Search

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking., (© RSNA, 2024 See also the editorial by Huisman and D'Antonoli in this issue.)

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).)

Purpose: To evaluate the potential benefit of using alternative reconstruction schemes of PET images for the prognostic value of radiomic features., Methods: Patients (n=91) with non-small cell lung cancer were prospectively included. All had a PET/CT examination before treatment. Three different PET images were reconstructed for each patient: the standard clinical protocol (i.e., 4×4×4 mm 3 voxels, 5mm Gaussian filter, denoted '200G5'), as well as using smaller voxels (i.e., 2×2×2 mm 3 with a larger reconstruction matrix, denoted 400G1) and/or 1mm post-reconstruction Gaussian filter, denoted 200G1). Metabolic volumes of the primary tumors were semi-automatically delineated on the PET images and IBSI compliant radiomic features (intensity, shape, textural) were extracted. First, the distributions of 200G1 and 400G1 features were compared to the reference clinical protocol (200G5) through Bland-Altman tests and the use of linear mixed models. Then, the prognostic value of the features from each of the 3 reconstructions was evaluated in a univariate analysis, through their stratification power in Kaplan-Meier curves through a threshold set at the median., Results: The 3 reconstructions led to different distributions for most of the features. The larger shifts and standard deviations of differences was observed between 200G5 and 400G1, which was also confirmed through linear mixed models. However, these relatively important differences in distributions did not translate into a significant impact on the stratification power of the features in terms of prognosis, although a trend in decreasing prognostic value could be observed (smaller number of features with HR above 2, overall lower HR values). Most prognostic features displayed high correlation with either volume or SUV max , although there was great variability of prognostic value for similar levels of correlation with these basic metrics., Conclusions: Using smaller voxels or less strong filtering options in the reconstruction settings of PET images compared to the standard clinical protocols led to different distributions of the resulting radiomic features. However, the hierarchy between patients according to these distributions remained overall the same and therefore the resulting stratification power of the radiomic features was not significantly altered. These results should be compared to those obtained in the context of other pathologies where radiomic features displaying lower correlation with volume or SUV max may have predictive value, such as in cervical cancer., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Carrying out large multicenter studies is one of the key goals to be achieved towards a faster transfer of the radiomics approach in the clinical setting. This requires large-scale radiomics data analysis, hence the need for integrating radiomic features extracted from images acquired in different centers. This is challenging as radiomic features exhibit variable sensitivity to differences in scanner model, acquisition protocols and reconstruction settings, which is similar to the so-called 'batch-effects' in genomics studies. In this review we discuss existing methods to perform data integration with the aid of reducing the unwanted variation associated with batch effects. We also discuss the future potential role of deep learning methods in providing solutions for addressing radiomic multicentre studies.

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

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.

Due to the recent developments of both hardware and software technologies, multimodality medical imaging techniques have been increasingly applied in clinical practice and research studies. Previously, the application of multimodality imaging in oncology has been mainly related to combining anatomical and functional imaging to improve diagnostic specificity and/or target definition, such as positron emission tomography/computed tomography (PET/CT) and single-photon emission CT (SPECT)/CT. More recently, the fusion of various images, such as multiparametric magnetic resonance imaging (MRI) sequences, different PET tracer images, PET/MRI, has become more prevalent, which has enabled more comprehensive characterization of the tumor phenotype. In order to take advantage of these valuable multimodal data for clinical decision making using radiomics, we present two ways to implement the multimodal image analysis, namely radiomic (handcrafted feature) based and deep learning (machine learned feature) based methods. Applying advanced machine (deep) learning algorithms across multimodality images have shown better results compared with single modality modeling for prognostic and/or prediction of clinical outcomes. This holds great potentials for providing more personalized treatment for patients and achieve better outcomes.

Our aim was to evaluate the impact of the accuracy of image segmentation techniques on establishing an overlap between pre-treatment and post-treatment functional tumour volumes in 18 FDG-PET/CT imaging. Simulated images and a clinical cohort were considered. Three different configurations (large, small or non-existent overlap) of a single simulated example was used to elucidate the behaviour of each approach. Fifty-four oesophageal and head and neck (H&N) cancer patients treated with radiochemotherapy with both pre- and post-treatment PET/CT scans were retrospectively analysed. Images were registered and volumes were determined using combinations of thresholds and the fuzzy locally adaptive Bayesian (FLAB) algorithm. Four overlap metrics were calculated. The simulations showed that thresholds lead to biased overlap estimation and that accurate metrics are obtained despite spatially inaccurate volumes. In the clinical dataset, only 17 patients exhibited residual uptake smaller than the pre-treatment volume. Overlaps obtained with FLAB were consistently moderate for esophageal and low for H&N cases across all metrics. Overlaps obtained using threshold combinations varied greatly depending on thresholds and metrics. In both cases overlaps were variable across patients. Our findings do not support optimisation of radiotherapy planning based on pre-treatment 18 FDG-PET/CT image definition of high-uptake sub-volumes. Combinations of thresholds may have led to overestimation of overlaps in previous studies.

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.

Introduction: Automatic functional volume segmentation in PET images is a challenge that has been addressed using a large array of methods. A major limitation for the field has been the lack of a benchmark dataset that would allow direct comparison of the results in the various publications. In the present work, we describe a comparison of recent methods on a large dataset following recommendations by the American Association of Physicists in Medicine (AAPM) task group (TG) 211, which was carried out within a MICCAI (Medical Image Computing and Computer Assisted Intervention) challenge., Materials and Methods: Organization and funding was provided by France Life Imaging (FLI). A dataset of 176 images combining simulated, phantom and clinical images was assembled. A website allowed the participants to register and download training data (n = 19). Challengers then submitted encapsulated pipelines on an online platform that autonomously ran the algorithms on the testing data (n = 157) and evaluated the results. The methods were ranked according to the arithmetic mean of sensitivity and positive predictive value., Results: Sixteen teams registered but only four provided manuscripts and pipeline(s) for a total of 10 methods. In addition, results using two thresholds and the Fuzzy Locally Adaptive Bayesian (FLAB) were generated. All competing methods except one performed with median accuracy above 0.8. The method with the highest score was the convolutional neural network-based segmentation, which significantly outperformed 9 out of 12 of the other methods, but not the improved K-Means, Gaussian Model Mixture and Fuzzy C-Means methods., Conclusion: The most rigorous comparative study of PET segmentation algorithms to date was carried out using a dataset that is the largest used in such studies so far. The hierarchy amongst the methods in terms of accuracy did not depend strongly on the subset of datasets or the metrics (or combination of metrics). All the methods submitted by the challengers except one demonstrated good performance with median accuracy scores above 0.8., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Purpose: The purpose of this study was to investigate the use of a probabilistic quad-tree graph (hidden Markov tree, HMT) to provide fast computation, robustness and an interpretational framework for multimodality image processing and to evaluate this framework for single gross tumor target (GTV) delineation from both positron emission tomography (PET) and computed tomography (CT) images., Methods: We exploited joint statistical dependencies between hidden states to handle the data stack using multi-observation, multi-resolution of HMT and Bayesian inference. This framework was applied to segmentation of lung tumors in PET/CT datasets taking into consideration simultaneously the CT and the PET image information. PET and CT images were considered using either the original voxels intensities, or after wavelet/contourlet enhancement. The Dice similarity coefficient (DSC), sensitivity (SE), positive predictive value (PPV) were used to assess the performance of the proposed approach on one simulated and 15 clinical PET/CT datasets of non-small cell lung cancer (NSCLC) cases. The surrogate of truth was a statistical consensus (obtained with the Simultaneous Truth and Performance Level Estimation algorithm) of three manual delineations performed by experts on fused PET/CT images. The proposed framework was applied to PET-only, CT-only and PET/CT datasets, and were compared to standard and improved fuzzy c-means (FCM) multimodal implementations., Results: A high agreement with the consensus of manual delineations was observed when using both PET and CT images. Contourlet-based HMT led to the best results with a DSC of 0.92 ± 0.11 compared to 0.89 ± 0.13 and 0.90 ± 0.12 for Intensity-based HMT and Wavelet-based HMT, respectively. Considering PET or CT only in the HMT led to much lower accuracy. Standard and improved FCM led to comparatively lower accuracy than HMT, even when considering multimodal implementations., Conclusions: We evaluated the accuracy of the proposed HMT-based framework for PET/CT image segmentation. The proposed method reached good accuracy, especially with pre-processing in the contourlet domain., (© 2017 American Association of Physicists in Medicine.)

