Dataset Information

Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images.

ABSTRACT: Quantitative imaging biomarkers (QIBs) provide medical image-derived intensity, texture, shape, and size features that may help characterize cancerous tumors and predict clinical outcomes. Successful clinical translation of QIBs depends on the robustness of their measurements. Biomarkers derived from positron emission tomography images are prone to measurement errors owing to differences in image processing factors such as the tumor segmentation method used to define volumes of interest over which to calculate QIBs. We illustrate a new Bayesian statistical approach to characterize the robustness of QIBs to different processing factors. Study data consist of 22 QIBs measured on 47 head and neck tumors in 10 positron emission tomography/computed tomography scans segmented manually and with semiautomated methods used by 7 institutional members of the NCI Quantitative Imaging Network. QIB performance is estimated and compared across institutions with respect to measurement errors and power to recover statistical associations with clinical outcomes. Analysis findings summarize the performance impact of different segmentation methods used by Quantitative Imaging Network members. Robustness of some advanced biomarkers was found to be similar to conventional markers, such as maximum standardized uptake value. Such similarities support current pursuits to better characterize disease and predict outcomes by developing QIBs that use more imaging information and are robust to different processing factors. Nevertheless, to ensure reproducibility of QIB measurements and measures of association with clinical outcomes, errors owing to segmentation methods need to be reduced.

SUBMITTER: Smith BJ

PROVIDER: S-EPMC7289247 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images.

Smith Brian J BJ Buatti John M JM Bauer Christian C Ulrich Ethan J EJ Ahmadvand Payam P Budzevich Mikalai M MM Gillies Robert J RJ Goldgof Dmitry D Grkovski Milan M Hamarneh Ghassan G Kinahan Paul E PE Muzi John P JP Muzi Mark M Laymon Charles M CM Mountz James M JM Nehmeh Sadek S Oborski Matthew J MJ Zhao Binsheng B Sunderland John J JJ Beichel Reinhard R RR

Tomography (Ann Arbor, Mich.) 20200601 2

Quantitative imaging biomarkers (QIBs) provide medical image-derived intensity, texture, shape, and size features that may help characterize cancerous tumors and predict clinical outcomes. Successful clinical translation of QIBs depends on the robustness of their measurements. Biomarkers derived from positron emission tomography images are prone to measurement errors owing to differences in image processing factors such as the tumor segmentation method used to define volumes of interest over whi ...[more]

PMID: 32548282

Similar Datasets

Project description:BACKGROUND:Radiomics is aimed at image-based tumor phenotyping, enabling application within clinical-decision-support-systems to improve diagnostic accuracy and allow for personalized treatment. The purpose was to identify predictive 18-fluor-fluoro-2-deoxyglucose (18F-FDG) positron-emission tomography (PET) radiomic features to predict recurrence, distant metastasis, and overall survival in patients with head and neck squamous cell carcinoma treated with chemoradiotherapy. METHODS:Between 2012 and 2018, 103 retrospectively (training cohort) and 71 consecutively included patients (validation cohort) underwent 18F-FDG-PET/CT imaging. The 434 extracted radiomic features were subjected, after redundancy filtering, to a projection resulting in outcome-independent meta-features (factors). Correlations between clinical, first-order 18F-FDG-PET parameters (e.g., SUVmean), and factors were assessed. Factors were combined with 18F-FDG-PET and clinical parameters in a multivariable survival regression and validated. A clinically applicable risk-stratification was constructed for patients' outcome. RESULTS:Based on 124 retained radiomic features from 103 patients, 8 factors were constructed. Recurrence prediction was significantly most accurate by combining HPV-status, SUVmean, SUVpeak, factor 3 (histogram gradient and long-run-low-grey-level-emphasis), factor 4 (volume-difference, coarseness, and grey-level-non-uniformity), and factor 6 (histogram variation coefficient) (CI = 0.645). Distant metastasis prediction was most accurate assessing metabolic-active tumor volume (MATV)(CI = 0.627). Overall survival prediction was most accurate using HPV-status, SUVmean, SUVmax, factor 1 (least-axis-length, non-uniformity, high-dependence-of-high grey-levels), and factor 5 (aspherity, major-axis-length, inversed-compactness and, inversed-flatness) (CI = 0.764). CONCLUSIONS:Combining HPV-status, first-order 18F-FDG-PET parameters, and complementary radiomic factors was most accurate for time-to-event prediction. Predictive phenotype-specific tumor characteristics and interactions might be captured and retained using radiomic factors, which allows for personalized risk stratification and optimizing personalized cancer care. TRIAL REGISTRATION:Trial NL3946 (NTR4111), local ethics commission reference: Prediction 2013.191 and 2016.498. Registered 7 August 2013, https://www.trialregister.nl/trial/3946.

Project description:PurposeRadiomics utilizes a large number of image-derived features for quantifying tumor characteristics that can in turn be correlated with response and prognosis. Unfortunately, extraction and analysis of such image-based features is subject to measurement variability and bias. The challenge for radiomics is particularly acute in Positron Emission Tomography (PET) where limited resolution, a high noise component related to the limited stochastic nature of the raw data, and the wide variety of reconstruction options confound quantitative feature metrics. Extracted feature quality is also affected by tumor segmentation methods used to define regions over which to calculate features, making it challenging to produce consistent radiomics analysis results across multiple institutions that use different segmentation algorithms in their PET image analysis. Understanding each element contributing to these inconsistencies in quantitative image feature and metric generation is paramount for ultimate utilization of these methods in multi-institutional trials and clinical oncology decision making.MethodsTo assess segmentation quality and consistency at the multi-institutional level, we conducted a study of seven institutional members of the National Cancer Institute Quantitative Imaging Network. For the study, members were asked to segment a common set of phantom PET scans acquired over a range of imaging conditions as well as a second set of head and neck cancer (HNC) PET scans. Segmentations were generated at each institution using their preferred approach. In addition, participants were asked to repeat segmentations with a time interval between initial and repeat segmentation. This procedure resulted in overall 806 phantom insert and 641 lesion segmentations. Subsequently, the volume was computed from the segmentations and compared to the corresponding reference volume by means of statistical analysis.ResultsOn the two test sets (phantom and HNC PET scans), the performance of the seven segmentation approaches was as follows. On the phantom test set, the mean relative volume errors ranged from 29.9 to 87.8% of the ground truth reference volumes, and the repeat difference for each institution ranged between -36.4 to 39.9%. On the HNC test set, the mean relative volume error ranged between -50.5 to 701.5%, and the repeat difference for each institution ranged between -37.7 to 31.5%. In addition, performance measures per phantom insert/lesion size categories are given in the paper. On phantom data, regression analysis resulted in coefficient of variation (CV) components of 42.5% for scanners, 26.8% for institutional approaches, 21.1% for repeated segmentations, 14.3% for relative contrasts, 5.3% for count statistics (acquisition times), and 0.0% for repeated scans. Analysis showed that the CV components for approaches and repeated segmentations were significantly larger on the HNC test set with increases by 112.7% and 102.4%, respectively.ConclusionAnalysis results underline the importance of PET scanner reconstruction harmonization and imaging protocol standardization for quantification of lesion volumes. In addition, to enable a distributed multi-site analysis of FDG PET images, harmonization of analysis approaches and operator training in combination with highly automated segmentation methods seems to be advisable. Future work will focus on quantifying the impact of segmentation variation on radiomics system performance.

Project description:To compare the interobserver agreement and degree of confidence in anatomical localisation of lesions using 2-[fluorine-18]fluoro-2-deoxy-D-glucose ((18)F-FDG) positron emission tomography (PET)/computed tomography (CT) and (18)F-FDG PET alone in patients with head and neck tumours. A prospective study of 24 patients (16 male, eight female, median age 59 years) with head and neck tumours was undertaken. (18)F-FDG PET/CT was performed for staging purposes. 2D images were acquired over the head and neck area using a GE Discovery LS PET/CT scanner. (18)F-FDG PET images were interpreted by three independent observers. The observers were asked to localise abnormal (18)F-FDG activity to an anatomical territory and score the degree of confidence in localisation on a scale from 1 to 3 (1=exact region unknown; 2=probable; 3=definite). For all (18)F-FDG-avid lesions, standardised uptake values (SUVs) were also calculated. After 3 weeks, the same exercise was carried out using (18)F-FDG PET/CT images, where CT and fused volume data were made available to observers. The degree of interobserver agreement was measured in both instances. A total of six primary lesions with abnormal (18)F-FDG uptake (SUV range 7.2-22) were identified on (18)F-FDG PET alone and on (18)F-FDG PET/CT. In all, 15 nonprimary tumour sites were identified with (18)F-FDG PET only (SUV range 4.5-11.7), while 17 were identified on (18)F-FDG PET/CT. Using (18)F-FDG PET only, correct localisation was documented in three of six primary lesions, while (18)F-FDG PET/CT correctly identified all primary sites. In nonprimary tumour sites, (18)F-FDG PET/CT improved the degree of confidence in anatomical localisation by 51%. Interobserver agreement in assigning primary and nonprimary lesions to anatomical territories was moderate using (18)F-FDG PET alone (kappa coefficients of 0.45 and 0.54, respectively), but almost perfect with (18)F-FDG PET/CT (kappa coefficients of 0.90 and 0.93, respectively). We conclude that (18)F-FDG PET/CT significantly increases interobserver agreement and confidence in disease localisation of (18)F-FDG-avid lesions in patients with head and neck cancers.

