FDG PET and CT radiomics in diagnosis and prognosis of non-small-cell lung cancer

Abstract

Background: 18 F-FDG PET and CT radiomics has been the object of a wide research for over 20 years but its contribution to clinical practice remains not yet well established. We have investigated its impact versus that of only histo-clinical data, for the routine management of non-small-cell lung cancer (NSCLC).Methods: Our patients were retrospectively considered. They all had a FDG PET-CT and immuno-histochemistry (IHC) to assess PD-L1 expression at the beginning of the disease. A prognosis univariate and multivariate Cox survival analyses was performed for overall survival (OS) and progression free survival (PFS) prediction, including a training/testing procedure. Two sets of 47 PET and 47 CT radiomics features (RFs) were extracted. Difference between RFs according to PD-L1 expression, the histology status and the stage level were tested using suited non parametric statistical tests and the receiver operating characteristics (ROC) curve and the area under curve (AUC).Results: From 2017 to 2019, 212 NSCLC patients treated in our institution were included. The main conventional prognostic variables were stage and gender with a low added prognostic value in the models including PET and CT RFs. Neither PET nor CT RFs were significant to separate the different levels of PD-L1 expression. Several RFs differ between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) tumours and a large number of PET and CT RFs are significantly linked to patient stage. Conclusions:In our population, PET and CT RFs show their intrinsic power to predict survival but do not significantly improve OS and PFS prediction in the different multivariate models, in comparison to conventional data. It would seem necessary to carry out one's own survival analysis before determining a radiomics signature.

Does FDG PET-Based Radiomics Have an Added Value for Prediction of Overall Survival in Non-Small Cell Lung Cancer?

“…Results very similar to ours were obtained by Hannequin et al [40] and Oliveira et al [43]. Hannequin et al showed that PET and CT radiomic features have intrinsic power to predict survival, but they do not significantly improve the prediction of OS and progression-free survival in different multivariate models, in comparison to stage and gender [40].…”

“…Machine learning has been employed in the context of medical imaging for segmentation and malignancy characterization [31], in histopathology [32], and in the study of biomarkers [33]. Recent studies have begun to explore the potential role of machine learning networks in prognosis, applying machine learning models to predict OS in NSCLC, mainly integrating tumor stage with clinical factors showing promising results [34][35][36][37][38][39][40][41][42][43][44]. However, a possible research gap lies in the fact that although studies indicate the potential of radiomics to predict survival in oncological patients, the clinical settings and the most important radiomic variables for such prediction need to be better established.…”

Combined morphologic-metabolic biomarkers from [18F]FDG-PET/CT stratify prognostic groups in low-risk NSCLC

“…The analysis of radiomic features ("radiomics") and use of machine learning might impact patient treatment and help improve clinical therapy assessment. A variety of recent studies has emphasized their capabilities for automated tumor detection and delineation, survival stratification or prediction of PD-L1 expression [10,11,12,13,14,15]. Qiao et al showed that a combination of PET and CT radiomic features derived from the primary tumor could noninvasively predict occult lymph node metastases [16].…”

“…Dondi et al recently emphasized the influence of the PET/CT scanner type on ML and radiomics in the classification of stage I and II NSCLCs [18]. Some authors question the robustness or suitability of radiomics for broad clinical use in their current state [11,18]. With these considerations, we decided to focus on imaging-based parameters that are easier to assess and less variable like SUV max , and the CT-derived lesion volume.…”

What is the real value of predictive models?

“…Hannequin et al ( 2 ) present the results of their retrospective study where positron emission tomography/computed tomography (PET/CT) and CT scan radiomic features fail to predict overall survival (OS) and progression-free survival (PFS) when compared to other traditionally used clinical variables, as gender and stage.…”