Purpose: The aim of this paper is to define the requirements and describe the design and implementation of a standard benchmark tool for evaluation and validation of PET-auto-segmentation (PET-AS) algorithms. This work follows the recommendations of Task Group 211 (TG211) appointed by the American Association of Physicists in Medicine (AAPM)., Methods: The recommendations published in the AAPM TG211 report were used to derive a set of required features and to guide the design and structure of a benchmarking software tool. These items included the selection of appropriate representative data and reference contours obtained from established approaches and the description of available metrics. The benchmark was designed in a way that it could be extendable by inclusion of bespoke segmentation methods, while maintaining its main purpose of being a standard testing platform for newly developed PET-AS methods. An example of implementation of the proposed framework, named PETASset, was built. In this work, a selection of PET-AS methods representing common approaches to PET image segmentation was evaluated within PETASset for the purpose of testing and demonstrating the capabilities of the software as a benchmark platform., Results: A selection of clinical, physical, and simulated phantom data, including "best estimates" reference contours from macroscopic specimens, simulation template, and CT scans was built into the PETASset application database. Specific metrics such as Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), and Sensitivity (S), were included to allow the user to compare the results of any given PET-AS algorithm to the reference contours. In addition, a tool to generate structured reports on the evaluation of the performance of PET-AS algorithms against the reference contours was built. The variation of the metric agreement values with the reference contours across the PET-AS methods evaluated for demonstration were between 0.51 and 0.83, 0.44 and 0.86, and 0.61 and 1.00 for DSC, PPV, and the S metric, respectively. Examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state-of-the art., Conclusions: PETASset provides a platform that allows standardizing the evaluation and comparison of different PET-AS methods on a wide range of PET datasets. The developed platform will be available to users willing to evaluate their PET-AS methods and contribute with more evaluation datasets., (© 2017 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.)

Purpose: The purpose of this educational report is to provide an overview of the present state-of-the-art PET auto-segmentation (PET-AS) algorithms and their respective validation, with an emphasis on providing the user with help in understanding the challenges and pitfalls associated with selecting and implementing a PET-AS algorithm for a particular application., Approach: A brief description of the different types of PET-AS algorithms is provided using a classification based on method complexity and type. The advantages and the limitations of the current PET-AS algorithms are highlighted based on current publications and existing comparison studies. A review of the available image datasets and contour evaluation metrics in terms of their applicability for establishing a standardized evaluation of PET-AS algorithms is provided. The performance requirements for the algorithms and their dependence on the application, the radiotracer used and the evaluation criteria are described and discussed. Finally, a procedure for algorithm acceptance and implementation, as well as the complementary role of manual and auto-segmentation are addressed., Findings: A large number of PET-AS algorithms have been developed within the last 20 years. Many of the proposed algorithms are based on either fixed or adaptively selected thresholds. More recently, numerous papers have proposed the use of more advanced image analysis paradigms to perform semi-automated delineation of the PET images. However, the level of algorithm validation is variable and for most published algorithms is either insufficient or inconsistent which prevents recommending a single algorithm. This is compounded by the fact that realistic image configurations with low signal-to-noise ratios (SNR) and heterogeneous tracer distributions have rarely been used. Large variations in the evaluation methods used in the literature point to the need for a standardized evaluation protocol., Conclusions: Available comparison studies suggest that PET-AS algorithms relying on advanced image analysis paradigms provide generally more accurate segmentation than approaches based on PET activity thresholds, particularly for realistic configurations. However, this may not be the case for simple shape lesions in situations with a narrower range of parameters, where simpler methods may also perform well. Recent algorithms which employ some type of consensus or automatic selection between several PET-AS methods have potential to overcome the limitations of the individual methods when appropriately trained. In either case, accuracy evaluation is required for each different PET scanner and scanning and image reconstruction protocol. For the simpler, less robust approaches, adaptation to scanning conditions, tumor type, and tumor location by optimization of parameters is necessary. The results from the method evaluation stage can be used to estimate the contouring uncertainty. All PET-AS contours should be critically verified by a physician. A standard test, i.e., a benchmark dedicated to evaluating both existing and future PET-AS algorithms needs to be designed, to aid clinicians in evaluating and selecting PET-AS algorithms and to establish performance limits for their acceptance for clinical use. The initial steps toward designing and building such a standard are undertaken by the task group members., (© 2017 American Association of Physicists in Medicine.)

