Search

Purpose: To develop machine learning models to predict regional and/or distant recurrence in patients with early-stage non-small cell lung cancer (ES-NSCLC) after stereotactic body radiation therapy (SBRT) using [ 18 F]FDG PET/CT and CT radiomics combined with clinical and dosimetric parameters., Methods: We retrospectively collected 464 patients (60% for training and 40% for testing) from University Hospital of Liège and 63 patients from University Hospital of Brest (external testing set) with ES-NSCLC treated with SBRT between 2010 and 2020 and who had undergone pretreatment [ 18 F]FDG PET/CT and planning CT. Radiomic features were extracted using the PyRadiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Clinical, radiomic, and combined models were trained and tested using a neural network approach to predict regional and/or distant recurrence., Results: In the training (n = 273) and testing sets (n = 191 and n = 63), the clinical model achieved moderate performances to predict regional and/or distant recurrence with C-statistics from 0.53 to 0.59 (95% CI, 0.41, 0.67). The radiomic (original_firstorder_Entropy, original_gldm_LowGrayLevelEmphasis and original_glcm_DifferenceAverage) model achieved higher predictive ability in the training set and kept the same performance in the testing sets, with C-statistics from 0.70 to 0.78 (95% CI, 0.63, 0.88) while the combined model performs moderately well with C-statistics from 0.50 to 0.62 (95% CI, 0.37, 0.69)., Conclusion: Radiomic features extracted from pre-SBRT analog and digital [ 18 F]FDG PET/CT outperform clinical parameters in the prediction of regional and/or distant recurrence and to discuss an adjuvant systemic treatment in ES-NSCLC. Prospective validation of our models should now be carried out., (© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: To develop machine learning models to predict para-aortic lymph node (PALN) involvement in patients with locally advanced cervical cancer (LACC) before chemoradiotherapy (CRT) using 18 F-FDG PET/CT and MRI radiomics combined with clinical parameters., Methods: We retrospectively collected 178 patients (60% for training and 40% for testing) in 2 centers and 61 patients corresponding to 2 further external testing cohorts with LACC between 2010 to 2022 and who had undergone pretreatment analog or digital 18 F-FDG PET/CT, pelvic MRI and surgical PALN staging. Only primary tumor volumes were delineated. Radiomics features were extracted using the Radiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Different prediction models were trained using a neural network approach with either clinical, radiomics or combined models. They were then evaluated on the testing and external validation sets and compared., Results: In the training set (n = 102), the clinical model achieved a good prediction of the risk of PALN involvement with a C-statistic of 0.80 (95% CI 0.71, 0.87). However, it performed in the testing (n = 76) and external testing sets (n = 30 and n = 31) with C-statistics of only 0.57 to 0.67 (95% CI 0.36, 0.83). The ComBat-radiomic (GLDZM_HISDE_PET_FBN64 and Shape_maxDiameter2D3_PET_FBW0.25) and ComBat-combined (FIGO 2018 and same radiomics features) models achieved very high predictive ability in the training set and both models kept the same performance in the testing sets, with C-statistics from 0.88 to 0.96 (95% CI 0.76, 1.00) and 0.85 to 0.92 (95% CI 0.75, 0.99), respectively., Conclusions: Radiomic features extracted from pre-CRT analog and digital 18 F-FDG PET/CT outperform clinical parameters in the decision to perform a para-aortic node staging or an extended field irradiation to PALN. Prospective validation of our models should now be carried out., (© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: This study aimed to investigate the impact of several ComBat harmonization strategies, intra-tumoral sub-volume characterization, and automatic segmentations for progression-free survival (PFS) prediction through radiomics modeling for patients with head and neck cancer (HNC) in PET/CT images., Methods: The HECKTOR MICCAI 2021 challenge set containing PET/CT images and clinical data of 325 oropharynx HNC patients was exploited. A total of 346 IBSI-compliant radiomic features were extracted for each patient's primary tumor volume defined by the reference manual contours. Modeling relied on least absolute shrinkage Cox regression (Lasso-Cox) for feature selection (FS) and Cox proportional-hazards (CoxPH) models were built to predict PFS. Within this methodological framework, 8 different strategies for ComBat harmonization were compared, including before or after FS, in feature groups separately or all features directly, and with center or clustering-determined labels. Features extracted from tumor sub-volume clustering were also investigated for their prognostic additional value. Finally, 3 automatic segmentations (2 threshold-based and a 3D U-Net) were also compared. All results were evaluated with the concordance index (C-index)., Results: Radiomics features without harmonization, combined with clinical factors, led to models with C-index values of 0.69 in the testing set. The best version of ComBat harmonization, i.e., after FS, for feature groups separately and relying on clustering-determined labels, achieved a C-index of 0.71. The use of features extracted from tumor sub-volumes further improved the C-index to 0.72. Models that relied on the automatic segmentations yielded close but slightly lower prognostic performance (0.67-0.70) compared to reference contours., Conclusion: A standard radiomics pipeline allowed for prediction of PFS in a multicenter HNC cohort. Applying a specific strategy of ComBat harmonization improved the performance. The extraction of intra-tumoral sub-volume features and automatic segmentation could contribute to the improvement and automation of prognosis modeling, respectively., (© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: The purpose of this guideline is to provide comprehensive information on best practices for robust radiomics analyses for both hand-crafted and deep learning-based approaches., Methods: In a cooperative effort between the EANM and SNMMI, we agreed upon current best practices and recommendations for relevant aspects of radiomics analyses, including study design, quality assurance, data collection, impact of acquisition and reconstruction, detection and segmentation, feature standardization and implementation, as well as appropriate modelling schemes, model evaluation, and interpretation. We also offer an outlook for future perspectives., Conclusion: Radiomics is a very quickly evolving field of research. The present guideline focused on established findings as well as recommendations based on the state of the art. Though this guideline recognizes both hand-crafted and deep learning-based radiomics approaches, it primarily focuses on the former as this field is more mature. This guideline will be updated once more studies and results have contributed to improved consensus regarding the application of deep learning methods for radiomics. Although methodological recommendations in the present document are valid for most medical image modalities, we focus here on nuclear medicine, and specific recommendations when necessary are made for PET/CT, PET/MR, and quantitative SPECT., (© 2022. The Author(s).)

Purpose: To evaluate the performance of combined PET and multiparametric MRI (mpMRI) radiomics for the group-wise prediction of postsurgical Gleason scores (psGSs) in primary prostate cancer (PCa) patients., Methods: Patients with PCa, who underwent [ 68  Ga]Ga-PSMA-11 PET/MRI followed by radical prostatectomy, were included in this retrospective analysis (n = 101). Patients were grouped by psGS in three categories: ISUP grades 1-3, ISUP grade 4, and ISUP grade 5. mpMRI images included T1-weighted, T2-weighted, and apparent diffusion coefficient (ADC) map. Whole-prostate segmentations were performed on each modality, and image biomarker standardization initiative (IBSI)-compliant radiomic features were extracted. Nine support vector machine (SVM) models were trained: four single-modality radiomic models (PET, T1w, T2w, ADC); three PET + MRI double-modality models (PET + T1w, PET + T2w, PET + ADC), and two baseline models (one with patient data, one image-based) for comparison. A sixfold stratified cross-validation was performed, and balanced accuracies (bAcc) of the predictions of the best-performing models were reported and compared through Student's t-tests. The predictions of the best-performing model were compared against biopsy GS (bGS)., Results: All radiomic models outperformed the baseline models. The best-performing (mean ± stdv [%]) single-modality model was the ADC model (76 ± 6%), although not significantly better (p > 0.05) than other single-modality models (T1w: 72 ± 3%, T2w: 73 ± 2%; PET: 75 ± 5%). The overall best-performing model combined PET + ADC radiomics (82 ± 5%). It significantly outperformed most other double-modality (PET + T1w: 74 ± 5%, p = 0.026; PET + T2w: 71 ± 4%, p = 0.003) and single-modality models (PET: p = 0.042; T1w: p = 0.002; T2w: p = 0.003), except the ADC-only model (p = 0.138). In this initial cohort, the PET + ADC model outperformed bGS overall (82.5% vs 72.4%) in the prediction of psGS., Conclusion: All single- and double-modality models outperformed the baseline models, showing their potential in the prediction of GS, even with an unbalanced cohort. The best-performing model included PET + ADC radiomics, suggesting a complementary value of PSMA-PET and ADC radiomics., (© 2021. The Author(s).)

Purpose: To test the performances of native and tumour to liver ratio (TLR) radiomic features extracted from pre-treatment 2-[ 18 F] fluoro-2-deoxy-D-glucose ([ 18 F]FDG) PET/CT and combined with machine learning (ML) for predicting cancer recurrence in patients with locally advanced cervical cancer (LACC)., Methods: One 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., Results: After 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), F 1 -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: [ 18 F]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., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics., Methods: In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing)., Results: The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training., Conclusion: The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context., (© 2021. The Author(s).)