Project description:PurposeThe use of magnetic resonance imaging (MRI) in radiotherapy treatment planning has rapidly increased due to its ability to evaluate patient's anatomy without the use of ionizing radiation and due to its high soft tissue contrast. For these reasons, MRI has become the modality of choice for longitudinal and adaptive treatment studies. Automatic segmentation could offer many benefits for these studies. In this work, we describe a T2-weighted MRI dataset of head and neck cancer patients that can be used to evaluate the accuracy of head and neck normal tissue auto-segmentation systems through comparisons to available expert manual segmentations.Acquisition and validation methodsT2-weighted MRI images were acquired for 55 head and neck cancer patients. These scans were collected after radiotherapy computed tomography (CT) simulation scans using a thermoplastic mask to replicate patient treatment position. All scans were acquired on a single 1.5 T Siemens MAGNETOM Aera MRI with two large four-channel flex phased-array coils. The scans covered the region encompassing the nasopharynx region cranially and supraclavicular lymph node region caudally, when possible, in the superior-inferior direction. Manual contours were created for the left/right submandibular gland, left/right parotids, left/right lymph node level II, and left/right lymph node level III. These contours underwent quality assurance to ensure adherence to predefined guidelines, and were corrected if edits were necessary.Data format and usage notesThe T2-weighted images and RTSTRUCT files are available in DICOM format. The regions of interest are named based on AAPM's Task Group 263 nomenclature recommendations (Glnd_Submand_L, Glnd_Submand_R, LN_Neck_II_L, Parotid_L, Parotid_R, LN_Neck_II_R, LN_Neck_III_L, LN_Neck_III_R). This dataset is available on The Cancer Imaging Archive (TCIA) by the National Cancer Institute under the collection "AAPM RT-MAC Grand Challenge 2019" (https://doi.org/10.7937/tcia.2019.bcfjqfqb).Potential applicationsThis dataset provides head and neck patient MRI scans to evaluate auto-segmentation systems on T2-weighted images. Additional anatomies could be provided at a later time to enhance the existing library of contours.

Project description:ImportanceThe mechanisms underlying the association between chronic stress and higher mortality among individuals with cancer remain incompletely understood.ObjectiveTo test the hypotheses that among individuals with active head and neck cancer, that higher stress-associated neural activity (ie. metabolic amygdalar activity [AmygA]) at cancer staging associates with survival.DesignRetrospective cohort study.SettingAcademic Medical Center (Massachusetts General Hospital, Boston).Participants240 patients with head and neck cancer (HNCA) who underwent 18F-FDG-PET/CT imaging as part of initial cancer staging.Measurements18F-FDG uptake in the amygdala was determined by placing circular regions of interest in the right and left amygdalae and measuring the mean tracer accumulation (i.e., standardized uptake value [SUV]) in each region of interest. Amygdalar uptake was corrected for background cerebral activity (mean temporal lobe SUV).ResultsAmong individuals with HNCA (age 59±13 years; 30% female), 67 died over a median follow-up period of 3 years (IQR: 1.7-5.1). AmygA associated with heightened bone marrow activity, leukocytosis, and C-reactive protein (P<0.05 each). In adjusted and unadjusted analyses, AmygA associated with subsequent mortality (HR [95% CI]: 1.35, [1.07-1.70], P = 0.009); the association persisted in stratified subset analyses restricted to patients with advanced cancer stage (P<0.001). Individuals within the highest tertile of AmygA experienced a 2-fold higher mortality rate compared to others (P = 0.01). The median progression-free survival was 25 months in patients with higher AmygA (upper tertile) as compared with 36.5 months in other individuals (HR for progression or death [95%CI], 1.83 [1.24-2.68], P = 0.001).Conclusions and relevanceAmygA, quantified on routine 18F-FDG-PET/CT images obtained at cancer staging, independently and robustly predicts mortality and cancer progression among patients with HNCA. Future studies should test whether strategies that attenuate AmygA (or its downstream biological consequences) may improve cancer survival.

Project description:BackgroundQuantification of molecular cell processes is important for prognostication and treatment individualization of head and neck cancer (HNC). However, individual tumor comparison can show discord in upregulation similarities when analyzing multiple biological mechanisms. Elaborate tumor characterization, integrating multiple pathways reflecting intrinsic and microenvironmental properties, may be beneficial to group most uniform tumors for treatment modification schemes. The goal of this study was to systematically analyze if immunohistochemical (IHC) assessment of molecular markers, involved in treatment resistance, and 18F-FDG PET parameters could accurately distinguish separate HNC tumors.MethodsSeveral imaging parameters and texture features for 18F-FDG small-animal PET and immunohistochemical markers related to metabolism, hypoxia, proliferation and tumor blood perfusion were assessed within groups of BALB/c nu/nu mice xenografted with 14 human HNC models. Classification methods were used to predict tumor line based on sets of parameters.ResultsWe found that 18F-FDG PET could not differentiate between the tumor lines. On the contrary, combined IHC parameters could accurately allocate individual tumors to the correct model. From 9 analyzed IHC parameters, a cluster of 6 random parameters already classified 70.3% correctly. Combining all PET/IHC characteristics resulted in the highest tumor line classification accuracy (81.0%; cross validation 82.0%), which was just 2.2% higher (p = 5.2×10-32) than the performance of the IHC parameter/feature based model.ConclusionsWith a select set of IHC markers representing cellular processes of metabolism, proliferation, hypoxia and perfusion, one can reliably distinguish between HNC tumor lines. Addition of 18F-FDG PET improves classification accuracy of IHC to a significant yet minor degree. These results may form a basis for development of tumor characterization models for treatment allocation purposes.

Dataset Information

Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images.

Publications

Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets