Dataset Information

Discovery of pre-therapy 2-deoxy-2-¹⁸F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.

ABSTRACT:

Purpose

The 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 methods

Pre-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.

Results

Of 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 SUV_max, SUV_mean and SUV_peak lacked any prognostic information.

Conclusion

PET-based radiomics classifiers derived from routine pre-treatment imaging possess intrinsic prognostic information for risk stratification of NSCLC patients to radiotherapy/chemo-radiotherapy.

SUBMITTER: Arshad MA

PROVIDER: S-EPMC6333728 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Discovery of pre-therapy 2-deoxy-2-<sup>18</sup>F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.

Arshad Mubarik A MA Thornton Andrew A Lu Haonan H Tam Henry H Wallitt Kathryn K Rodgers Nicola N Scarsbrook Andrew A McDermott Garry G Cook Gary J GJ Landau David D Chua Sue S O'Connor Richard R Dickson Jeanette J Power Danielle A DA Barwick Tara D TD Rockall Andrea A Aboagye Eric O EO

European journal of nuclear medicine and molecular imaging 20180901 2

<h4>Purpose</h4>The 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).<h4>Patients and methods</h4>Pre-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 tum ...[more]

PMID: 30173391

Similar Datasets

Project description:BackgroundInflammation of patients joints with severe disease activity of rheumatoid arthritis (RA) has already been visualized and quantified by 2-[18F]fluoro-2-deoxy-D-glucose positron emission computed tomography ([18F] FDG PET/CT), but little is known about the metabolic status and its relationship with clinical and ultrasonography (US) metrology in patients with low/moderate activity or in remission.MethodsClinical assessments [based on 28-joint disease activity score (DAS28-CRP) and Clinical Disease Activity Index (CDAI)], [18F] FDG PET/CT, US and X-ray were performed on 63 RA patients classified into remission or low/moderate or severe disease activity groups. PET/CT was visually and then semi-quantitatively analysed by determining the standardized uptake value (SUV) of positive joints.ResultsOf the 1764 joints, 21.1% were tender only, 13.7% swollen only, 27.6% tender or swollen, 7.3% tender and swollen, 20.5% PET/CT-positive and 8.6% US-positive. PET and US measurements were correlated, albeit with poor concordance. The positive predictive value of PET/CT for clinical evaluation (tender and/or swollen) was low, whereas its negative predictive value was high. Highly significant differences were found with the number of PET/CT-positive joints and with cumulative SUV between "severe" and "non-severe" patients (including those in remission and those with low/moderate activity) and not between those classified as "remission" and "non-remission" or "remission" and "low/moderate activity". Moreover, the correlation between PET/CT measurements and clinical activity was positive only in the CDAI severe disease group. In patients in remission or with low/moderate activity, only 20-30% of joints were PET/CT-negative. In remission, PET/CT and US were positive in different joints, and PET/CT-positive but US-negative joints mainly exhibited RA (38.1%) or normal (49.2%) and not osteoarthritic (12.7%) X-ray patterns.Conclusions[18F] FDG PET/CT was effective at distinguishing patients with severely active disease from other patients. In non-severe RA patients, including those in remission, PET/CT results are discordant from US and clinical observations. A longitudinal analysis is needed to explore the clinical relevance of such infra-clinical disease.

Project description:PurposeTo image inflammation and monitor therapeutic response to anti-inflammatory intervention using 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) positron emission tomography (PET) in a preclinical model of acute lung injury (ALI).ProceduresMice were intratracheally administered lipopolysaccharide (LPS, 2.5 mg/kg) to induce ALI or phosphate-buffered saline as the vehicle control. A subset of mice in the ALI group received two intraperitoneal doses of dexamethasone 1 and 24 h after LPS. [18F]FDG PET/CT was performed 2 days after the induction of ALI. [18F]FDG uptake in the lungs was quantified by PET (%ID/mLmean and standardized uptake value (SUVmean)) and ex vivo γ-counting (%ID/g). The severity of lung inflammation was determined by quantifying the protein level of inflammatory cytokines/chemokines and the activity of neutrophil elastase and glycolytic enzymes. In separate groups of mice, flow cytometry was performed to estimate the contribution of individual immune cell types to the total pulmonary inflammatory cell burden under different treatment conditions.ResultsLung uptake of [18F]FDG was significantly increased during LPS-induced ALI, and a decreased [18F]FDG uptake was observed following dexamethasone treatment to an intermediate level between that of LPS-treated and control mice. Protein expression of inflammatory biomarkers and the activity of neutrophil elastase and glycolytic enzymes were increased in the lungs of LPS-treated mice versus those of control mice, and correlated with [18F]FDG uptake. Furthermore, dexamethasone-induced decreases in cytokine/chemokine protein levels and enzyme activities correlated with [18F]FDG uptake. Neutrophils were the most abundant cells in LPS-induced ALI, and the pattern of total cell burden during ALI with or without dexamethasone therapy mirrored that of [18F]FDG uptake.Conclusions[18F]FDG PET noninvasively detects lung inflammation in ALI and its response to anti-inflammatory therapy in a preclinical model. However, high [18F]FDG uptake by bone, brown fat, and myocardium remains a technical limitation for quantification of [18F]FDG in the lungs.

Dataset Information

Discovery of pre-therapy 2-deoxy-2-¹⁸F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.

Purpose

Patients and methods

Results

Conclusion

Publications

Discovery of pre-therapy 2-deoxy-2-<sup>18</sup>F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

Discovery of pre-therapy 2-deoxy-2-18F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.

Purpose

Patients and methods

Results

Conclusion

Publications

Discovery of pre-therapy 2-deoxy-2-<sup>18</sup>F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Discovery of pre-therapy 2-deoxy-2-¹⁸F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients.