PET Features Research Articles

Extracting and Selecting Robust Radiomic Features from PET/MR Images in Nasopharyngeal Carcinoma.

This work aims to study the variation, robustness, and feature redundancy of PET/MR radiomic features in the primary tumor of nasopharyngeal carcinoma (NPC). PET/MR scans of 21 NPC patients were used in this study. The primary tumor volumes were defined using PET, T2-weighted-MR (T2-MR), and diffusion-weighted MR (DW-MR) images. A random-dilation-erosion method was used to simulate 10 sets of tumor volumes for identifying features invariant with manual segmentation uncertainties. Feature robustness was evaluated against imaging modalities, pixel sizes, slice thickness, and grey-level bin sizes using intraclass correlation coefficient (ICC) and spearman correlation coefficient. Feature redundancy was analyzed using the hierarchical cluster analysis. Voxel size of 0.5×0.5×1.0mm3 was found optimal for robust feature extraction from PET and MR. Normalized grey level of 64 and 128 was suggested for PET and MR, respectively. The features from wavelet-transformed images were less stable than those from the original images. The robustness analysis and volume correlation analysis identified 335 (62.04%) PET features, 240 (44.44%) T2-MR features, and 366 (67.78%) DW-MR features. The cluster analysis grouped PET, T2-MR, and DW-MR features into 106, 83, and 133 representative features, respectively. The present study analyzed and identified robust features extracted from tumor volumes on PET/MR, which can provide guidance and promote standardization for PET/MR radiomic studies in NPC.

PET/CT radiomics signature of human papilloma virus association in oropharyngeal squamous cell carcinoma

To devise, validate, and externally test PET/CT radiomics signatures for human papillomavirus (HPV) association in primary tumors and metastatic cervical lymph nodes of oropharyngeal squamous cell carcinoma (OPSCC). We analyzed 435 primary tumors (326 for training, 109 for validation) and 741 metastatic cervical lymph nodes (518 for training, 223 for validation) using FDG-PET and non-contrast CT from a multi-institutional and multi-national cohort. Utilizing 1037 radiomics features per imaging modality and per lesion, we trained, optimized, and independently validated machine-learning classifiers for prediction of HPV association in primary tumors, lymph nodes, and combined "virtual" volumes of interest (VOI). PET-based models were additionally validated in an external cohort. Single-modality PET and CT final models yielded similar classification performance without significant difference in independent validation; however, models combining PET and CT features outperformed single-modality PET- or CT-based models, with receiver operating characteristic area under the curve (AUC) of 0.78, and 0.77 for prediction of HPV association using primary tumor lesion features, in cross-validation and independent validation, respectively. In the external PET-only validation dataset, final models achieved an AUC of 0.83 for a virtual VOI combining primary tumor and lymph nodes, and an AUC of 0.73 for a virtual VOI combining all lymph nodes. We found that PET-based radiomics signatures yielded similar classification performance to CT-based models, with potential added value from combining PET- and CT-based radiomics for prediction of HPV status. While our results are promising, radiomics signatures may not yet substitute tissue sampling for clinical decision-making.

Radiogenomics Based on PET Imaging

Radiogenomics or imaging genomics is a novel omics strategy of associating imaging data with genetic information, which has the potential to advance personalized medicine. Imaging features extracted from PET or PET/CT enable assessment of in vivo functional and physiological activity and provide comprehensive tumor information non-invasively. However, PET features are considered secondary to features on conventional imaging, and there has not yet been a review of the radiogenomic approach using PET features. This review article summarizes the current state of PET-based radiogenomic research for cancer, which discusses some of its limitations and directions for future study.

PET/MRI Radiomics in Rectal Cancer: a Pilot Study on the Correlation Between PET- and MRI-Derived Image Features with a Clinical Interpretation.

The aim of this study was to explore possible correlations among different imaging features from 2-deoxy-2-[18F]fluoro-D-Glucose positron emission tomography/magnetic resonance imaging (PET/MRI) in rectal cancer (RC). RC patients who underwent PET/MRI were enrolled. A region of interest (ROI) was drawn around each primary RC on PET/MRI images (PET, pelvic axial T2w, and apparent diffusion coefficient maps(ADC)). Multiple imaging features were assessed, and Pearson's correlation was used to explore possible correlations among them. A total of 13 patients were included, mean age 56.1years old, 6 females. A strong inverse correlation was observed between SUVpeak and ADCmean values, MTV and T2 sphericity, MTV and ADC sphericity, MTV and T2 entropy, and TLG and ADC sphericity. There was also strong direct correlation between PET entropy and ADC sphericity. In conclusion, several clinically relevant correlations were observed between PET and MRI imaging features. These findings show how the use of both modalities provides complementary information.

Textural features in FDG-PET/CT can predict outcome in melanoma patients to treatment with Vemurafenib and Ipililumab.

Recently, textural parameters assessed in FDG-PET/CT as surrogate marker for tumor heterogeneity have been shown to provide prognostic power. Therefore, we investigated the use of such parameters in FDG-PET/CT examinations before the start of immunotherapy with vemurafenib or ipilimumab in patients with malignant melanoma. In this retrospective analysis 26 patients with histologically proven advanced melanoma were included. FGD-PET/CT was performed before the start of treatment either with vemurafenib (n = 9) or ipilimumab (n = 17) and tumors were analyzed for textural parameters as well as conventional PET features. Lesions were classified as responding or not responding following PERCIST criteria. ROC analysis was performed to analyze the predictive power and cut-off values. In addition, the change of maximum SUV of the lesions between pretherapeutic PET/CT and another PET/CT performed about 12 weeks after start of treatment was evaluated and correlated with the pretreatment parameters. In both groups, six textural parameters showed statistically significant predictive power as well as the metabolic tumor volume. In the group treated with vemurafenib eight additional textural parameters as well as the maximum and mean SUV and the TLG showed significance. A statistically significant correlation between the change of maximum SUV in the course of treatment and the pretherapeutic parameters was found in both treatment groups for three textural features. In patients with malignant melanoma textural parameters in pretherapeutic FDG-PET/CT examinations seem to have prognostic power for treatment response of immunotherapy with vemurafenib and ipilimumab. This can be an important step towards personalized tumor therapy.

Predicting late radiation-induced xerostomia with parotid gland PET biomarkers and dose metrics

PurposeTo assess associations between parotid gland PET biomarkers and late radiation-induced xerostomia, and to validate improvement of xerostomia predictive models by adding pre-treatment PET features to models based on dose and pre-treatment xerostomia. Materials and MethodsIntensity PET features from 47 patients treated on institutional prospective clinical trials for HPV-associated oropharyngeal squamous cell carcinoma with uniform chemoRT were analyzed. Associations between 90th percentile of the parotid gland standardized uptake values (P90) from pre-treatment and post-treatment PET scans, mean parotid gland doses, and late xerostomia defined by the Xerostomia Questionnaire (XQ) and salivary flow rates were quantified. Multivariable analysis was applied for dose and PET features using penalized logistic regression for feature selection and generation of predictive models using the LASSO technique, and optimism bias was estimated by bootstrap resampling. ResultsSignificant associations between late xerostomia and both mean parotid gland dose and P90 were demonstrated, and were generally stronger for post-treatment PET scans. The addition of P90 from pre-treatment PET scans improved the prediction model for late moderate or severe xerostomia compared to the base model, from AUC = 0.74 to 0.78 (p-value <0.001) for XQ summary score and from 0.77 to 0.84 (p-value <0.001) for the single eating-related XQ item with the largest inter-patient variability; however, only the latter remained significant on cross validation (AUC = 0.69 to 0.70 and 0.73 to 0.80, respectively). ConclusionsThe addition of pre-treatment parotid gland PET biomarkers improved a predictive model for late patient-reported xerostomia over dose and pre-treatment xerostomia.

Next-Generation Radiogenomics Sequencing for Prediction of EGFR and KRAS Mutation Status in NSCLC Patients Using Multimodal Imaging and Machine Learning Algorithms.

Considerable progress has been made in the assessment and management of non-small cell lung cancer (NSCLC) patients based on mutation status in the epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma viral oncogene (KRAS). At the same time, NSCLC management through KRAS and EGFR mutation profiling faces challenges. In the present work, we aimed to evaluate a comprehensive radiomics framework that enabled prediction of EGFR and KRAS mutation status in NSCLC patients based on radiomic features from low-dose computed tomography (CT), contrast-enhanced diagnostic quality CT (CTD), and positron emission tomography (PET) imaging modalities and use of machine learning algorithms. Our study involved NSCLC patients including 150 PET, low-dose CT, and CTD images. Radiomic features from original and preprocessed (including 64 bin discretizing, Laplacian-of-Gaussian (LOG), and Wavelet) images were extracted. Conventional clinically used standard uptake value (SUV) parameters and metabolic tumor volume (MTV) were also obtained from PET images. Highly correlated features were pre-eliminated, and false discovery rate (FDR) correction was performed with the resulting q-values reported for univariate analysis. Six feature selection methods and 12 classifiers were then used for multivariate prediction of gene mutation status (provided by polymerase chain reaction (PCR)) in patients. We performed 10-fold cross-validation for model tuning to improve robustness, and our developed models were assessed on an independent validation set with 68 patients (common in all three imaging modalities). The average area under the receiver operator characteristic curve (AUC) was utilized for performance evaluation. The best predictive power for conventional PET parameters was achieved by SUVpeak (AUC 0.69, p value = 0.0002) and MTV (AUC 0.55, p value = 0.0011) for EGFR and KRAS, respectively. Univariate analysis of extracted radiomics features improved AUC performance to 0.75 (q-value 0.003, Short-Run Emphasis feature of GLRLM from LOG preprocessed image of PET with sigma value 1.5) and 0.71 (q-value 0.00005, Large Dependence Low Gray-Level Emphasis feature of GLDM in LOG preprocessed image of CTD with sigma value 5) for EGFR and KRAS, respectively. Furthermore, multivariate machine learning-based AUC performances were significantly improved to 0.82 for EGFR (LOG preprocessed image of PET with sigma 3 with variance threshold (VT) feature selector and stochastic gradient descent (SGD) classifier (q-value = 4.86E-05) and 0.83 for KRAS (LOG preprocessed image of CT with sigma 3.5 with select model (SM) feature selector and SGD classifier (q-value = 2.81E-09). Our work demonstrated that non-invasive and reliable radiomics analysis can be successfully used to predict EGFR and KRAS mutation status in NSCLC patients. We demonstrated that radiomic features extracted from different image-feature sets could be used for EGFR and KRAS mutation status prediction in NSCLC patients and showed improved predictive power relative to conventional image-derived metrics.

Comparison of Dual-Tracer PET and CT Features to Conventional Risk Categories in Assessing Response to 177Lu-PSMA-617 Therapy for Metastatic Prostate Adenocarcinoma with Urinary Bladder Involvement

The present communication details the imaging characteristics, peculiarities, and response to 177Lu-labeled prostate-specific membrane antigen (PSMA)-617-targeted radioligand therapy (PRLT) in accordance with Gleason score and use of dual-tracer PET (68Ga-PSMA-11 and 18F-FDG) in patients with urinary bladder invasion or metastasis by prostate cancer, including the prognostic value of 18F-FDG PET in predicting response to treatment. The CT attenuation units (Hounsfield units) correlated with the prostate primary in the case of direct tumor extension from the prostate, whereas in hematogenous metastatic seeding the Hounsfield units were lower than in the primary prostatic tumor. A favorable outcome to 177Lu-PSMA-617 PRLT was observed in patients with low or no baseline 18F-FDG uptake despite a high Gleason score and a high-risk National Comprehensive Cancer Network prognostic category and did not correlate with the latter alone, whereas a high SUVmax on 18F-FDG PET/CT was associated with an adverse outcome. These findings suggest a promising role for 18F-FDG PET/CT in predicting therapeutic outcomes more confidently, and hence the concept of dual-tracer PET appears to hold good in prostate adenocarcinoma theranostics.

Development and validation of a radiomics signature on differentially expressed features of 18F-FDG PET to predict treatment response of concurrent chemoradiotherapy in thoracic esophagus squamous cell carcinoma

Background and purposeTo investigate potential image markers for early prediction of treatment response on thoracic esophagus squamous cell carcinoma (ESCC) treated with concurrent chemoradiotherapy (CCRT). Materials and methods159 thoracic ESCC patients enrolled from two institutions were divided into training and validation sets. A total of 944 radiomics features were extracted from pretreatment 18F-FDG PET images. We first performed the inter-observer reproducibility test in 10 pairs of patients (responders vs. nonresponders), and the limma package was used to identify differentially expressed features (DEFs). Then the least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation was used to construct a treatment response related radiomics signature. Finally, the performance was assessed in both sets with receiver operating characteristic (ROC) curves and Kaplan-Meier analysis. ResultsAfter the inter-observer test, 691 features were considered reproducible and been retained (ICC > 0.9). 61 DEFs were selected from limma and entered into the LASSO logistic regression model. The radiomics signature was significantly associated with treatment response in the training (p < 0.001) and validation set (p = 0.026), which achieved area under curve (AUC) values of 0.844 and 0.835, respectively. Delong test results of two ROCs showed no significant difference (p = 0.918). The cut-off value of the radiomics signature could successfully divide patients into high-risk and low-risk groups in both sets. ConclusionThis study indicated that the proposed radiomics signature could be a useful image marker to predict the therapeutic response of thoracic ESCC patients treated with CCRT.

Autosomal dominantly inherited alzheimer disease: Analysis of genetic subgroups by machine learning

Despite subjects with Dominantly-Inherited Alzheimer’s Disease (DIAD) represent less than 1% of all Alzheimer’s Disease (AD) cases, the Dominantly Inherited Alzheimer Network (DIAN) initiative constitutes a strong impact in the understanding of AD disease course with special emphasis on the presyptomatic disease phase. Until now, the 3 genes involved in DIAD pathogenesis (PSEN1, PSEN2 and APP) have been commonly merged into one group (Mutation Carriers, MC) and studied using conventional statistical analysis. Comparisons between groups using null-hypothesis testing or longitudinal regression procedures, such as the linear-mixed-effects models, have been assessed in the extant literature.Within this context, the work presented here performs a comparison between different groups of subjects by considering the 3 genes, either jointly or separately, and using tools based on Machine Learning (ML). This involves a feature selection step which makes use of ANOVA followed by Principal Component Analysis (PCA) to determine which features would be realiable for further comparison purposes. Then, the selected predictors are classified using a Support-Vector-Machine (SVM) in a nested k-Fold cross-validation resulting in maximum classification rates of 72–74% using PiB PET features, specially when comparing asymptomatic Non-Carriers (NC) subjects with asymptomatic PSEN1 Mutation-Carriers (PSEN1-MC). Results obtained from these experiments led to the idea that PSEN1-MC might be considered as a mixture of two different subgroups including: a first group whose patterns were very close to NC subjects, and a second group much more different in terms of imaging patterns. Thus, using a k-Means clustering algorithm it was determined both subgroups and a new classification scenario was conducted to validate this process. The comparison between each subgroup vs. NC subjects resulted in classification rates around 80% underscoring the importance of considering DIAN as an heterogeneous entity.

18F-fluorodeoxyglucose positron emission tomography in dementia with Lewy bodies.

Among individuals with dementia with Lewy bodies, pathologic correlates of clinical course include the presence and extent of coexisting Alzheimer’s pathology and the presence of transitional or diffuse Lewy body disease. The objectives of this study are to determine (i) whether 18F-fluorodeoxyglucose PET signature patterns of dementia with Lewy bodies are associated with the extent of coexisting Alzheimer’s pathology and the presence of transitional or diffuse Lewy body disease and (ii) whether these 18F-fluorodeoxyglucose pattern(s) are associated with clinical course in dementia with Lewy bodies. Two groups of participants were included: a pathology-confirmed subset with Lewy body disease (n = 34) and a clinically diagnosed group of dementia with Lewy bodies (n = 87). A subset of the clinically diagnosed group was followed longitudinally (n = 51). We evaluated whether 18F-fluorodeoxyglucose PET features of dementia with Lewy bodies (higher cingulate island sign ratio and greater occipital hypometabolism) varied by Lewy body disease subtype (transitional versus diffuse) and Braak neurofibrillary tangle stage. We investigated whether the PET features were associated with the clinical trajectories by performing regression models predicting Clinical Dementia Rating Scale Sum of Boxes. Among autopsied participants, there was no difference in cingulate island sign or occipital hypometabolism by Lewy body disease type, but those with a lower Braak tangle stage had a higher cingulate island sign ratio compared to those with a higher Braak tangle stage. Among the clinically diagnosed dementia with Lewy bodies participants, a higher cingulate island ratio was associated with better cognitive scores at baseline and longitudinally. A higher 18F-fluorodeoxyglucose PET cingulate island sign ratio was associated with lower Braak tangle stage at autopsy, predicted a better clinical trajectory in dementia with Lewy body patients and may allow for improved prognostication of the clinical course in this disease.

Correlation of texture feature analysis with bone marrow infiltration in initial staging of patients with lymphoma using 18F-fluorodeoxyglucose positron emission tomography combined with computed tomography.

PurposeTo explore whether radiomic features of fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomo-graphy–computed tomography (PET/CT) has association with bone marrow infiltration (BMI) in comparison to other conventional PET metrics.Material and methodsForty-four patients (with pathologically proven lymphoma disease) underwent staging 18F-FDG PET/CT scan. Primary tumour was semi-automatically or manually segmented with a threshold standardised uptake value (SUV) of 3. A total of 73 features were extracted from eight different textures. Spearman correlation was used to test the correlation of features with conventional quantitative metrics such as SUV, metabolic tumour volume, and total lesion glycolysis. Specificity and sensitivity (including 95% confidence intervals [CI]) for each of the studied parameters were derived using receiver operative characteristic (ROC) curves. Univariate and multivariate analyses were used to identify independent predictors associated with BMI.ResultsCorrelation between conventional PET metrics and features ranged between 0.50 and 0.97 for positive correlation (33 significant association features) and ranged from –0.52 to –0.97 for inverse correlation (three significant association features) for both strong and moderate correlations. Analysis of ROC curves showed that high-intensity long-run emphasis 4 bin, high-intensity large zone emphasis 64 bin, long-run emphasis (LRE) 64 bin, large-zone emphasis 64 bin, max spectrum 8 bin, busyness 64 bin, and code similarity 32 and 64 bin were significant discriminators of BMI among other features (area under curve > 0.682, p < 0.05). Univariate analyses of texture features showed that code similarity and long-run emphasis (both 64 bin) were significant predictors of bone marrow involvement. Multivariate analyses revealed that LRE (64 bin, p = 0.031) with an odds ratio of 1.022 and 95% CI of (1.002–1.043) were independent variables for bone marrow involvement.Conclusions18F-FDG PET/CT radiomic features are synergistic to visual assessment of BMI in patients diagnosed with lymphoma using 18F-FDG PET/CT. Further assessment of long-run emphasis is highly warranted.

Association of metabolic and genetic heterogeneity in head and neck squamous cell carcinoma with prognostic implications: integration of FDG PET and genomic analysis

PurposeThe linkage between the genetic and phenotypic heterogeneity of the tumor has not been thoroughly evaluated. Herein, we investigated how the genetic and metabolic heterogeneity features of the tumor are associated with each other in head and neck squamous cell carcinoma (HNSC). We further assessed the prognostic significance of those features.MethodsThe mutant-allele tumor heterogeneity (MATH) score (n = 508), a genetic heterogeneity feature, and tumor glycolysis feature (GlycoS) (n = 503) were obtained from the HNSC dataset in the cancer genome atlas (TCGA). We identified matching patients (n = 33) who underwent 18F-fluorodeoxyglucose positron emission tomography (FDG PET) from the cancer imaging archive (TCIA) and obtained the following information from the primary tumor: metabolic, metabolic-volumetric, and metabolic heterogeneity features. The association between the genetic and metabolic features and their prognostic values were assessed.ResultsTumor metabolic heterogeneity and metabolic-volumetric features showed a mild degree of association with MATH (n = 25, ρ = 0.4~0.5, P < 0.05 for all features). The patients with higher FDG PET features and MATH died sooner. Combination of MATH and tumor metabolic heterogeneity features showed a better stratification of prognosis than MATH. Also, higher MATH and GlycoS were associated with significantly worse overall survival (n = 499, P = 0.002 and 0.0001 for MATH and GlycoS, respectively). Furthermore, both MATH and GlycoS independently predicted overall survival after adjusting for clinicopathologic features and the other (P = 0.015 and 0.006, respectively).ConclusionBoth tumor metabolic heterogeneity and metabolic-volumetric features assessed by FDG PET showed a mild degree of association with genetic heterogeneity in HNSC. Both metabolic and genetic heterogeneity features were predictive of survival and there was an additive prognostic value when the metabolic and genetic heterogeneity features were combined. Also, MATH and GlycoS were independent prognostic factors in HNSC; they can be used for precise prognostication once validated.