Purpose: Accurate tumor delineation in positron emission tomography (PET) images is crucial in oncology. Although recent methods achieved good results, there is still room for improvement regarding tumors with complex shapes, low signal-to-noise ratio, and high levels of uptake heterogeneity., Methods: The authors developed and evaluated an original clustering-based method called spatial positron emission quantification of tumor-Automatic Lp-norm estimation (SPEQTACLE), based on the fuzzy C-means (FCM) algorithm with a generalization exploiting a Hilbertian norm to more accurately account for the fuzzy and non-Gaussian distributions of PET images. An automatic and reproducible estimation scheme of the norm on an image-by-image basis was developed. Robustness was assessed by studying the consistency of results obtained on multiple acquisitions of the NEMA phantom on three different scanners with varying acquisition parameters. Accuracy was evaluated using classification errors (CEs) on simulated and clinical images. SPEQTACLE was compared to another FCM implementation, fuzzy local information C-means (FLICM) and fuzzy locally adaptive Bayesian (FLAB)., Results: SPEQTACLE demonstrated a level of robustness similar to FLAB (variability of 14% ± 9% vs 14% ± 7%, p = 0.15) and higher than FLICM (45% ± 18%, p < 0.0001), and improved accuracy with lower CE (14% ± 11%) over both FLICM (29% ± 29%) and FLAB (22% ± 20%) on simulated images. Improvement was significant for the more challenging cases with CE of 17% ± 11% for SPEQTACLE vs 28% ± 22% for FLAB (p = 0.009) and 40% ± 35% for FLICM (p < 0.0001). For the clinical cases, SPEQTACLE outperformed FLAB and FLICM (15% ± 6% vs 37% ± 14% and 30% ± 17%, p < 0.004)., Conclusions: SPEQTACLE benefitted from the fully automatic estimation of the norm on a case-by-case basis. This promising approach will be extended to multimodal images and multiclass estimation in future developments.

Unlabelled: The goal of this study was to compare visual assessment of intratumor (18)F-FDG PET uptake distribution with a textural-features (TF) automated quantification and to establish their respective prognostic value in non-small cell lung cancer (NSCLC)., Methods: The study retrospectively included 102 consecutive patients. Only primary tumors were considered. Intratumor heterogeneity was visually scored (3-level scale [Hvisu]) by 2 nuclear medicine physicians. Tumor volumes were automatically delineated, and heterogeneity was quantified with TF. Mean and maximum standardized uptake value were also included. Visual interobserver agreement and correlations with quantitative assessment were evaluated using the κ test and Spearman rank (ρ) coefficient, respectively. Association with overall survival and recurrence-free survival was investigated using the Kaplan-Meier method and Cox regression models., Results: Moderate correlations (0.4 < ρ < 0.6) between TF parameters and Hvisu were observed. Interobserver agreement for Hvisu was moderate (κ = 0.64, discrepancies in 27% of the cases). High standardized uptake value, large metabolic volumes, and high heterogeneity according to TF were associated with poorer overall survival and recurrence-free survival and remained an independent prognostic factor of overall survival with respect to clinical variables., Conclusion: Quantification of (18)F-FDG uptake heterogeneity in NSCLC through TF was correlated with visual assessment by experts. However, TF also constitutes an objective heterogeneity quantification, with reduced interobserver variability, and independent prognostic value potentially useful for patient stratification and management., (© 2014 by the Society of Nuclear Medicine and Molecular Imaging, Inc.)

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.

The interest of PET complementary information for the delineation of the target volume in radiotherapy of lung cancer is increasing. However, respiratory motion requires the determination of a functional internal target volume (ITV) on PET images for which several strategies have been proposed. The purpose of this study was the comparison of these strategies for taking into account respiratory motion and deriving the ITV: (1) adding fixed margins to the volume defined on a single binned image, (2) segmenting a motion averaged image and (3) considering the union of volumes delineated on binned frames. For this third strategy, binned frames were either non-corrected for motion, or corrected using two different methods: elastic registration or super resolution. The strategies' performances were assessed on realistic simulated datasets combining the NCAT phantom with a PET Philips GEMINI scanner model in GATE, and containing various configurations of tumor to background contrast, with both regular and irregular respiratory motion (with a range of motion amplitudes). The obtained ITVs' sensitivity (SE) and positive predictive value (PVE) with respect to the known true ITV were significantly higher (from 0.8 to 0.95) than all other techniques when using binned frames corrected for motion, independently of motion regularity, amplitude, or tumor to background contrast. Although the absolute difference was small and not always significant, images corrected using super resolution led to systematically better results than using elastic registration. The worst results were obtained when using the motion averaged image for SE (around 0.5-0.6) and using the margins added to a single frame for PPV (0.6-0.7), respectively. The best strategy to account for breathing motion for tumor ITV delineation in radiotherapy planning is to rely on the use of the union of volumes delineated on super resolution-corrected binned images.

Over the past few years several automatic and semi-automatic PET segmentation methods for target volume definition in radiotherapy have been proposed. The objective of this study is to compare different methods in terms of dosimetry. For such a comparison, a gold standard is needed. For this purpose, realistic GATE-simulated PET images were used. Three lung cases and three H&N cases were designed with various shapes, contrasts and heterogeneities. Four different segmentation approaches were compared: fixed and adaptive thresholds, a fuzzy C-mean and the fuzzy locally adaptive Bayesian method. For each of these target volumes, an IMRT treatment plan was defined. The different algorithms and resulting plans were compared in terms of segmentation errors and ground-truth volume coverage using different metrics (V(95), D(95), homogeneity index and conformity index). The major differences between the threshold-based methods and automatic methods occurred in the most heterogeneous cases. Within the two groups, the major differences occurred for low contrast cases. For homogeneous cases, equivalent ground-truth volume coverage was observed for all methods but for more heterogeneous cases, significantly lower coverage was observed for threshold-based methods. Our study demonstrates that significant dosimetry errors can be avoided by using more advanced image-segmentation methods.

In clinical oncology, positron emission tomography (PET) imaging can be used to assess therapeutic response by quantifying the evolution of semi-quantitative values such as standardized uptake value, early during treatment or after treatment. Current guidelines do not include metabolically active tumor volume (MATV) measurements and derived parameters such as total lesion glycolysis (TLG) to characterize the response to the treatment. To achieve automatic MATV variation estimation during treatment, we propose an approach based on the change detection principle using the recent paradoxical theory, which models imprecision, uncertainty, and conflict between sources. It was applied here simultaneously to pre- and post-treatment PET scans. The proposed method was applied to both simulated and clinical datasets, and its performance was compared to adaptive thresholding applied separately on pre- and post-treatment PET scans. On simulated datasets, the adaptive threshold was associated with significantly higher classification errors than the developed approach. On clinical datasets, the proposed method led to results more consistent with the known partial responder status of these patients. The method requires accurate rigid registration of both scans which can be obtained only in specific body regions and does not explicitly model uptake heterogeneity. In further investigations, the change detection of intra-MATV tracer uptake heterogeneity will be developed by incorporating textural features into the proposed approach.

Unlabelled: (18)F-FDG PET measurement of standardized uptake value (SUV) is increasingly used for monitoring therapy response and predicting outcome. Alternative parameters computed through textural analysis were recently proposed to quantify the heterogeneity of tracer uptake by tumors as a significant predictor of response. The primary objective of this study was to evaluate the reproducibility of these heterogeneity measurements., Methods: Double baseline (18)F-FDG PET scans were acquired within 4 d of each other for 16 patients before any treatment was considered. A Bland-Altman analysis was performed on 8 parameters based on histogram measurements and 17 parameters based on textural heterogeneity features after discretization with values between 8 and 128., Results: The reproducibility of maximum and mean SUV was similar to that in previously reported studies, with a mean percentage difference of 4.7% ± 19.5% and 5.5% ± 21.2%, respectively. By comparison, better reproducibility was measured for some textural features describing local heterogeneity of tracer uptake, such as entropy and homogeneity, with a mean percentage difference of -2% ± 5.4% and 1.8% ± 11.5%, respectively. Several regional heterogeneity parameters such as variability in the intensity and size of regions of homogeneous activity distribution had reproducibility similar to that of SUV measurements, with 95% confidence intervals of -22.5% to 3.1% and -1.1% to 23.5%, respectively. These parameters were largely insensitive to the discretization range., Conclusion: Several parameters derived from textural analysis describing heterogeneity of tracer uptake by tumors on local and regional scales had reproducibility similar to or better than that of simple SUV measurements. These reproducibility results suggest that these (18)F-FDG PET-derived parameters, which have already been shown to have predictive and prognostic value in certain cancer models, may be used to monitor therapy response and predict patient outcome.

Unlabelled: The objective of this study was to investigate the clinical impact of partial-volume effect (PVE) correction on the predictive and prognostic value of metabolically active tumor volume (MATV) measurements on (18)F-FDG PET baseline scans for therapy response and overall survival in esophageal cancer patients., Methods: Fifty patients with esophageal cancer treated with concomitant radiochemotherapy between 2004 and 2008 were retrospectively considered. PET baseline scans were corrected for PVE with iterative deconvolution incorporating wavelet denoising. MATV delineation on both original and corrected images was performed using the automatic fuzzy locally adaptive Bayesian methodology. Several parameters were extracted considering the original and corrected images: maximum and peak standardized uptake value (SUV), mean SUV, MATV, and total lesion glycolysis (TLG) (TLG = MATV × mean SUV). The predictive value of each parameter with or without correction was investigated using Kruskal-Wallis tests, and the prognostic value was determined with Kaplan-Meier curves., Results: Whereas PVE correction had a significant quantitative impact on the absolute values of the investigated parameters, their clinical value within the clinical context of interest was not significantly modified-a result that was observed for both overall survival and response to therapy. The hierarchy between parameters was the same before and after correction. SUV measurements (maximum, peak, and mean) had nonsignificant (P > 0.05) predictive or prognostic value, whereas functional tumor-related measurements (MATV and TLG) were significant (P < 0.002) predictors of response and independent prognostic factors., Conclusion: PVE correction does not improve the predictive and prognostic value of baseline PET image-derived parameters in esophageal cancer patients.

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.

Accurate volume estimation in positron emission tomography (PET) is crucial for different oncology applications. The objective of our study was to develop a new fuzzy locally adaptive Bayesian (FLAB) segmentation for automatic lesion volume delineation. FLAB was compared with a threshold approach as well as the previously proposed fuzzy hidden Markov chains (FHMC) and the fuzzy C-Means (FCM) algorithms. The performance of the algorithms was assessed on acquired datasets of the IEC phantom, covering a range of spherical lesion sizes (10-37 mm), contrast ratios (4:1 and 8:1), noise levels (1, 2, and 5 min acquisitions), and voxel sizes (8 and 64 mm(3)). In addition, the performance of the FLAB model was assessed on realistic nonuniform and nonspherical volumes simulated from patient lesions. Results show that FLAB performs better than the other methodologies, particularly for smaller objects. The volume error was 5%-15% for the different sphere sizes (down to 13 mm), contrast and image qualities considered, with a high reproducibility (variation < 4%). By comparison, the thresholding results were greatly dependent on image contrast and noise, whereas FCM results were less dependent on noise but consistently failed to segment lesions < 2 cm. In addition, FLAB performed consistently better for lesions < 2 cm in comparison to the FHMC algorithm. Finally the FLAB model provided errors less than 10% for nonspherical lesions with inhomogeneous activity distributions. Future developments will concentrate on an extension of FLAB in order to allow the segmentation of separate activity distribution regions within the same functional volume as well as a robustness study with respect to different scanners and reconstruction algorithms.

Partial volume effects (PVEs) are consequences of the limited spatial resolution in emission tomography. They lead to a loss of signal in tissues of size similar to the point spread function and induce activity spillover between regions. Although PVE can be corrected for by using algorithms that provide the correct radioactivity concentration in a series of regions of interest (ROIs), so far little attention has been given to the possibility of creating improved images as a result of PVE correction. Potential advantages of PVE-corrected images include the ability to accurately delineate functional volumes as well as improving tumour-to-background ratio, resulting in an associated improvement in the analysis of response to therapy studies and diagnostic examinations, respectively. The objective of our study was therefore to develop a methodology for PVE correction not only to enable the accurate recuperation of activity concentrations, but also to generate PVE-corrected images. In the multiresolution analysis that we define here, details of a high-resolution image H (MRI or CT) are extracted, transformed and integrated in a low-resolution image L (PET or SPECT). A discrete wavelet transform of both H and L images is performed by using the "à trous" algorithm, which allows the spatial frequencies (details, edges, textures) to be obtained easily at a level of resolution common to H and L. A model is then inferred to build the lacking details of L from the high-frequency details in H. The process was successfully tested on synthetic and simulated data, proving the ability to obtain accurately corrected images. Quantitative PVE correction was found to be comparable with a method considered as a reference but limited to ROI analyses. Visual improvement and quantitative correction were also obtained in two examples of clinical images, the first using a combined PET/CT scanner with a lymphoma patient and the second using a FDG brain PET and corresponding T1-weighted MRI in an epileptic patient.