Abstract
PurposeThe aim of this multi-center study was to discover and validate radiomics classifiers as image-derived biomarkers for risk stratification of non-small-cell lung cancer (NSCLC).Patients and methodsPre-therapy PET scans from a total of 358 Stage I–III NSCLC patients scheduled for radiotherapy/chemo-radiotherapy acquired between October 2008 and December 2013 were included in this seven-institution study. A semi-automatic threshold method was used to segment the primary tumors. Radiomics predictive classifiers were derived from a training set of 133 scans using TexLAB v2. Least absolute shrinkage and selection operator (LASSO) regression analysis was used for data dimension reduction and radiomics feature vector (FV) discovery. Multivariable analysis was performed to establish the relationship between FV, stage and overall survival (OS). Performance of the optimal FV was tested in an independent validation set of 204 patients, and a further independent set of 21 (TESTI) patients.ResultsOf 358 patients, 249 died within the follow-up period [median 22 (range 0–85) months]. From each primary tumor, 665 three-dimensional radiomics features from each of seven gray levels were extracted. The most predictive feature vector discovered (FVX) was independent of known prognostic factors, such as stage and tumor volume, and of interest to multi-center studies, invariant to the type of PET/CT manufacturer. Using the median cut-off, FVX predicted a 14-month survival difference in the validation cohort (N = 204, p = 0.00465; HR = 1.61, 95% CI 1.16–2.24). In the TESTI cohort, a smaller cohort that presented with unusually poor survival of stage I cancers, FVX correctly indicated a lack of survival difference (N = 21, p = 0.501). In contrast to the radiomics classifier, clinically routine PET variables including SUVmax, SUVmean and SUVpeak lacked any prognostic information.ConclusionPET-based radiomics classifiers derived from routine pre-treatment imaging possess intrinsic prognostic information for risk stratification of NSCLC patients to radiotherapy/chemo-radiotherapy.
Highlights
Patients and methodsLung malignancy is a leading cause of cancer-related death, with a predicted 5-year survival rate of 8–13% [1]
PET-based radiomics classifiers derived from routine pre-treatment imaging possess intrinsic prognostic information for risk stratification of non-small-cell lung cancer (NSCLC) patients to radiotherapy/chemo-radiotherapy
Beyond the use of FDG-PET/CT for staging, we investigated in the present study whether pre-therapy radiomics features derived from routine FDG-PET/CT examinations of non-small-cell lung cancer (NSCLC) patients who were subsequently treated with radiotherapy/chemo-radiotherapy across multiple hospitals might harbor useful prognostic information
Summary
Lung malignancy is a leading cause of cancer-related death, with a predicted 5-year survival rate of 8–13% [1]. Beyond the use of FDG-PET/CT for staging, we investigated in the present study whether pre-therapy radiomics features derived from routine FDG-PET/CT examinations of non-small-cell lung cancer (NSCLC) patients who were subsequently treated with radiotherapy/chemo-radiotherapy across multiple hospitals might harbor useful prognostic information. 665 radiomic features (listed in Supplementary Table 3) were extracted from segmented VOIs using local, regional, global, fractal, and wavelet techniques. These included intensity features, shape features, and texture features [gray level cooccurrence matrix (GLCM), gray level run length matrix (GLRLM) and neighbourhood gray difference matrix (NGTDM)] with or without wavelet transformation, as previously reported [5, 6]. Similar survival comparisons were made with routine PET variables including SUVmean, SUVmax, SUVpeak, MTV, and TLG
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