Pretreatment 18F-FDG PET/CT Radiomics Predict Local Recurrence in Patients Treated with Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer: A Multicentric Study.

The aim of this retrospective multicentric study was to develop and evaluate a prognostic 18F-FDG PET/CT radiomic signature in early-stage non-small cell lung cancer patients treated with stereotactic body radiotherapy (SBRT). Methods: Patients from 3 different centers (n = 27, 29, and 8) were pooled to constitute the training set, whereas the patients from a fourth center (n = 23) were used as the testing set. The primary endpoint was local control. The primary tumor was semiautomatically delineated in the PET images using the fuzzy locally adaptive Bayesian algorithm, and manually in the low-dose CT images. In total, 184 Image Biomarkers Standardization Initiative-compliant radiomic features were extracted. Seven clinical and treatment parameters were included. We used ComBat to harmonize radiomic features extracted from the 4 institutions relying on different PET/CT scanners. In the training set, variables found significant in the univariate analysis were fed into a multivariate regression model, and models were built by combining independent prognostic factors. Results: Median follow-up was 21.1 mo (range, 1.7-63.4 mo) and 25.5 mo (range, 7.7-57.8 mo) in training and testing sets, respectively. In univariate analysis, none of the clinical variables, 2 PET features, and 2 CT features were significantly predictive of local control. The best predictive models in the training set were obtained by combining one feature from PET (Information Correlation 2) and one feature from CT (flatness), reaching a sensitivity of 100% and a specificity of 96%. Another model combining 2 PET features (Information Correlation 2 and strength) reached sensitivity of 100% and specificity of 88%, both with an undefined hazard ratio (P < 0.001). The latter model obtained an accuracy of 0.91 (sensitivity, 100%; specificity, 81%), with a hazard ratio undefined (P = 0.023) in the testing set; however, other models relying on CT radiomic features only or the combination of PET and CT features failed to validate in the testing set. Conclusion: We showed that 2 radiomic features derived from 18F-FDG PET were independently associated with local control in patients with non-small cell lung cancer undergoing SBRT and could be combined in an accurate predictive model. This model could provide local relapse-related information and could be helpful in clinical decision making.

Prediction of Overall Survival and Progression-Free Survival by the 18F-FDG PET/CT Radiomic Features in Patients with Primary Gastric Diffuse Large B-Cell Lymphoma.

Purpose. To determine whether the radiomic features of 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) contribute to prognosis prediction in primary gastric diffuse large B-cell lymphoma (PG-DLBCL) patients. Methods. This retrospective study included 35 PG-DLBCL patients who underwent PET/CT scans at West China Hospital before curative treatment. The volume of interest (VOI) was drawn around the tumor, and radiomic analysis of the PET and CT images, within the same VOI, was conducted. The metabolic and textural features of PET and CT images were evaluated. Correlations of the extracted features with the overall survival (OS) and progression-free survival (PFS) were evaluated. Univariate and multivariate analyses were conducted to assess the prognostic value of the radiomic parameters. Results. In the univariate model, many of the textural features, including kurtosis and volume, extracted from the PET and CT datasets were significantly associated with survival (5 for OS and 7 for PFS (PET); 7 for OS and 14 for PFS (CT)). Multivariate analysis identified kurtosis (hazard ratio (HR): 28.685, 95% confidence interval (CI): 2.067–398.152, p=0.012), metabolic tumor volume (MTV) (HR: 26.152, 95% CI: 2.089–327.392, p=0.011), and gray-level nonuniformity (GLNU) (HR: 14.642, 95% CI: 2.661–80.549, p=0.002) in PET and sphericity (HR: 11.390, 95% CI: 1.360–95.371, p=0.025) and kurtosis (HR: 11.791, 95% CI: 1.583–87.808, p=0.016), gray-level nonuniformity (GLNU) (HR: 6.934, 95% CI: 1.069–44.981, p=0.042), and high gray-level zone emphasis (HGZE) (HR: 9.805, 95% CI: 1.359–70.747, p=0.024) in CT as independent prognostic factors. Conclusion. 18F-FDG PET/CT radiomic features are potentially useful for survival prediction in PG-DLBCL patients. However, studies with larger cohorts are needed to confirm the clinical prognostication of these parameters.

11C-methionine-PET for differentiating recurrent brain tumor from radiation necrosis: radiomics approach with random forest classifier

Differentiating recurrent brain tumor from radiation necrosis is often difficult. This study aims to investigate the efficacy of 11C-methionine (MET)-PET radiomics for distinguishing recurrent brain tumor from radiation necrosis, as compared with conventional tumor-to-normal cortex (T/N) ratio evaluation. We enrolled 41 patients with metastatic brain tumor or glioma treated using radiation therapy who underwent MET-PET. The area with a standardized uptake value > 1.3 times that of the normal brain cortex was contoured. Forty-two PET features were extracted and used in a random forest classifier and the diagnostic performance was evaluated using a 10-fold cross-validation scheme. Gini index was measured to identify relevant PET parameters for classification. The reference standard was surgical histopathological analysis or more than 6 months of follow-up with MRI. Forty-four lesions were used for the analysis. Thirty-three and 11 lesions were confirmed as recurrent brain tumor and radiation necrosis, respectively. Radiomics and T/N ratio evaluation showed sensitivities of 90.1% and 60.6%, and specificities of 93.9% and 72.7% with areas under the curve of 0.98 and 0.73, respectively. Gray level co-occurrence matrix dissimilarity was the most pertinent feature for diagnosis. MET-PET radiomics yielded excellent outcome for differentiating recurrent brain tumor from radiation necrosis, which outperformed T/N ratio evaluation.

Predictive Power of a Radiomic Signature Based on 18F-FDG PET/CT Images for EGFR Mutational Status in NSCLC.

Radiomics has become an area of interest for tumor characterization in 18F-Fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) imaging. The aim of the present study was to demonstrate how imaging phenotypes was connected to somatic mutations through an integrated analysis of 115 non-small cell lung cancer (NSCLC) patients with somatic mutation testings and engineered computed PET/CT image analytics. A total of 38 radiomic features quantifying tumor morphological, grayscale statistic, and texture features were extracted from the segmented entire-tumor region of interest (ROI) of the primary PET/CT images. The ensembles for boosting machine learning scheme were employed for classification, and the least absolute shrink age and selection operator (LASSO) method was used to select the most predictive radiomic features for the classifiers. A radiomic signature based on both PET and CT radiomic features outperformed individual radiomic features, the PET or CT radiomic signature, and the conventional PET parameters including the maximum standardized uptake value (SUVmax), SUVmean, SUVpeak, metabolic tumor volume (MTV), and total lesion glycolysis (TLG), in discriminating between mutant-type of epidermal growth factor receptor (EGFR) and wild-type of EGFR- cases with an AUC of 0.805, an accuracy of 80.798%, a sensitivity of 0.826 and a specificity of 0.783. Consistently, a combined radiomic signature with clinical factors exhibited a further improved performance in EGFR mutation differentiation in NSCLC. In conclusion, tumor imaging phenotypes that are driven by somatic mutations may be predicted by radiomics based on PET/CT images.

A Novel Adaptive PET/CT Image Fusion Algorithm

Background: Lung cancer is one of the common malignant tumors. The successful diagnosis of lung cancer depends on the accuracy of the image obtained from medical imaging modalities. Objective: The fusion of CT and PET is combining the complimentary and redundant information both images and can increase the ease of perception. Since the existing fusion method sare not perfect enough, and the fusion effect remains to be improved, the paper proposes a novel method called adaptive PET/CT fusion for lung cancer in Piella framework. Methods: This algorithm firstly adopted the DTCWT to decompose the PET and CT images into different components, respectively. In accordance with the characteristics of low-frequency and high-frequency components and the features of PET and CT image, 5 membership functions are used as a combination method so as to determine the fusion weight for low-frequency components. In order to fuse different high-frequency components, we select the energy difference of decomposition coefficients as the match measure, and the local energy as the activity measure; in addition, the decision factor is also determined for the high-frequency components. Results: The proposed method is compared with some of the pixel-level spatial domain image fusion algorithms. The experimental results show that our proposed algorithm is feasible and effective. Conclusion: Our proposed algorithm can better retain and protrude the lesions edge information and the texture information of lesions in the image fusion.

