PET Radiomic Features Research Articles

Evaluation and optimization of radiomics features stability to respiratory motion in 18F‐FDG 3D PET imaging

To evaluate the impact of respiratory motion on radiomics features in 18 F-fluoro-2-deoxy-D-glucose three dimensional positron emission tomography (18 F-FDG 3D PET) imaging and optimize feature stability by combining preprocessing configurations and aggregation strategies. An in-house developed respiratory motion phantom was imaged in 3D PET scanner under nine respiratory patterns including one reference pattern. In total, 487radiomics features were extracted for each respiratory pattern. Feature stability to respiratory motion was first evaluated by metrics of coefficient of variation (COV) and relative difference (RD) in a fixed preprocessing configuration. Further, one-way ANOVA and trend analysis were performed to evaluate the impact of preprocessing configuration (voxel size, discretization scheme) and aggregation strategy on feature stability. Finally, an optimization framework was proposed by selected feature-specific configurations with minimum COV value, and the diagnostic performance was validated in stable versus unstable features and fixed versus optimal features by a set of 46 patients with lung disease. PET radiomics features were sensitive to respiratory motion, only 79/487 (16%) features were identified to be very stable in the fixed configuration. Preprocessing configuration and aggregation strategy had an impact on feature stability. For different voxel size, bin number, bin size and aggregation strategy, 188/487 (39%), 70/487 (15%), 148/487 (30%), and 38/95 (29%) features appeared significant changes in feature stability. The optimized configuration had the potential to improve feature stability compared to fixed configuration, with the COV decreased from 22% ±24% to 16% ±20%. Regarding the diagnostic performance, the stable and optimal configuration features outperformed the unstable and fixed configuration features, respectively (AUC 0.88, 0.87 vs. 0.83, 0.85). Respiratory motion shows considerable impact on feature stability in 3D PET imaging, while optimizing preprocessing configuration may improve feature stability and diagnostic performance.

PET Radiomic Features Variability: A Phantom Study on the Influence of Reconstruction and Discretization Method

We aimed to explore the variability of PET radiomic features for varying reconstruction methods and quantification settings. The IQ-NEMA phantom was scanned 5 times with a sphere to background F-18 concentration ratio of 10:1. The activity and the image duration were matched to result typical counting statistics for 18F-FDG oncologic examinations. The images were reconstructed with OSEM and PSF reconstructions, then 99 radiomic features were extracted using two discretization methods: fixed bin number (FBN = 16, 32 and 64 gray levels) and fixed bin width (FBW=0.25). This scheme resulted in a total of 1,188 features, classified as having low (<5.0%), intermediate (5-29.9%) or high (≥30%) variability. In general, FBW discretization yielded more stable features. A total of 499, 558 and 131 features had low, intermediate and high variability, respectively. First order features such as energy and entropy and textural features such as entropy (GLCM), long run emphasis and short run emphasis (GLRLM) were more likely to present low variability, regardless the reconstruction and discretization method. Other textural features such as large area emphasis (GLSZM), zone percentage (GLSZM) and complexity (NGTDM) had more frequently intermediate or high variability.These findings could facilitate features’ selection for further PET radiomic applications.

The role of PET radiomic features in prostate cancer: a systematic review

The role of PET radiomic features in prostate cancer: a systematic review

18F-FDOPA PET for the Noninvasive Prediction of Glioma Molecular Parameters: A Radiomics Study.

The assessment of gliomas by 18F-FDOPA PET imaging as an adjunct to MRI showed high performance by combining static and dynamic features to noninvasively predict the isocitrate dehydrogenase (IDH) mutations and the 1p/19q codeletion, which the World Health Organization classified as significant parameters in 2016. The current study evaluated whether other 18F-FDOPA PET radiomics features further improve performance and the contributions of each of these features to performance. Methods: Our study included 72 retrospectively selected, newly diagnosed glioma patients with 18F-FDOPA PET dynamic acquisitions. A set of 114 features, including conventional static features and dynamic features, as well as other radiomics features, were extracted and machine-learning models trained to predict IDH mutations and the 1p/19q codeletion. Models were based on a machine-learning algorithm built from stable, relevant, and uncorrelated features selected by hierarchic clustering followed by a bootstrapped feature selection process. Models were assessed by comparing area under the curve using a nested cross-validation approach. Feature importance was assessed using Shapley additive explanations values. Results: The best models were able to predict IDH mutations (logistic regression with L2 regularization) and the 1p/19q codeletion (support vector machine with radial basis function kernel) with an area under the curve of 0.831 (95% CI, 0.790-0.873) and 0.724 (95% CI, 0.669-0.782), respectively. For the prediction of IDH mutations, dynamic features were the most important features in the model (time to peak, 35.5%). In contrast, other radiomics features were the most useful for predicting the 1p/19q codeletion (up to 14.5% of importance for the small-zone low-gray-level emphasis). Conclusion:18F-FDOPA PET is an effective tool for the noninvasive prediction of glioma molecular parameters using a full set of amino-acid PET radiomics features. The contribution of each feature set shows the importance of systematically integrating dynamic acquisition for prediction of the IDH mutations as well as developing the use of radiomics features in routine practice for prediction of the 1p/19q codeletion.

Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer

ObjectiveThe objectives of our study were to assess the association of radiomic and genomic data with histology and patient outcome in non-small cell lung cancer (NSCLC).MethodsIn this retrospective single-centre observational study, we selected 151 surgically treated patients with adenocarcinoma or squamous cell carcinoma who performed baseline [18F] FDG PET/CT. A subgroup of patients with cancer tissue samples at the Institutional Biobank (n = 74/151) was included in the genomic analysis. Features were extracted from both PET and CT images using an in-house tool. The genomic analysis included detection of genetic variants, fusion transcripts, and gene expression. Generalised linear model (GLM) and machine learning (ML) algorithms were used to predict histology and tumour recurrence.ResultsStandardised uptake value (SUV) and kurtosis (among the PET and CT radiomic features, respectively), and the expression of TP63, EPHA10, FBN2, and IL1RAP were associated with the histotype. No correlation was found between radiomic features/genomic data and relapse using GLM. The ML approach identified several radiomic/genomic rules to predict the histotype successfully. The ML approach showed a modest ability of PET radiomic features to predict relapse, while it identified a robust gene expression signature able to predict patient relapse correctly. The best-performing ML radiogenomic rule predicting the outcome resulted in an area under the curve (AUC) of 0.87.ConclusionsRadiogenomic data may provide clinically relevant information in NSCLC patients regarding the histotype, aggressiveness, and progression. Gene expression analysis showed potential new biomarkers and targets valuable for patient management and treatment. The application of ML allows to increase the efficacy of radiogenomic analysis and provides novel insights into cancer biology.

Radiomics Analysis of PET and CT Components of 18F-FDG PET/CT Imaging for Prediction of Progression-Free Survival in Advanced High-Grade Serous Ovarian Cancer.

ObjectiveTo investigate radiomics features extracted from PET and CT components of 18F-FDG PET/CT images integrating clinical factors and metabolic parameters of PET to predict progression-free survival (PFS) in advanced high-grade serous ovarian cancer (HGSOC).MethodsA total of 261 patients were finally enrolled in this study and randomly divided into training (n=182) and validation cohorts (n=79). The data of clinical features and metabolic parameters of PET were reviewed from hospital information system(HIS). All volumes of interest (VOIs) of PET/CT images were semi-automatically segmented with a threshold of 42% of maximal standard uptake value (SUVmax) in PET images. A total of 1700 (850×2) radiomics features were separately extracted from PET and CT components of PET/CT images. Then two radiomics signatures (RSs) were constructed by the least absolute shrinkage and selection operator (LASSO) method. The RSs of PET (PET_RS) and CT components(CT_RS) were separately divided into low and high RS groups according to the optimum cutoff value. The potential associations between RSs with PFS were assessed in training and validation cohorts based on the Log-rank test. Clinical features and metabolic parameters of PET images (PET_MP) with P-value <0.05 in univariate and multivariate Cox regression were combined with PET_RS and CT_RS to develop prediction nomograms (Clinical, Clinical+ PET_MP, Clinical+ PET_RS, Clinical+ CT_RS, Clinical+ PET_MP + PET_RS, Clinical+ PET_MP + CT_RS) by using multivariate Cox regression. The concordance index (C-index), calibration curve, and net reclassification improvement (NRI) was applied to evaluate the predictive performance of nomograms in training and validation cohorts.ResultsIn univariate Cox regression analysis, six clinical features were significantly associated with PFS. Ten PET radiomics features were selected by LASSO to construct PET_RS, and 1 CT radiomics features to construct CT_RS. PET_RS and CT_RS was significantly associated with PFS both in training (P <0.00 for both RSs) and validation cohorts (P=0.01 for both RSs). Because there was no PET_MP significantly associated with PFS in training cohorts. Only three models were constructed by 4 clinical features with P-value <0.05 in multivariate Cox regression and RSs (Clinical, Clinical+ PET_RS, Clinical+ CT_RS). Clinical+ PET_RS model showed higher prognostic performance than other models in training cohort (C-index=0.70, 95% CI 0.68-0.72) and validation cohort (C-index=0.70, 95% CI 0.66-0.74). Calibration curves of each model for prediction of 1-, 3-year PFS indicated Clinical +PET_RS model showed excellent agreements between estimated and the observed 1-, 3-outcomes. Compared to the basic clinical model, Clinical+ PET_MS model resulted in greater improvement in predictive performance in the validation cohort.ConclusionPET_RS can improve diagnostic accuracy and provide complementary prognostic information compared with the use of clinical factors alone or combined with CT_RS. The newly developed radiomics nomogram is an effective tool to predict PFS for patients with advanced HGSOC.

Prognostic Value of Computed Tomography and/or 18F-Fluorodeoxyglucose Positron Emission Tomography Radiomics Features in Locally Advanced Non-small Cell Lung Cancer

IntroductionWe investigated whether adding computed tomography (CT) and/or 18F-fluorodeoxyglucose (18F-FDG) PET radiomics features to conventional prognostic factors (CPFs) improves prognostic value in locally advanced non-small cell lung cancer (NSCLC). Materials and MethodsWe retrospectively identified 39 cases with stage III NSCLC who received chemoradiotherapy and underwent planning CT and staging 18F-FDG PET scans. Seven CPFs were recorded. Feature selection was performed on 48 CT and 49 PET extracted radiomics features. A penalized multivariate Cox proportional hazards model was used to generate models for overall survival based on CPFs alone, CPFs with CT features, CPFs with PET features, and CPFs with CT and PET features. Linear predictors generated and categorized into 2 risk groups for which Kaplan-Meier survival curves were calculated. A log-rank test was performed to quantify the discrimination between the groups and calculated the Harrell's C-index to quantify the discriminatory power. A likelihood ratio test was performed to determine whether adding CT and/or PET features to CPFs improved model performance. ResultsAll 4 models significantly discriminated between the 2 risk groups. The discriminatory power was significantly increased when CPFs were combined with PET features (C-index 0.82; likelihood ratio test P < .01) or with both CT and PET features (0.83; P < .01) compared with CPFs alone (0.68). There was no significant improvement when CPFs were combined with CT features (0.68). ConclusionAdding PET radiomics features to CPFs yielded a significant improvement in the prognostic value in locally advanced NSCLC; adding CT features did not.

18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation

PurposeTo test the performances of native and tumour to liver ratio (TLR) radiomic features extracted from pre-treatment 2-[18F] fluoro-2-deoxy-D-glucose ([18F]FDG) PET/CT and combined with machine learning (ML) for predicting cancer recurrence in patients with locally advanced cervical cancer (LACC).MethodsOne hundred fifty-eight patients with LACC from multiple centers were retrospectively included in the study. Tumours were segmented using the Fuzzy Local Adaptive Bayesian (FLAB) algorithm. Radiomic features were extracted from the tumours and from regions drawn over the normal liver. Cox proportional hazard model was used to test statistical significance of clinical and radiomic features. Fivefold cross validation was used to tune the number of features. Seven different feature selection methods and four classifiers were tested. The models with the selected features were trained using bootstrapping and tested in data from each scanner independently. Reproducibility of radiomics features, clinical data added value and effect of ComBat-based harmonisation were evaluated across scanners.ResultsAfter a median follow-up of 23 months, 29% of the patients recurred. No individual radiomic or clinical features were significantly associated with cancer recurrence. The best model was obtained using 10 TLR features combined with clinical information. The area under the curve (AUC), F1-score, precision and recall were respectively 0.78 (0.67–0.88), 0.49 (0.25–0.67), 0.42 (0.25–0.60) and 0.63 (0.20–0.80). ComBat did not improve the predictive performance of the best models. Both the TLR and the native models performance varied across scanners used in the test set.Conclusion[18F]FDG PET radiomic features combined with ML add relevant information to the standard clinical parameters in terms of LACC patient’s outcome but remain subject to variability across PET/CT devices.

Preoperative prediction of regional lymph node metastasis of colorectal cancer based on 18F-FDG PET/CT and machine learning.

To establish and validate a regional lymph node (LN) metastasis prediction model of colorectal cancer (CRC) based on 18F-FDG PET/CT and radiomic features using machine-learning methods. A total of 199 colorectal cancer patients underwent pre-therapy diagnostic 18F-FDG PET/CT scans and CRC radical surgery. The Chang-Gung Image Texture Analysis toolbox (CGITA) was used to extract 70 PET radiomic features reflecting 18F-FDG uptake heterogeneity of tumors. The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomic features and develop a radiomic signature score (Rad-score). The training set was used to establish five machine-learning prediction models and the test set was used to test the efficacy of the models. The effectiveness of the models was compared by ROC analysis. The CRC patients were divided into a training set (n = 144) and a test set (n = 55). Two radiomic features were selected to build the Rad-score. Five machine-learning algorithms including logistic regression, support vector machine (SVM), random forest, neural network and eXtreme gradient boosting (XGBoost) were used to established models. Among the five machine-learning models, logistic regression (AUC 0.866, 95% CI 0.808-0.925) and XGBoost (AUC 0.903, 95% CI 0.855-0.951) models performed the best. In the training set, the AUC of these two models were significantly higher than that of the LN metastasis status reported by 18F-FDG PET/CT for differentiating positive and negative regional LN metastases in CRC (all p < 0.05). Good efficacy of the above two models was also achieved in the test set. We created a nomogram based on the logistic regression model that visualized the results and provided an easy-to-use method for predicting regional LN metastasis in patients with CRC. In this study, five machine-learning models for preoperative prediction of regional LN metastasis of CRC based on 18F-FDG PET/CT and PET-based radiomic features were successfully developed and validated. Among them, the logistic regression and XGBoost models performed the best, with higher efficacy than 18F-FDG PET/CT in both the training and test sets.

Stage-Specific PET Radiomic Prediction Model for the Histological Subtype Classification of Non-Small-Cell Lung Cancer.

PurposeTo investigate the impact of staging on differences in glucose metabolic heterogeneity between lung adenocarcinoma (ADC) and squamous cell carcinoma (SCC) by 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) textural analysis and to develop a stage-specific PET radiomic prediction model to distinguish lung ADC from SCC.Patients and MethodsPatients who were histologically diagnosed with lung ADC or SCC and underwent pretreatment 18F-FDG PET/CT scans were retrospectively identified. Radiomic features were extracted from a semiautomatically outlined tumor region in the Chang-Gung Image Texture Analysis (CGITA) software package. The differences in radiomic parameters between lung ADC and SCC were compared stage-by-stage in 253 consecutive NSCLC patients with stages I to III disease. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature selection. A radiomic signature for each stage was subsequently constructed and evaluated. Then, an individual nomogram incorporating the radiomic signature and clinical risk factors was established and evaluated. The performance of the constructed models was assessed by receiver operating characteristic (ROC) curve analysis, and the nomogram was further validated by calibration curve analysis.ResultsThe performance of the radiomic signature for distinguishing lung ADC and SCC in both the training and validation cohorts was good, with AUCs of 0.883, 0.854, and 0.895 in the training cohort and 0.932, 0.944, and 0.886 in the validation cohort for stages I, II, and III NSCLC, respectively. The radiomic-clinical nomogram integrating radiomic features with independent clinical predictors exhibited more favorable discriminative performance, with AUCs of 0.982, 0.963, and 0.979 in the training cohort and 0.989, 0.984, and 0.978 in the validation cohort for stages I, II, and III, respectively.ConclusionDifferences in PET radiomic features between lung ADC and SCC varied in different stages. Stage-specific PET radiomic prediction models provided more favorable performance for discriminating the histological subtype of NSCLC.

Prognostic Value of Baseline Radiomic Features of 18F-FDG PET in Patients with Diffuse Large B-Cell Lymphoma.

This study investigates whether baseline 18F-FDG PET radiomic features can predict survival outcomes in patients with diffuse large B-cell lymphoma (DLBCL). We retrospectively enrolled 83 patients diagnosed with DLBCL who underwent 18F-FDG PET scans before treatment. The patients were divided into the training cohort (n = 58) and the validation cohort (n = 25). Eighty radiomic features were extracted from the PET images for each patient. Least absolute shrinkage and selection operator regression were used to reduce the dimensionality within radiomic features. Cox proportional hazards model was used to determine the prognostic factors for progression-free survival (PFS) and overall survival (OS). A prognostic stratification model was built in the training cohort and validated in the validation cohort using Kaplan–Meier survival analysis. In the training cohort, run length non-uniformity (RLN), extracted from a gray level run length matrix (GLRLM), was independently associated with PFS (hazard ratio (HR) = 15.7, p = 0.007) and OS (HR = 8.64, p = 0.040). The International Prognostic Index was an independent prognostic factor for OS (HR = 2.63, p = 0.049). A prognostic stratification model was devised based on both risk factors, which allowed identification of three risk groups for PFS and OS in the training (p < 0.001 and p < 0.001) and validation (p < 0.001 and p = 0.020) cohorts. Our results indicate that the baseline 18F-FDG PET radiomic feature, RLNGLRLM, is an independent prognostic factor for survival outcomes. Furthermore, we propose a prognostic stratification model that may enable tailored therapeutic strategies for patients with DLBCL.

Addition of HER2 and CD44 to 18F-FDG PET\u2013based clinico-radiomic models enhances prediction of neoadjuvant chemoradiotherapy response in esophageal cancer

ObjectivesTo assess the complementary value of human epidermal growth factor receptor 2 (HER2)-related biological tumor markers to clinico-radiomic models in predicting complete response to neoadjuvant chemoradiotherapy (NCRT) in esophageal cancer patients.MethodsExpression of HER2 was assessed by immunohistochemistry in pre-treatment tumor biopsies of 96 patients with locally advanced esophageal cancer. Five other potentially active HER2-related biological tumor markers in esophageal cancer were examined in a sub-analysis on 43 patients. Patients received at least four of the five cycles of chemotherapy and full radiotherapy regimen followed by esophagectomy. Three reference clinico-radiomic models based on 18F-FDG PET were constructed to predict pathologic response, which was categorized into complete versus incomplete (Mandard tumor regression grade 1 vs. 2–5). The complementary value of the biological tumor markers was evaluated by internal validation through bootstrapping.ResultsPathologic examination revealed 21 (22%) complete and 75 (78%) incomplete responders. HER2 and cluster of differentiation 44 (CD44), analyzed in the sub-analysis, were univariably associated with pathologic response. Incorporation of HER2 and CD44 into the reference models improved the overall performance (R2s of 0.221, 0.270, and 0.225) and discrimination AUCs of 0.759, 0.857, and 0.816. All models exhibited moderate to good calibration. The remaining studied biological tumor markers did not yield model improvement.ConclusionsIncorporation of HER2 and CD44 into clinico-radiomic prediction models improved NCRT response prediction in esophageal cancer. These biological tumor markers are promising in initial response evaluation.Key Points• A multimodality approach, integrating independent genomic and radiomic information, is promising to improve prediction of γpCR in patients with esophageal cancer.• HER2 and CD44 are potential biological tumor markers in the initial work-up of patients with esophageal cancer.• Prediction models combining 18F-FDG PET radiomic features with HER2 and CD44 may be useful in the decision to omit surgery after neoadjuvant chemoradiotherapy in patients with esophageal cancer.

Predicting Circulating Tumor Cells from Intratumoral Radiomic Heterogeneity of 18F-FDG-PET/CT in Early Stage Non-Small Cell Lung Cancer Treated with Stereotactic Body Radiation Therapy

Patients with early stage non-small cell lung cancer (ES-NSCLC) treated with stereotactic body radiation therapy (SBRT) have excellent local control rates although they have a relatively high rate of regional and distant recurrences. Recently, patients with elevated pre-treatment (pre-RT) circulating tumor cells (CTCs) or persistently detectable post-treatment (post-RT) CTCs were found to have significantly increased risk of regional and distant recurrence outside the treatment volume. Knowledge about radiomics biomarkers associated with CTCs may have additional value in predicting these recurrences. This study aims to evaluate the predictability of radiomic phenotypes of intratumoral heterogeneity for pre- and post-RT CTCs in ES-NSCLC patients treated with SBRT. A total of 56 patients with stage I NSCLC treated with SBRT underwent 18F-FDG-PET/CT imaging pre-SBRT and post-SBRT (median, 5 months; range, 3 to 10 months). For each patient, CTCs were assessed via a telomerase-based assay before (“pre”) and within 3 months after SBRT (“post”), and dichotomized at 5 and 1.3 CTCs/mL. Pre-RT, post-RT and delta radiomics features were extracted from the gross tumor volume of the original, wavelet-filtered, Laplacian of Gaussian-filtered PET/CT images, each of which included 1,562 CT and 1,548 PET radiomics features that consisted of shape, first-order, second-order, higher-order local gray-level statistics and global texture features. CT and PET radiomics features were considered different omics data types. Two (CT and PET)-block radiomics-based data integration analysis for biomarker discovery using latent components (DIABLO) was performed to seek for common information between CT and PET radiomics data types through feature selection, while discriminating CTC levels. ROC AUC value and 20-repeated 5-fold cross-validation (CV) were used to evaluate the prediction performance of the DIABLO models. CV prediction scores between one class vs the other were compared using the Wilcoxon rank sum test. For predicting pre-SBRT CTCs, a pre-SBRT radiomics-derived DIABLO model showed the CV AUC of 0.841 (p = 0.018) with two global texture features from wavelet-filtered CT and PET. For predicting post-RT CTCs, post-RT and delta radiomics-derived DIABLO models showed the CV AUCs of 0.794 (p = 0.018) with four global texture features from wavelet-filtered CT and original PET, and 0.799 (p = 0.013) with three first-order features from wavelet-filtered PET and a single second-order texture feature from wavelet-filtered CT. Radiomics signatures that reflect intratumoral anatomic and metabolic heterogeneities derived by maximizing common information between CT and PET may reveal surrogate biomarkers for pre-RT and post-RT CTCs.

Machine learning based on clinico-biological features integrated 18F-FDG PET/CT radiomics for distinguishing squamous cell carcinoma from adenocarcinoma of lung

PurposeTo develop and validate a clinico-biological features and 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) radiomic-based nomogram via machine learning for the pretherapy prediction of discriminating between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) in non-small cell lung cancer (NSCLC).MethodsA total of 315 NSCLC patients confirmed by postoperative pathology between January 2017 and June 2019 were retrospectively analyzed and randomly divided into the training (n = 220) and validation (n = 95) sets. Preoperative clinical factors, serum tumor markers, and PET, and CT radiomic features were analyzed. Prediction models were developed using the least absolute shrinkage and selection operator (LASSO) regression analysis. The performance of the models was evaluated and compared by the area under receiver-operator characteristic (ROC) curve (AUC) and DeLong test. The clinical utility of the models was determined via decision curve analysis (DCA). Then, a nomogram was developed based on the model with the best predictive efficiency and clinical utility and was validated using the calibration plots.ResultsIn total, 122 SCC and 193 ADC patients were enrolled in this study. Four independent prediction models were separately developed to differentiate SCC from ADC using clinical factors-tumor markers, PET radiomics, CT radiomics, and their combination. The DeLong test and DCA showed that the Combined Model, consisting of 2 clinical factors, 2 tumor markers, 7 PET radiomics, and 3 CT radiomic parameters, held the highest predictive efficiency and clinical utility in predicting the NSCLC subtypes compared with the use of these parameters alone in both the training and validation sets (AUCs (95% CIs) = 0.932 (0.900–0.964), 0.901 (0.840–0.957), respectively) (p < 0.05). A quantitative nomogram was subsequently constructed using the independently risk factors from the Combined Model. The calibration curves indicated a good consistency between the actual observations and nomogram predictions.ConclusionThis study presents an integrated clinico-biologico-radiological nomogram that can be accurately and noninvasively used for the individualized differentiation SCC from ADC in NSCLC, thereby assisting in clinical decision making for precision treatment.

Performance of 18F-FDG PET/CT Radiomics for Predicting EGFR Mutation Status in Patients With Non-Small Cell Lung Cancer.

ObjectiveTo assess the performance of pretreatment 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomics features for predicting EGFR mutation status in patients with non-small cell lung cancer (NSCLC).Patients and MethodsWe enrolled total 173 patients with histologically proven NSCLC who underwent preoperative 18F-FDG PET/CT. Tumor tissues of all patients were tested for EGFR mutation status. A PET/CT radiomics prediction model was established through multi-step feature selection. The predictive performances of radiomics model, clinical features and conventional PET-derived semi-quantitative parameters were compared using receiver operating curves (ROCs) analysis.ResultsFour CT and two PET radiomics features were finally selected to build the PET/CT radiomics model. Compared with area under the ROC curve (AUC) equal to 0.664, 0.683 and 0.662 for clinical features, maximum standardized uptake values (SUVmax) and total lesion glycolysis (TLG), the PET/CT radiomics model showed better performance to discriminate between EGFR positive and negative mutations with the AUC of 0.769 and the accuracy of 67.06% after 10-fold cross-validation. The combined model, based on the PET/CT radiomics and clinical feature (gender) further improved the AUC to 0.827 and the accuracy to 75.29%. Only one PET radiomics feature demonstrated significant but low predictive ability (AUC = 0.661) for differentiating 19 Del from 21 L858R mutation subtypes.ConclusionsEGFR mutations status in patients with NSCLC could be well predicted by the combined model based on 18F-FDG PET/CT radiomics and clinical feature, providing an alternative useful method for the selection of targeted therapy.

Adding the temporal domain to PET radiomic features.

Radiomic features, extracted from positron emission tomography, aim to characterize tumour biology based on tracer intensity, tumour geometry and/or tracer uptake heterogeneity. Currently, radiomic features are derived from static images. However, temporal changes in tracer uptake might reveal new aspects of tumour biology. This study aims to explore additional information of these novel dynamic radiomic features compared to those derived from static or metabolic rate images. Thirty-five patients with non-small cell lung carcinoma underwent dynamic [18F]FDG PET/CT scans. Spatial intensity, shape and texture radiomic features were derived from volumes of interest delineated on static PET and parametric metabolic rate PET. Dynamic grey level cooccurrence matrix (GLCM) and grey level run length matrix (GLRLM) features, assessing the temporal domain unidirectionally, were calculated on eight and sixteen time frames of equal length. Spearman's rank correlations of parametric and dynamic features with static features were calculated to identify features with potential additional information. Survival analysis was performed for the non-redundant temporal features and a selection of static features using Kaplan-Meier analysis. Three out of 90 parametric features showed moderate correlations with corresponding static features (ρ≥0.61), all other features showed high correlations (ρ>0.7). Dynamic features are robust independent of frame duration. Five out of 22 dynamic GLCM features showed a negligible to moderate correlation with any static feature, suggesting additional information. All sixteen dynamic GLRLM features showed high correlations with static features, implying redundancy. Log-rank analyses of Kaplan-Meier survival curves for all features dichotomised at the median were insignificant. This study suggests that, compared to static features, some dynamic GLCM radiomic features show different information, whereas parametric features provide minimal additional information. Future studies should be conducted in larger populations to assess whether there is a clinical benefit of radiomics using the temporal domain over traditional radiomics.

Abstract 868: Prediction of clinical benefit to checkpoint blockade in advanced NSCLC patients using radiomics of PET/CT images

Abstract Immunotherapy has emerged as a one of the most successful treatment approach in advanced Non-small Cell Lung Cancer (NSCLC) patients. However, only 25-50% patients obtain durable clinical benefit (DCB), and 7-43% patient may suffer from immune-related severe adverse events. Therefore robust biomarkers that are predictive of response immune-checkpoint blockades at baseline are needed. Though PD-L1 expression by immunohistochemistry (IHC) is the only clinically-approved biomarker to trigger treatment decisions, sampling bias and the dynamic nature of PD-L1 expression can affect the final results. In this study, we investigated the value of PET/CT images in the predicting progression-free survival (PFS) and overall survival (OS) of immunotherapy in advanced NSCLC patients. The retrospective arm of this study included 400 patients with histologically-confirmed NSCLC, and these were split into training (N=284) and test (N=116) cohorts. A residual-convolutional-network model was developed to generate a deep learning score (PDL1-DLS) to predict the PD-L1 expression status with PET/CT images. Another 146 retrospective patients with histologically confirmed stage IIIB-IV NSCLC treated with immunotherapy (IO) were split into training (N=99) and test (N=47) cohorts, and a multiparametric radiomics signature (mpRS) generated from conventional PET and CT radiomics features was developed to predict DCB using an improved least absolute shrinkage and selection operator (LASSO) method. Subsequently, multivariable Cox regression models for PFS and OS prediction were trained with the mpRS, PDL1-DLS, and clinical characteristics, and these were further validated with 48 prospective IO-treated NSCLC patients. The PDL1-DLS significantly discriminated PD-L1 positive and negative patients with AUCs of 0.89 (95%CI:0.84-0.94) and 0.84 (95%CI:0.76-0.92) for training and test cohorts. The mpRS could predict DCB with AUCs of 0.86 (95%CI:0.79-0.94) and 0.83 (95%CI:0.71-0.94) in the training and test cohorts. In both retrospective and prospective IO-treated cohorts, the combination of binarized PDL1-DLS and binarized mpRS significantly improved the prediction of PFS and OS compared to single binarized PDL1-DLS (PFS: p&amp;lt;0.001, OS: p&amp;lt;0.001) or single binarized mpRS (PFS: p&amp;lt;0.040, OS: p&amp;lt;0.10). Subsequent multivariable Cox regression models identified binarized mpRS, binarized PDL1-DLS, ECOG, and histology as significant independent variables, and could achieve significant higher C-indices of 0.75 (95%CI:0.70-0.79) and 0.79 (95%CI:0.73-0.86) in prediction of PFS, 0.79 (95%CI:0.73-0.85) and 0.76 (95%CI:0.61-0.92) in prediction of OS in the retrospective and prospective IO-treated cohorts. We have therefore observed that, prior to therapy initiation, PET/CT fusion images can be used independently to predict PD-L1 status or DCB of immunotherapy in advanced NSCLC patients. Both of these models can be leveraged to improve more precise and individualized decision support in the treatment of patients with advanced NSCLC. Citation Format: Wei Mu, Ilke Tunali, Jhanelle E. Gray, Jin Qi, Matthew B. Schabath, Robert J. Gillies. Prediction of clinical benefit to checkpoint blockade in advanced NSCLC patients using radiomics of PET/CT images [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 868.

Training and validation of a robust PET radiomic-based index to predict distant-relapse-free-survival after radio-chemotherapy for locally advanced pancreatic cancer

PurposeTo assess the value of 18F-Fluorodeoxyglucose (18F-FDG) PET Radiomic Features (RF) in predicting Distant Relapse Free Survival (DRFS) in patients with Locally AdvancedPancreaticCancer (LAPC) treated with radio-chemotherapy. Materials & methodsOne-hundred-ninety-eight RFs were extracted using IBSI (Image Biomarker Standardization Initiative) consistent software from pre-radiotherapy images of 176 LAPC patients treated with moderate hypo-fractionation (44.25 Gy, 2.95 Gy/fr). Tumors were segmented by applying a previously validated semi-automatic method. One-hundred-twenty-six RFs were excluded due to poor reproducibility and/or repeatability and/or inter-scanner variability. The original cohort was randomly split into a training (n = 116) and a validation (n = 60) group. Multi-variable Cox regression was applied to the training group, including only independent RFs in the model. The resulting radiomic index was tested in the validation cohort. The impact of selected clinical variables was also investigated. ResultsThe resulting Cox model included two first order RFs: Center of Mass Shift (COMshift) and 10th Intensity percentile (P10) (p = 0.0005, HR = 2.72, 95%CI = 1.54–4.80), showing worse outcomes for patients with lower COMshift and higher P10. Once stratified by quartile values (<lowest quartile vs >highest quartile vs the remaining), the index properly stratified patients according to their DRFS (p = 0.0024, log-rank test). Performances were confirmed in the validation cohort (p = 0.03, HR = 2.53, 95%CI = 0.96–6.65). The addition of clinical factors did not significantly improve the models’ performance. ConclusionsA radiomic-based index including only two robust PET-RFs predicted DRFS of LAPC patients after radio-chemotherapy. The current results could find relevant applications in the treatment personalization of LAPC. A multi-institution independent validation has been planned.

Radiomics Analysis of [18F]-Fluorodeoxyglucose-Avid Thyroid Incidentalomas Improves Risk Stratification and Selection for Clinical Assessment.

Background: [18F]-Fluorodeoxyglucose (FDG)-avid thyroid lesions incidentally detected on positron emission tomography/computed tomography (PET/CT) scans represent a tumor lesion in about 30% of cases. The present study evaluated the ability of PET metrics and radiomics features to predict final diagnosis of [18F]FDG thyroid incidentalomas (TIs). Methods: A total of 104 patients with 107 TIs were retrospectively studied; 30 nodules (28%) were diagnosed as malignant. After volumetric segmentation of each thyroid lesion, metabolic tumor volume (MTV), total lesion glycolysis (TLG), standardized uptake values (SUVs), and metabolic heterogeneity were estimated, and 107 radiomics features were extracted following a standard protocol. Results: MTV, TLG, SUVmax, SUVmean, and SUVpeak among functional PET parameters, and gray-level co-occurrence matrix (GLCM)_InverseDifferenceMoment, shape_Sphericity, GLCM_SumSquares, firstorder_Maximum2DDiameterSlice, firstorder_Energy, and GLCM_Contrast among nonredundant radiomics features, showed significantly different values between malignant and benign TIs (Mann-Whitney U-test, p < 0.01 for all). Univariate logistic regression revealed that these parameters demonstrated good ability to predict final diagnosis of TIs (p < 0.02 for all). Shape_Sphericity was the best predictor classifying 82% of TIs correctly (p < 0.0001). Only TLG, SUVmax, and shape_Sphericity retained significance (p < 0.0001) by multivariate analysis. Malignant lesion prevalence increased from 7% to 100% in accordance with the number (score, 0-3) of the three positive parameters present (χ2 trend, p < 0.0001). A score of 0 excludes malignant TIs with a negative predictive value of 93%, while a score of 3 predicted malignancy with a positive predictive value of 100%. Conclusions: PET metrics and radiomics analysis can improve identification of [18F]FDG-avid TIs at high risk of malignancy. A model based on TLG, SUVmax, and shape_Sphericity may allow prediction of a final diagnosis, providing useful information for the management of TIs.

Additional value of metabolic parameters to PET/CT-based radiomics nomogram in predicting lymphovascular invasion and outcome in lung adenocarcinoma.

Lymphovascular invasion (LVI) impairs surgical outcomes in lung adenocarcinoma (LAC) patients. Preoperative prediction of LVI is challenging by using traditional clinical and imaging parameters. The purpose of this study was to investigate the value of the radiomics nomogram integrating clinical factors, CT features, and maximum standardized uptake value (SUVmax) to predict LVI and outcome in LAC and to evaluate the additional value of the SUVmax to the PET/CT-based radiomics nomogram. A total of 272 LAC patients (87 LVI-present LACs and 185 LVI-absent LACs) with PET/CT scans were retrospectively enrolled, and 160 patients with SUVmax ≥ 2.5 of them were used for PET radiomics analysis. Clinical data and CT features were analyzed to select independent LVI predictors. The performance of the independent LVI predictors and SUVmax was evaluated. Two-dimensional (2D) and three-dimensional (3D) CT radiomics signatures (RSs) and PET-RS were constructed with the least absolute shrinkage and selection operator algorithm and radiomics scores (Rad-scores) were calculated. The radiomics nomograms, incorporating Rad-score and independent clinical and CT factors, with SUVmax (RNWS) or without SUVmax (RNWOS) were built. The performance of the models was assessed with respect to calibration, discrimination, and clinical usefulness. All the clinical, PET/CT, pathologic, therapeutic, and radiomics parameters were assessed to identify independent predictors of progression-free survival (PFS). CT morphology was the independent LVI predictor. SUVmax provided better discrimination capability compared with CT morphology in the training set (P < 0.001) and test set (P = 0.042). A total of 1409 CT and PET radiomics features were extracted and reduced to 8, 8, and 10 features to build the 2D CT-RS, 3D CT-RS, and the PET-RS, respectively. There was no significant difference in AUC between the 2D-RS and 3D-RS (P > 0.05), and 2D CT-RS showed a relatively higher AUC than 3D CT-RS. The CT-RS, the CT-RNWOS, and the CT-RNWS showed good discrimination in the training set (AUC [area under the curve], 0.799, 0.796, and 0.851, respectively) and the test set (AUC, 0.818, 0.822, and 0.838, respectively). There was significant difference in AUC between the CT-RNWS and CT-RNWOS (P = 0.044) in the training set. Decision curve analysis (DCA) demonstrated the CT-RNWS outperformed the CT-RS and the CT-RNWOS in terms of clinical usefulness. Furthermore, DCA showed the PETCT-RNWS provided the highest net benefit compared with the PET-RNWS and CT-RNWS. PFS was significantly different between the pathologic and RNWS-predicted LVI-present and LVI-absent patients (P < 0.001). Carbohydrate antigen 125 (CA125), carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), pathologic LVI, histologic subtype, and SUVmax were independent predictors of PFS in the 244 CT-RNWS-predicted cohort; and CA125, NSE, pathologic LVI, and SUVmax were the independent predictors of PFS in the 141 PETCT-RNWS-predicted cohort. The radiomics nomogram, incorporating Rad-score, clinical and PET/CT parameters, shows favorable predictive efficacy for LVI status in LAC. Pathologic LVI and SUVmax are associated with LAC prognosis.