Predicting Distant Failure in Lung Stereotactic Body Radiation Therapy Using Multiobjective Radiomics Model

"Radio-oncomics" : The potential of radiomics in radiation oncology

INTRODUCTION

Radiomics, a recently introduced concept, describes quantitative computerized algorithm-based feature extraction from imaging data including computer tomography (CT), magnetic resonance imaging (MRT), or positron-emission tomography (PET) images. For radiation oncology it offers the potential to significantly influence clinical decision-making and thus therapy planning and follow-up workflow.

METHODS

After image acquisition, image preprocessing, and defining regions of interest by structure segmentation, algorithms are applied to calculate shape, intensity, texture, and multiscale filter features. By combining multiple features and correlating them with clinical outcome, prognostic models can be created.

RESULTS

Retrospective studies have proposed radiomics classifiers predicting, e. g., overall survival, radiation treatment response, distant metastases, or radiation-related toxicity. Besides, radiomics features can be correlated with genomic information ("radiogenomics") and could be used for tumor characterization.

DISCUSSION

Distinct patterns based on data-based as well as genomics-based features will influence radiation oncology in the future. Individualized treatments in terms of dose level adaption and target volume definition, as well as other outcome-related parameters will depend on radiomics and radiogenomics. By integration of various datasets, the prognostic power can be increased making radiomics a valuable part of future precision medicine approaches.

CONCLUSION

This perspective demonstrates the evidence for the radiomics concept in radiation oncology. The necessity of further studies to integrate radiomics classifiers into clinical decision-making and the radiation therapy workflow is emphasized.

Stereotactic Ablative Radiation Therapy for Lung Oligometastases: Predictive Parameters of Early Response by 18FDG-PET/CT

OBJECTIVES

The objective of this study was to investigate fludeoxyglucose F 18 positron emission tomography/computed tomography (¹⁸FDG-PET/CT) parameters as predictive of response after stereotactic ablative radiotherapy (SABR) for lung oligometastases.

METHODS

The inclusion criteria of the current retrospective study were as follows: (1) lung oligometastases treated by SABR, (2) presence of ¹⁸FDG-PET/CT before and after SABR for at least two subsequent evaluations, (3) Karnofsky performance status higher than 80, and (4) life expectancy longer than 6 months. All patients were treated with a biologically equivalent dose of at least 100 Gy with an alpha/beta ratio of 10. The following metabolic parameters were semiquantitatively defined: maximum standardized uptake value (SUV_max), mean standardized uptake value (SUV_mean), metabolic tumor volume, and total lesion glycolysis.

RESULTS

A total of 50 patients met the inclusion criteria, for a total of 70 lung metastases. The pre-SABR median SUV_max was 6.5 (range 4-17), the median SUV_mean was 3.7 (range 2.5-6.5), and the median metabolic tumor volume was 2.3 cm³ (0.2-31 cm³). The following metabolic parameters were significantly related to complete response at 6 months: SUV_max less than 5 (p < 0.001) and SUV_mean less than 3.5 (p = 0.03). ΔSUV_max at 3 to 6 months was +126% for lesions with in-field progression versus -26% for the remaining lesions (p = 0.002). ΔSUV_mean at 3 to 6 months was +15% for lesions with in-field progression versus -26% for the remaining metastases (p = 0.008).

CONCLUSIONS

In the current analysis, complete response from lung metastasis at 6 months after stereotactic body radiation therapy was significantly associated with both the maximum and mean values of pre-SABR ¹⁸FDG-PET/CT SUV. Longer-term trials are strongly advocated to improve the personalization of the monitoring of tumor response in patients with lung oligometastases and, consequently, monitoring of the cost-effectiveness of the health care.