Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge.

By focusing on metabolic and morphological tissue properties respectively, FluoroDeoxyGlucose (FDG)-Positron Emission Tomography (PET) and Computed Tomography (CT) modalities include complementary and synergistic information for cancerous lesion delineation and characterization (e.g. for outcome prediction), in addition to usual clinical variables. This is especially true in Head and Neck Cancer (HNC). The goal of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge was to develop and compare modern image analysis methods to best extract and leverage this information automatically. We present here the post-analysis of HECKTOR 2nd edition, at the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2021. The scope of the challenge was substantially expanded compared to the first edition, by providing a larger population (adding patients from a new clinical center) and proposing an additional task to the challengers, namely the prediction of Progression-Free Survival (PFS). To this end, the participants were given access to a training set of 224 cases from 5 different centers, each with a pre-treatment FDG-PET/CT scan and clinical variables. Their methods were subsequently evaluated on a held-out test set of 101 cases from two centers. For the segmentation task (Task 1), the ranking was based on a Borda counting of their ranks according to two metrics: mean Dice Similarity Coefficient (DSC) and median Hausdorff Distance at 95th percentile (HD95). For the PFS prediction task, challengers could use the tumor contours provided by experts (Task 3) or rely on their own (Task 2). The ranking was obtained according to the Concordance index (C-index) calculated on the predicted risk scores. A total of 103 teams registered for the challenge, for a total of 448 submissions and 29 papers. The best method in the segmentation task obtained an average DSC of 0.759, and the best predictions of PFS obtained a C-index of 0.717 (without relying on the provided contours) and 0.698 (using the expert contours). An interesting finding was that best PFS predictions were reached by relying on DL approaches (with or without explicit tumor segmentation, 4 out of the 5 best ranked) compared to standard radiomics methods using handcrafted features extracted from delineated tumors, and by exploiting alternative tumor contours (automated and/or larger volumes encompassing surrounding tissues) rather than relying on the expert contours. This second edition of the challenge confirmed the promising performance of fully automated primary tumor delineation in PET/CT images of HNC patients, although there is still a margin for improvement in some difficult cases. For the first time, the prediction of outcome was also addressed and the best methods reached relatively good performance (C-index above 0.7). Both results constitute another step forward toward large-scale outcome prediction studies in HNC.

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT.

This paper presents an overview of the third edition of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge, organized as a satellite event of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022. The challenge comprises two tasks related to the automatic analysis of FDG-PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the fully automatic segmentation of H&N primary Gross Tumor Volume (GTVp) and metastatic lymph nodes (GTVn) from FDG-PET/CT images. Task 2 is the fully automatic prediction of Recurrence-Free Survival (RFS) from the same FDG-PET/CT and clinical data. The data were collected from nine centers for a total of 883 cases consisting of FDG-PET/CT images and clinical information, split into 524 training and 359 test cases. The best methods obtained an aggregated Dice Similarity Coefficient (DSCagg) of 0.788 in Task 1, and a Concordance index (C-index) of 0.682 in Task 2.

Radiomics: Data Are Also Images.

The aim of this review is to provide readers with an update on the state of the art, pitfalls, solutions for those pitfalls, future perspectives, and challenges in the quickly evolving field of radiomics in nuclear medicine imaging and associated oncology applications. The main pitfalls were identified in study design, data acquisition, segmentation, feature calculation, and modeling; however, in most cases, potential solutions are available and existing recommendations should be followed to improve the overall quality and reproducibility of published radiomics studies. The techniques from the field of deep learning have some potential to provide solutions, especially in terms of automation. Some important challenges remain to be addressed but, overall, striking advances have been made in the field in the last 5 y.

Tumour functional sphericity from PET images: prognostic value in NSCLC and impact of delineation method.

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 SUVmax), 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.

Characterization of PET/CT images using texture analysis: the past, the present any future?

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.

Do clinical, histological or immunohistochemical primary tumour characteristics translate into different (18)F-FDG PET/CT volumetric and heterogeneity features in stage II/III breast cancer?

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.

18F-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort.

UNLABELLED: Intratumoral uptake heterogeneity in (18)F-FDG PET has been associated with patient treatment outcomes in several cancer types. Textural feature analysis is a promising method for its quantification. An open issue associated with textural features for the quantification of intratumoral heterogeneity concerns its added contribution and dependence on the metabolically active tumor volume (MATV), which has already been shown to be a significant predictive and prognostic parameter. Our objective was to address this question using a larger cohort of patients covering different cancer types. METHODS: A single database of 555 pretreatment (18)F-FDG PET images (breast, cervix, esophageal, head and neck, and lung cancer tumors) was assembled. Four robust and reproducible textural feature-derived parameters were considered. The issues associated with the calculation of textural features using co-occurrence matrices (such as the quantization and spatial directionality relationships) were also investigated. The relationship between these features and MATV, as well as among the features themselves, was investigated using Spearman rank coefficients for different volume ranges. The complementary prognostic value of MATV and textural features was assessed through multivariate Cox analysis in the esophageal and non-small cell lung cancer (NSCLC) cohorts. RESULTS: A large range of MATVs was included in the population considered (3-415 cm(3); mean, 35; median, 19; SD, 50). The correlation between MATV and textural features varied greatly depending on the MATVs, with reduced correlation for increasing volumes. These findings were reproducible across the different cancer types. The quantization and calculation methods both had an impact on the correlation. Volume and heterogeneity were independent prognostic factors (P = 0.0053 and 0.0093, respectively) along with stage (P = 0.002) in non-small cell lung cancer, but in the esophageal tumors, volume and heterogeneity had less complementary value because of smaller overall volumes. CONCLUSION: Our results suggest that heterogeneity quantification and volume may provide valuable complementary information for volumes above 10 cm(3), although the complementary information increases substantially with larger volumes.

Visual versus quantitative assessment of intratumor 18F-FDG PET uptake heterogeneity: prognostic value in non-small cell lung cancer.

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.

Correlation of intra-tumor 18F-FDG uptake heterogeneity indices with perfusion CT derived parameters in colorectal cancer.

METHODS: Thirty patients with proven colorectal cancer prospectively underwent integrated 18F-FDG PET/DCE-CT to assess the metabolic-flow phenotype. Both CT blood flow parametric maps and PET images were analyzed. Correlations between PET heterogeneity and perfusion CT were assessed by Spearman's rank correlation analysis. RESULTS: Blood flow visualization provided by DCE-CT images was significantly correlated with 18F-FDG PET metabolically active tumor volume as well as with uptake heterogeneity for patients with stage III/IV tumors (|ρ|:0.66 to 0.78; p-value<0.02). CONCLUSION: The positive correlation found with tumor blood flow indicates that intra-tumor heterogeneity of 18F-FDG PET accumulation reflects to some extent tracer distribution and consequently indicates that 18F-FDG PET intra-tumor heterogeneity may be associated with physiological processes such as tumor vascularization.

Generation of 4-dimensional CT images based on 4-dimensional PET-derived motion fields.

UNLABELLED: Respiratory motion can potentially reduce accuracy in anatomic and functional image fusion from multimodality systems. It can blur the uptake of small lesions and lead to significant activity underestimation. Solutions presented to date include respiration-synchronized anatomic and functional acquisitions. To increase the signal-to-noise ratio of the synchronized PET images, methods using nonrigid transformations during the reconstruction process have been proposed. In most of these methods, 4-dimensional (4D) CT images were used to derive the required deformation matrices. However, variations between acquired 4D PET and corresponding CT image series due to differences in respiratory conditions during PET and CT acquisitions have been reported. In addition, the radiation dose burden resulting from a 4D CT acquisition may not be justifiable for every patient. METHODS: In this paper, we present a method for the generation of dynamic CT images from the combination of one reference CT image and deformation matrices obtained from the elastic registration of 4D PET images not corrected for attenuation. On the one hand, our approach eliminates the need for the acquisition of dynamic CT. On the other hand, it also ensures a good match between CT and PET images, allowing accurate attenuation correction to be performed for respiration-synchronized PET acquisitions. RESULTS: The proposed method was first validated on Monte Carlo-simulated datasets, and then on patient datasets (n = 4) by comparing generated 4D CT images with the corresponding acquired original CT images. Different levels of PET image statistical quality were considered in order to investigate the impact of image noise in the derivation of the 4D CT series. CONCLUSION: Our results suggest that clinically relevant PET acquisition times can be used for the implementation of such an approach, making this an even more attractive solution considering the absence of the extra dose given by a standard 4D CT acquisition. Finally, this approach may be applicable to other multimodality devices such as PET/MR.

Image change detection using paradoxical theory for patient follow-up quantitation and therapy assessment.

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.

Reproducibility of tumor uptake heterogeneity characterization through textural feature analysis in 18F-FDG PET.

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.

Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer.

UNLABELLED: (18)F-FDG PET is often used in clinical routine for diagnosis, staging, and response to therapy assessment or prediction. The standardized uptake value (SUV) in the primary or regional area is the most common quantitative measurement derived from PET images used for those purposes. The aim of this study was to propose and evaluate new parameters obtained by textural analysis of baseline PET scans for the prediction of therapy response in esophageal cancer. METHODS: Forty-one patients with newly diagnosed esophageal cancer treated with combined radiochemotherapy were included in this study. All patients underwent pretreatment whole-body (18)F-FDG PET. Patients were treated with radiotherapy and alkylatinlike agents (5-fluorouracil-cisplatin or 5-fluorouracil-carboplatin). Patients were classified as nonresponders (progressive or stable disease), partial responders, or complete responders according to the Response Evaluation Criteria in Solid Tumors. Different image-derived indices obtained from the pretreatment PET tumor images were considered. These included usual indices such as maximum SUV, peak SUV, and mean SUV and a total of 38 features (such as entropy, size, and magnitude of local and global heterogeneous and homogeneous tumor regions) extracted from the 5 different textures considered. The capacity of each parameter to classify patients with respect to response to therapy was assessed using the Kruskal-Wallis test (P < 0.05). Specificity and sensitivity (including 95% confidence intervals) for each of the studied parameters were derived using receiver-operating-characteristic curves. RESULTS: Relationships between pairs of voxels, characterizing local tumor metabolic nonuniformities, were able to significantly differentiate all 3 patient groups (P < 0.0006). Regional measures of tumor characteristics, such as size of nonuniform metabolic regions and corresponding intensity nonuniformities within these regions, were also significant factors for prediction of response to therapy (P = 0.0002). Receiver-operating-characteristic curve analysis showed that tumor textural analysis can provide nonresponder, partial-responder, and complete-responder patient identification with higher sensitivity (76%-92%) than any SUV measurement. CONCLUSION: Textural features of tumor metabolic distribution extracted from baseline (18)F-FDG PET images allow for the best stratification of esophageal carcinoma patients in the context of therapy-response prediction.