Techniques from the field of artificial intelligence, and more specifically machine (deep) learning methods, have been core components of most recent developments in the field of medical imaging. They are already being exploited or are being considered to tackle most tasks, including image reconstruction, processing (denoising, segmentation), analysis and predictive modelling. In this review we introduce and define these key concepts and discuss how the techniques from this field can be applied to nuclear medicine imaging applications with a particular focus on radio(geno)mics.

Purpose: The aim of this study was to validate previously developed radiomics models relying on just two radiomics features from 18 F-fluorodeoxyglucose positron emission tomography (PET) and magnetic resonance imaging (MRI) images for prediction of disease free survival (DFS) and locoregional control (LRC) in locally advanced cervical cancer (LACC)., Methods: Patients with LACC receiving chemoradiotherapy were enrolled in two French and one Canadian center. Pre-treatment imaging was performed for each patient. Multicentric harmonization of the two radiomics features was performed with the ComBat method. The models for DFS (using the feature from apparent diffusion coefficient (ADC) MRI) and LRC (adding one PET feature to the DFS model) were tuned using one of the French cohorts (n = 112) and applied to the other French (n = 50) and the Canadian (n = 28) external validation cohorts., Results: The DFS model reached an accuracy of 90% (95% CI [79-98%]) (sensitivity 92-93%, specificity 87-89%) in both the French and the Canadian cohorts. The LRC model reached an accuracy of 98% (95% CI [90-99%]) (sensitivity 86%, specificity 100%) in the French cohort and 96% (95% CI [80-99%]) (sensitivity 83%, specificity 100%) in the Canadian cohort. Accuracy was significantly lower without ComBat harmonization (82-85% and 71-86% for DFS and LRC, respectively). The best prediction using standard clinical variables was 56-60% only., Conclusions: The previously developed PET/MRI radiomics predictive models were successfully validated in two independent external cohorts. A proposed flowchart for improved management of patients based on these models should now be confirmed in future larger prospective studies.

Purpose: The aim of this study is to determine if radiomics features from 18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) and magnetic resonance imaging (MRI) images could contribute to prognoses in cervical cancer., Methods: One hundred and two patients (69 for training and 33 for testing) with locally advanced cervical cancer (LACC) receiving chemoradiotherapy (CRT) from 08/2010 to 12/2016 were enrolled in this study. 18 F-FDG PET/CT and MRI examination [T1, T2, T1C, diffusion-weighted imaging (DWI)] were performed for each patient before CRT. Primary tumor volumes were delineated with the fuzzy locally adaptive Bayesian algorithm in the PET images and with 3D Slicer™ in the MRI images. Radiomics features (intensity, shape, and texture) were extracted and their prognostic value was compared with clinical parameters for recurrence-free and locoregional control., Results: In the training cohort, median follow-up was 3.0 years (range, 0.43-6.56 years) and relapse occurred in 36% of patients. In univariate analysis, FIGO stage (I-II vs. III-IV) and metabolic response (complete vs. non-complete) were probably associated with outcome without reaching statistical significance, contrary to several radiomics features from both PET and MRI sequences. Multivariate analysis in training test identified Grey Level Non Uniformity GLRLM in PET and Entropy GLCM in ADC maps from DWI MRI as independent prognostic factors. These had significantly higher prognostic power than clinical parameters, as evaluated in the testing cohort with accuracy of 94% for predicting recurrence and 100% for predicting lack of loco-regional control (versus ~50-60% for clinical parameters)., Conclusions: In LACC treated with CRT, radiomics features such as EntropyGLCM and GLNUGLRLM from functional imaging DWI-MRI and PET, respectively, are independent predictors of recurrence and loco-regional control with significantly higher prognostic power than usual clinical parameters. Further research is warranted for their validation, which may justify more aggressive treatment in patients identified with high probability of recurrence.

Purpose: Sphericity has been proposed as a parameter for characterizing PET tumour volumes, with complementary prognostic value with respect to SUV and volume in both head and neck cancer and lung cancer. The objective of the present study was to investigate its dependency on tumour delineation and the resulting impact on its prognostic value., Methods: Five segmentation methods were considered: two thresholds (40% and 50% of SUV max ), ant colony optimization, fuzzy locally adaptive Bayesian (FLAB), and gradient-aided region-based active contour. The accuracy of each method in extracting sphericity was evaluated using a dataset of 176 simulated, phantom and clinical PET images of tumours with associated ground truth. The prognostic value of sphericity and its complementary value with respect to volume for each segmentation method was evaluated in a cohort of 87 patients with stage II/III lung cancer., Results: Volume and associated sphericity values were dependent on the segmentation method. The correlation between segmentation accuracy and sphericity error was moderate (|ρ| from 0.24 to 0.57). The accuracy in measuring sphericity was not dependent on volume (|ρ| < 0.4). In the patients with lung cancer, sphericity had prognostic value, although lower than that of volume, except for that derived using FLAB for which when combined with volume showed a small improvement over volume alone (hazard ratio 2.67, compared with 2.5). Substantial differences in patient prognosis stratification were observed depending on the segmentation method used., Conclusion: Tumour functional sphericity was found to be dependent on the segmentation method, although the accuracy in retrieving the true sphericity was not dependent on tumour volume. In addition, even accurate segmentation can lead to an inaccurate sphericity value, and vice versa. Sphericity had similar or lower prognostic value than volume alone in the patients with lung cancer, except when determined using the FLAB method for which there was a small improvement in stratification when the parameters were combined.

Purpose: The aim of this study was to investigate the prognostic value of baseline 18 F-FDG PET/CT textural analysis in locally-advanced rectal cancer (LARC)., Methods: Eighty-six patients with LARC underwent 18 F-FDG PET/CT before treatment. Maximum and mean standard uptake values (SUVmax and SUVmean), metabolic tumoral volume (MTV), total lesion glycolysis (TLG), histogram-intensity features, as well as 11 local and regional textural features, were evaluated. The relationships of clinical, pathological and PET-derived metabolic parameters with disease-specific survival (DSS), disease-free survival (DFS) and overall survival (OS) were assessed by Cox regression analysis. Logistic regression was used to predict the pathological response by the Dworak tumor regression grade (TRG) in the 66 patients treated with neoadjuvant chemoradiotherapy (nCRT)., Results: The median follow-up of patients was 41 months. Seventeen patients (19.7%) had recurrent disease and 18 (20.9 %) died, either due to cancer progression (n = 10) or from another cause while in complete remission (n = 8). DSS was 95% at 1 year, 93% at 2 years and 87% at 4 years. Weight loss, surgery and the texture parameter coarseness were significantly associated with DSS in multivariate analyses. DFS was 94 % at 1 year, 86 % at 2 years and 79 % at 4 years. From a multivariate standpoint, tumoral differentiation and the texture parameters homogeneity and coarseness were significantly associated with DFS. OS was 93% at 1 year, 87% at 2 years and 79% after 4 years. cT, surgery, SUVmean, dissimilarity and contrast from the neighborhood intensity-difference matrix (contrast NGTDM ) were significantly and independently associated with OS. Finally, RAS-mutational status (KRAS and NRAS mutations) and TLG were significant predictors of pathological response to nCRT (TRG 3-4)., Conclusion: Textural analysis of baseline 18 F-FDG PET/CT provides strong independent predictors of survival in patients with LARC, with better predictive power than intensity- and volume-based parameters. The utility of such features, especially coarseness, should be confirmed by larger clinical studies before considering their potential integration into decisional algorithms aimed at personalized medicine.

After seminal papers over the period 2009 - 2011, the use of texture analysis of PET/CT images for quantification of intratumour uptake heterogeneity has received increasing attention in the last 4 years. Results are difficult to compare due to the heterogeneity of studies and lack of standardization. There are also numerous challenges to address. In this review we provide critical insights into the recent development of texture analysis for quantifying the heterogeneity in PET/CT images, identify issues and challenges, and offer recommendations for the use of texture analysis in clinical research. Numerous potentially confounding issues have been identified, related to the complex workflow for the calculation of textural features, and the dependency of features on various factors such as acquisition, image reconstruction, preprocessing, functional volume segmentation, and methods of establishing and quantifying correspondences with genomic and clinical metrics of interest. A lack of understanding of what the features may represent in terms of the underlying pathophysiological processes and the variability of technical implementation practices makes comparing results in the literature challenging, if not impossible. Since progress as a field requires pooling results, there is an urgent need for standardization and recommendations/guidelines to enable the field to move forward. We provide a list of correct formulae for usual features and recommendations regarding implementation. Studies on larger cohorts with robust statistical analysis and machine learning approaches are promising directions to evaluate the potential of this approach., Competing Interests: P.E.K. has received a research grant from GE Healthcare and is cofounder of PET/X LLC. The other authors declare that they have no conflicts of interest.

Purpose: Quantification of tumour heterogeneity in PET images has recently gained interest, but has been shown to be dependent on image reconstruction. This study aimed to evaluate the impact of the EANM/EARL accreditation program on selected 18 F-FDG heterogeneity metrics., Methods: To carry out our study, we prospectively analysed 71 tumours in 60 biopsy-proven lung cancer patient acquisitions reconstructed with unfiltered point spread function (PSF) positron emission tomography (PET) images (optimised for diagnostic purposes), PSF-reconstructed images with a 7-mm Gaussian filter (PSF 7 ) chosen to meet European Association of Nuclear Medicine (EANM) 1.0 harmonising standards, and EANM Research Ltd. (EARL)-compliant ordered subset expectation maximisation (OSEM) images. Delineation was performed with fuzzy locally adaptive Bayesian (FLAB) algorithm on PSF images and reported on PSF 7 and OSEM ones, and with a 50 % standardised uptake values (SUV) max threshold (SUV max50% ) applied independently to each image. Robust and repeatable heterogeneity metrics including 1st-order [area under the curve of the cumulative histogram (CH AUC )], 2nd-order (entropy, correlation, and dissimilarity), and 3rd-order [high-intensity larger area emphasis (HILAE) and zone percentage (ZP)] textural features (TF) were statistically compared., Results: Volumes obtained with SUV max50% were significantly smaller than FLAB-derived ones, and were significantly smaller in PSF images compared to OSEM and PSF 7 images. PSF-reconstructed images showed significantly higher SUVmax and SUVmean values, as well as heterogeneity for CH AUC , dissimilarity, correlation, and HILAE, and a wider range of heterogeneity values than OSEM images for most of the metrics considered, especially when analysing larger tumours. Histological subtypes had no impact on TF distribution. No significant difference was observed between any of the considered metrics (SUV or heterogeneity features) that we extracted from OSEM and PSF 7 reconstructions. Furthermore, the distributions of TF for OSEM and PSF 7 reconstructions according to tumour volumes were similar for all ranges of volumes., Conclusion: PSF reconstruction with Gaussian filtering chosen to meet harmonising standards resulted in similar SUV values and heterogeneity information as compared to OSEM images, which validates its use within the harmonisation strategy context. However, unfiltered PSF-reconstructed images also showed higher heterogeneity according to some metrics, as well as a wider range of heterogeneity values than OSEM images for most of the metrics considered, especially when analysing larger tumours. This suggests that, whenever available, unfiltered PSF images should also be exploited to obtain the most discriminative quantitative heterogeneity features.

Purpose: Our goal was to develop a nomogram by exploiting intratumour heterogeneity on CT and PET images from routine (18)F-FDG PET/CT acquisitions to identify patients with the poorest prognosis., Methods: This retrospective study included 116 patients with NSCLC stage I, II or III and with staging (18)F-FDG PET/CT imaging. Primary tumour volumes were delineated using the FLAB algorithm and 3D Slicer™ on PET and CT images, respectively. PET and CT heterogeneities were quantified using texture analysis. The reproducibility of the CT features was assessed on a separate test-retest dataset. The stratification power of the PET/CT features was evaluated using the Kaplan-Meier method and the log-rank test. The best standard metric (functional volume) was combined with the least redundant and most prognostic PET/CT heterogeneity features to build the nomogram., Results: PET entropy and CT zone percentage had the highest complementary values with clinical stage and functional volume. The nomogram improved stratification amongst patients with stage II and III disease, allowing identification of patients with the poorest prognosis (clinical stage III, large tumour volume, high PET heterogeneity and low CT heterogeneity)., Conclusion: Intratumour heterogeneity quantified using textural features on both CT and PET images from routine staging (18)F-FDG PET/CT acquisitions can be used to create a nomogram with higher stratification power than staging alone.

Introduction: With (18)F-FDG PET/CT, tumor uptake intensity and heterogeneity have been associated with outcome in several cancers. This study aimed at investigating whether (18)F-FDG uptake intensity, volume or heterogeneity could predict the outcome in patients with non-small cell lung cancers (NSCLC) treated by stereotactic body radiation therapy (SBRT)., Methods: Sixty-three patients with NSCLC treated by SBRT underwent a (18)F-FDG PET/CT before treatment. Maximum and mean standard uptake value (SUVmax and SUVmean), metabolic tumoral volume (MTV), total lesion glycolysis (TLG), as well as 13 global, local and regional textural features were analysed. The predictive value of these parameters, along with clinical features, was assessed using univariate and multivariate analysis for overall survival (OS), disease-specific survival (DSS) and disease-free survival (DFS). Cutoff values were obtained using logistic regression analysis, and survivals were compared using Kaplan-Meier analysis., Results: The median follow-up period was 27.1 months for the entire cohort and 32.1 months for the surviving patients. At the end of the study, 25 patients had local and/or distant recurrence including 12 who died because of the cancer progression. None of the clinical variables was predictive of the outcome, except age, which was associated with DFS (HR 1.1, P = 0.002). None of the (18)F-FDG PET/CT or clinical parameters, except gender, were associated with OS. The univariate analysis showed that only dissimilarity (D) was associated with DSS (HR = 0.822, P = 0.037), and that several metabolic measurements were associated with DFS. In multivariate analysis, only dissimilarity was significantly associated with DSS (HR = 0.822, P = 0.037) and with DFS (HR = 0.834, P < 0.01)., Conclusion: The textural feature dissimilarity measured on the baseline (18)F-FDG PET/CT appears to be a strong independent predictor of the outcome in patients with NSCLC treated by SBRT. This may help selecting patients who may benefit from closer monitoring and therapeutic optimization.

Purpose: The aim of this retrospective study was to determine if some features of baseline (18)F-FDG PET images, including volume and heterogeneity, reflect clinical, histological or immunohistochemical characteristics in patients with stage II or III breast cancer (BC)., Methods: Included in the present retrospective analysis were 171 prospectively recruited patients with stage II/III BC treated consecutively at Saint-Louis hospital. Primary tumour volumes were semiautomatically delineated on pretreatment (18)F-FDG PET images. The parameters extracted included SUVmax, SUVmean, metabolically active tumour volume (MATV), total lesion glycolysis (TLG) and heterogeneity quantified using the area under the curve of the cumulative histogram and textural features. Associations between clinical/histopathological characteristics and (18)F-FDG PET features were assessed using one-way analysis of variance. Areas under the ROC curves (AUC) were used to quantify the discriminative power of the features significantly associated with clinical/histopathological characteristics., Results: T3 tumours (>5 cm) exhibited higher textural heterogeneity in (18)F-FDG uptake than T2 tumours (AUC <0.75), whereas there were no significant differences in SUVmax and SUVmean. Invasive ductal carcinoma showed higher SUVmax values than invasive lobular carcinoma (p = 0.008) but MATV, TLG and textural features were not discriminative. Grade 3 tumours had higher FDG uptake (AUC 0.779 for SUVmax and 0.694 for TLG), and exhibited slightly higher regional heterogeneity (AUC 0.624). Hormone receptor-negative tumours had higher SUV values than oestrogen receptor-positive (ER-positive) and progesterone receptor-positive tumours, while heterogeneity patterns showed only low-level variation according to hormone receptor expression. HER-2 status was not associated with any of the image features. Finally, SUVmax, SUVmean and TLG significantly differed among the three phenotype subgroups (HER2-positive, triple-negative and ER-positive/HER2-negative BCs), but MATV and heterogeneity metrics were not discriminative., Conclusion: SUV parameters, MATV and textural features showed limited correlations with clinical and histopathological features. The three main BC subgroups differed in terms of SUVs and TLG but not in terms of MATV and heterogeneity. None of the PET-derived metrics offered high discriminative power.

Purpose: Radiotherapy of head and neck cancer induces changes in tumour cell proliferation during treatment, which can be depicted by the PET tracer (18)F-fluorothymidine (FLT). In this study, three advanced semiautomatic PET segmentation methods for delineation of the proliferative tumour volume (PV) before and during (chemo)radiotherapy were compared and related to clinical outcome., Methods: The study group comprised 46 patients with 48 squamous cell carcinomas of the head and neck, treated with accelerated (chemo)radiotherapy, who underwent FLT PET/CT prior to treatment and in the 2nd and 4th week of therapy. Primary gross tumour volumes were visually delineated on CT images (GTV CT). PVs were visually determined on all PET scans (PV VIS). The following semiautomatic segmentation methods were applied to sequential PET scans: background-subtracted relative-threshold level (PV RTL), a gradient-based method using the watershed transform algorithm and hierarchical clustering analysis (PV W&C), and a fuzzy locally adaptive Bayesian algorithm (PV FLAB)., Results: Pretreatment PV VIS correlated best with PV FLAB and GTV CT. Correlations with PV RTL and PV W&C were weaker although statistically significant. During treatment, the PV VIS, PV W&C and PV FLAB significant decreased over time with the steepest decline over time for PV FLAB. Among these advanced segmentation methods, PV FLAB was the most robust in segmenting volumes in the third scan (67 % of tumours as compared to 40 % for PV W&C and 27 % for PV RTL). A decrease in PV FLAB above the median between the pretreatment scan and the scan obtained in the 4th week was associated with better disease-free survival (4 years 90 % versus 53 %)., Conclusion: In patients with head and neck cancer, FLAB proved to be the best performing method for segmentation of the PV on repeat FLT PET/CT scans during (chemo)radiotherapy. This may potentially facilitate radiation dose adaptation to changing PV.

Purpose: Intratumour uptake heterogeneity in PET quantified in terms of textural features for response to therapy has been investigated in several studies, including assessment of their robustness for reconstruction and physiological reproducibility. However, there has been no thorough assessment of the potential impact of preprocessing steps on the resulting quantification and its predictive value. The goal of this work was to assess the robustness of PET heterogeneity in textural features for delineation of functional volumes and partial volume correction (PVC)., Methods: This retrospective analysis included 50 patients with oesophageal cancer. PVC of each PET image was performed. Tumour volumes were determined using fixed and adaptive thresholding, and the fuzzy locally adaptive Bayesian algorithm, and heterogeneity was quantified using local and regional textural features. Differences in the absolute values of the image-derived parameters considered were assessed using Bland-Altman analysis. The impact on their predictive value for the identification of patient nonresponders was assessed by comparing areas under the receiver operating characteristic curves., Results: Heterogeneity parameters were more dependent on delineation than on PVC. The parameters most sensitive to delineation and PVC were regional ones (intensity variability and size zone variability), whereas local parameters such as entropy and homogeneity were the most robust. Despite the large differences in absolute values obtained from different delineation methods or after PVC, these differences did not necessarily translate into a significant impact on their predictive value., Conclusion: Parameters such as entropy, homogeneity, dissimilarity (for local heterogeneity characterization) and zone percentage (for regional characterization) should be preferred. This selection is based on a demonstrated high differentiation power in terms of predicting response, as well as a significant robustness with respect to the delineation method used and the partial volume effects.

Purpose: Several studies showed potential for monitoring response to systemic therapy in metastatic colorectal cancer patients with (18)F-fluorodeoxyglucose (FDG) positron emission tomography (PET). Before (18)F-FDG PET can be implemented for response evaluation the repeatability should be known. This study was performed to assess the magnitude of the changes in standardized uptake value (SUV), volume and total lesion glycolysis (TLG) in colorectal liver metastases and validate the biological basis of (18)F-FDG PET in colorectal liver metastases., Methods: Twenty patients scheduled for liver metastasectomy underwent two (18)F-FDG PET scans within 1 week. Bland-Altman analysis was performed to assess repeatability of SUV(max), SUV(mean), volume and TLG. Tumours were delineated using an adaptive threshold method (PET(SBR)) and a semiautomatic fuzzy locally adaptive Bayesian (FLAB) delineation method., Results: Coefficient of repeatability of SUV(max) and SUV(mean) were ∼39 and ∼31 %, respectively, independent of the delineation method used and image reconstruction parameters. However, repeatability was worse in recently treated patients. The FLAB delineation method improved the repeatability of the volume and TLG measurements compared to PET(SBR), from coefficients of repeatability of over 85 % to 45 % and 57 % for volume and TLG, respectively. Glucose transporter 1 (GLUT1) expression correlated to the SUV(mean). Vascularity (CD34 expression) and tumour hypoxia (carbonic anhydrase IX expression) did not correlate with (18)F-FDG PET parameters., Conclusion: In conclusion, repeatability of SUV(mean) and SUV(max) was mainly affected by preceding systemic therapy. The repeatability of tumour volume and TLG could be improved using more advanced and robust delineation approaches such as FLAB, which is recommended when (18)F-FDG PET is utilized for volume or TLG measurements. Improvement of repeatability of PET measurements, for instance by dynamic PET scanning protocols, is probably necessary to effectively use PET for early response monitoring.

Purpose: The objectives of this study were to investigate the predictive value of tumour measurements on 2-deoxy-2-[(18)F]fluoro-D-glucose ((18)F-FDG) positron emission tomography (PET) pretreatment scan regarding therapy response in oesophageal cancer and to evaluate the impact of tumour delineation strategies., Methods: Fifty patients with oesophageal cancer treated with concomitant radiochemotherapy between 2004 and 2008 were retrospectively considered and classified as complete, partial or non-responders (including stable and progressive disease) according to Response Evaluation Criteria in Solid Tumors (RECIST). The classification of partial and complete responders was confirmed by biopsy. Tumours were delineated on the (18)F-FDG pretreatment scan using an adaptive threshold and the automatic fuzzy locally adaptive Bayesian (FLAB) methodologies. Several parameters were then extracted: maximum and peak standardized uptake value (SUV), tumour longitudinal length (TL) and volume (TV), SUV(mean), and total lesion glycolysis (TLG = TV × SUV(mean)). The correlation between each parameter and response was investigated using Kruskal-Wallis tests, and receiver-operating characteristic methodology was used to assess performance of the parameters to differentiate patients., Results: Whereas commonly used parameters such as SUV measurements were not significant predictive factors of the response, parameters related to tumour functional spatial extent (TL, TV, TLG) allowed significant differentiation of all three groups of patients, independently of the delineation strategy, and could identify complete and non-responders with sensitivity above 75% and specificity above 85%. A systematic although not statistically significant trend was observed regarding the hierarchy of the delineation methodologies and the parameters considered, with slightly higher predictive value obtained with FLAB over adaptive thresholding, and TLG over TV and TL., Conclusion: TLG is a promising predictive factor of concomitant radiochemotherapy response with statistically higher predictive value than SUV measurements in advanced oesophageal cancer.

Purpose: (18)F-fluorodeoxyglucose (FDG) positron emission tomography (PET) image-derived parameters, such as standardized uptake value (SUV), functional tumour length (TL) and tumour volume (TV) or total lesion glycolysis (TLG), may be useful for determining prognosis in patients with oesophageal carcinoma. The objectives of this work were to investigate the prognostic value of these indices in oesophageal cancer patients undergoing combined chemoradiotherapy treatment and the impact of TV delineation strategies., Methods: A total of 45 patients were retrospectively analysed. Tumours were delineated on pretreatment (18)F-FDG scans using adaptive threshold and automatic (fuzzy locally adaptive Bayesian, FLAB) methodologies. The maximum standardized uptake value (SUV(max)), SUV(peak), SUV(mean), TL, TV and TLG were computed. The prognostic value of each parameter for overall survival was investigated using Kaplan-Meier and Cox regression models for univariate and multivariate analyses, respectively., Results: Large differences were observed between methodologies (from -140 to +50% for TV). SUV measurements were not significant prognostic factors for overall survival, whereas TV, TL and TLG were, irrespective of the segmentation strategy. After multivariate analysis including standard tumour staging, only TV (p < 0.002) and TL (p = 0.042) determined using FLAB were independent prognostic factors., Conclusion: Whereas no SUV measurement was a significant prognostic factor, TV, TL and TLG were significant prognostic factors for overall survival, irrespective of the delineation methodology. Only functional TV and TL derived using FLAB were independent prognostic factors, highlighting the need for accurate and robust PET tumour delineation tools for oncology applications.

Purpose: Current state-of-the-art algorithms for functional uptake volume segmentation in PET imaging consist of threshold-based approaches, whose parameters often require specific optimization for a given scanner and associated reconstruction algorithms. Different advanced image segmentation approaches previously proposed and extensively validated, such as among others fuzzy C-means (FCM) clustering, or fuzzy locally adaptive bayesian (FLAB) algorithm have the potential to improve the robustness of functional uptake volume measurements. The objective of this study was to investigate robustness and repeatability with respect to various scanner models, reconstruction algorithms and acquisition conditions., Methods and Materials: Robustness was evaluated using a series of IEC phantom acquisitions carried out on different PET/CT scanners (Philips Gemini and Gemini Time-of-Flight, Siemens Biograph and GE Discovery LS) with their associated reconstruction algorithms (RAMLA, TF MLEM, OSEM). A range of acquisition parameters (contrast, duration) and reconstruction parameters (voxel size) were considered for each scanner model, and the repeatability of each method was evaluated on simulated and clinical tumours and compared to manual delineation., Results: For all the scanner models, acquisition parameters and reconstruction algorithms considered, the FLAB algorithm demonstrated higher robustness in delineation of the spheres with low mean errors (10%) and variability (5%), with respect to threshold-based methodologies and FCM. The repeatability provided by all segmentation algorithms considered was very high with a negligible variability of <5% in comparison to that associated with manual delineation (5-35%)., Conclusion: The use of advanced image segmentation algorithms may not only allow high accuracy as previously demonstrated, but also provide a robust and repeatable tool to aid physicians as an initial guess in determining functional volumes in PET.

Purpose: Partial volume effects (PVEs) are consequences of the limited resolution of emission tomography. The aim of the present study was to compare two new voxel-wise PVE correction algorithms based on deconvolution and wavelet-based denoising., Materials and Methods: Deconvolution was performed using the Lucy-Richardson and the Van-Cittert algorithms. Both of these methods were tested using simulated and real FDG PET images. Wavelet-based denoising was incorporated into the process in order to eliminate the noise observed in classical deconvolution methods., Results: Both deconvolution approaches led to significant intensity recovery, but the Van-Cittert algorithm provided images of inferior qualitative appearance. Furthermore, this method added massive levels of noise, even with the associated use of wavelet-denoising. On the other hand, the Lucy-Richardson algorithm combined with the same denoising process gave the best compromise between intensity recovery, noise attenuation and qualitative aspect of the images., Conclusion: The appropriate combination of deconvolution and wavelet-based denoising is an efficient method for reducing PVEs in emission tomography.