tumors through Gaussian mixture model-based clustering and machine learning. The features showed high accuracy and low mean discrepancy at both the whole data set and individual tumor levels.