Metabolic Biomarker-Based BRAFV600 Mutation Association and Prediction in Melanoma.

The aim of this study was to associate and predict B-rapidly accelerated fibrosarcoma valine 600 (BRAFV600) mutation status with both conventional and radiomics 18F-FDG PET/CT features, while exploring several methods of feature selection in melanoma radiomics. Methods: Seventy unresectable stage III-IV melanoma patients who underwent a baseline 18F-FDG PET/CT scan were identified. Patients were assigned to the BRAFV600 group or BRAF wild-type group according to mutational status. 18F-FDG uptake quantification was performed by semiautomatic lesion delineation. Four hundred eighty radiomics features and 4 conventional PET features (SUVmax, SUVmean, SUVpeak, and total lesion glycolysis) were extracted per lesion. Six different methods of feature selection were implemented, and 10-fold cross-validated predictive models were built for each. Model performances were evaluated with areas under the curve (AUCs) for the receiver operating characteristic curves. Results: Thirty-five BRAFV600 mutated patients (100 lesions) and 35 BRAF wild-type patients (79 lesions) were analyzed. AUCs predicting the BRAFV600 mutation varied from 0.54 to 0.62 and were susceptible to feature selection method. The best AUCs were achieved by feature selection based on literature, a penalized binary logistic regression model, and random forest model. No significant difference was found between the BRAFV600 and BRAF wild-type group in conventional PET features or predictive value. Conclusion: BRAFV600 mutation status is not associated with, nor can it be predicted with, conventional PET features, whereas radiomics features were of low predictive value (AUC = 0.62). We showed feature selection methods to influence predictive model performance, describing and evaluating 6 unique methods. Detecting BRAFV600 status in melanoma based on 18F-FDG PET/CT alone does not yet provide clinically relevant knowledge.

MLTI-17. DIFFERENTIATION OF RADIATION INJURY FROM RECURRENT BRAIN METASTASIS USING COMBINED FET PET/MRI RADIOMICS

BACKGROUND: The aim of this study was to investigate the potential of combined radiomics textural feature analysis of contrast-enhanced MRI (CE MRI) and static O-(2-[18F]fluoroethyl)-L-tyrosine(FET) PET for the differentiation of recurrent brain metastasis from radiation injury. PATIENTS AND METHODS: Fifty-two patients with newly diagnosed or progressive contrast-enhancing brain lesions on MRI after radiotherapy (predominantly radiosurgery, 84% of patients) of brain metastases were additionally investigated using FET PET. Based on histology (n=19) or clinicoradiological follow-up (n=33), local recurrent brain metastases were diagnosed in 21 patients (40%) and radiation injury in 31 patients (60%). Forty-two features (shape-based, first and second order features) were calculated on both unfiltered and filtered CE MRI and summed FET PET images (20–40 min p.i). After feature selection, logistic regression models using a maximum of five features to avoid overfitting were calculated for each imaging modality separately and for the combined FET PET/MRI features. The resulting models were validated using cross-validation. Diagnostic accuracies were calculated for each imaging modality separately as well as for the combined model. RESULTS: For differentiation between radiation injury and brain metastasis recurrence, textural features extracted from CE MRI had a diagnostic accuracy of 81%. FET PET textural features revealed a slightly higher diagnostic accuracy of 83%. However, the highest diagnostic accuracy was obtained when combining CE MRI and FET PET features (accuracy, 89%). CONCLUSION: Our findings suggest that combined FET PET/MRI radiomics using textural feature analysis offers a great potential to contribute significantly to the management of patients with brain metastases. SUPPORT: This work was supported by the Wilhelm-Sander Stiftung, Germany