Search

Artificial intelligence (AI) may decrease 18F-FDG PET/CT-based gross tumor volume (GTV) delineation variability and automate tumor-volume-derived image biomarker extraction. Hence, we aimed to identify and evaluate promising state-of-the-art deep learning methods for head and neck cancer (HNC) PET GTV delineation. Methods: We trained and evaluated deep learning methods using retrospectively included scans of HNC patients referred for radiotherapy between January 2014 and December 2019 (ISRCTN16907234). We used 3 test datasets: an internal set to compare methods, another internal set to compare AI-to-expert variability and expert interobserver variability (IOV), and an external set to compare internal and external AI-to-expert variability. Expert PET GTVs were used as the reference standard. Our benchmark IOV was measured using the PET GTV of 6 experts. The primary outcome was the Dice similarity coefficient (DSC). ANOVA was used to compare methods, a paired t test was used to compare AI-to-expert variability and expert IOV, an unpaired t test was used to compare internal and external AI-to-expert variability, and post hoc Bland-Altman analysis was used to evaluate biomarker agreement. Results: In total, 1,220 18F-FDG PET/CT scans of 1,190 patients (mean age ± SD, 63 ± 10 y; 858 men) were included, and 5 deep learning methods were trained using 5-fold cross-validation (n = 805). The nnU-Net method achieved the highest similarity (DSC, 0.80 [95% CI, 0.77-0.86]; n = 196). We found no evidence of a difference between expert IOV and AI-to-expert variability (DSC, 0.78 for AI vs. 0.82 for experts; mean difference of 0.04 [95% CI, -0.01 to 0.09]; P = 0.12; n = 64). We found no evidence of a difference between the internal and external AI-to-expert variability (DSC, 0.80 internally vs. 0.81 externally; mean difference of 0.004 [95% CI, -0.05 to 0.04]; P = 0.87; n = 125). PET GTV-derived bio

PET/CT with the tracer 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) has improved diagnostic imaging in cancer and is routinely used for diagnosing, staging and treatment planning in lung cancer patients. However, pitfalls of [18F]FDG-PET/CT limit the use in specific settings. Additionally, lung cancer is still the leading cause of cancer associated death and has high risk of recurrence after curative treatment. These circumstances have led to the continuous search for more sensitive and specific PET tracers to optimize lung cancer diagnosis, staging, treatment planning and evaluation. The objective of this review is to present and discuss current knowledge and perspectives of new PET tracers for use in lung cancer. A literature search was performed on PubMed and clinicaltrials.gov, limited to the past decade, excluding case reports, preclinical studies and studies on established tracers such as [18F]FDG and DOTATE. The most relevant papers from the search were evaluated. Several tracers have been developed targeting specific tumor characteristics and hallmarks of cancer. A small number of tracers have been studied extensively and evaluated head-to-head with [18F]FDG-PET/CT, whereas others need further investigation and validation in larger clinical trials. At this moment, none of the tracers can replace [18F]FDG-PET/CT. However, they might serve as supplementary imaging methods to provide more knowledge about biological tumor characteristics and visualize intra- and inter-tumoral heterogeneity.

Objectives The aim of this study was to assess the test-retest repeatability and interobserver variation in healthy tissue (HT) metabolism using 2-deoxy-2-[F-18]fluoro-d-glucose (F-18-FDG) PET/computed tomography (PET/CT) of the thorax in lung cancer patients. Methods A retrospective analysis was conducted in 22 patients with non-small cell lung cancer who had two PET/CT scans of the thorax performed 3 days apart with no interval treatment. The maximum, mean and peak standardized uptake values (SUVs) in different HTs were measured by a single observer for the test-retest analysis and two observers for interobserver variation. Bland-Altman plots were used to assess the repeatability and interobserver variation. Intrasubject variability was evaluated using within-subject coefficients of variation (wCV). Results The wCV of test-retest SUVmean measurements in mediastinal blood pool, bone marrow, skeletal muscles and lungs was less than 20%. The left ventricle (LV) showed higher wCV (>60%) in all SUV parameters with wide limits of repeatability. High interobserver agreement was found with wCV of less than 10% in SUVmean of all HT, but up to 22% was noted in the LV. Conclusion HT metabolism is stable in a test-retest scenario and has high interobserver agreement. SUVmean was the most stable metric in organs with low FDG uptake and SUVpeak in HTs with moderate uptake. Test-retest measurements in LV were highly variable irrespective of the SUV parameters used for measurements.

RATIONALE: Tumor biopsy cannot detect heterogeneity and an association between heterogeneity in functional imaging and molecular biology will have an impact on both diagnostics and treatment possibilities.PURPOSE: Multiparametric imaging can provide 3D information on functional aspects of a tumor and may be suitable for predicting intratumor heterogeneity. Here, we investigate the correlation between intratumor heterogeneity assessed with multiparametric imaging and multiple-biopsy immunohistochemistry.METHODS: In this prospective study, patients with primary or recurrent head and neck squamous cell carcinoma (HNSCC) underwent PET/MRI scanning prior to surgery. Tumors were removed en bloc and six core biopsies were used for immunohistochemical (IHC) staining with a predefined list of biomarkers: p40, p53, EGFR, Ki-67, GLUT1, VEGF, Bcl-2, CAIX, PD-L1. Intratumor heterogeneity of each IHC biomarker was quantified by calculating the coefficient of variation (CV) in tumor proportion score among the six core biopsies within each tumor lesion. The heterogeneity in the imaging biomarkers was assessed by calculating CV in 18F-fluorodeoxyglucose (FDG)-uptake, diffusion and perfusion. Concordance of the two variance measures was quantified using Spearman's rank correlation RESULTS: Twenty-eight patients with a total of 33 lesions were included. There was considerable heterogeneity in most of the IHC biomarkers especially in GLUT1, PD-L1, Ki-67, CAIX and p53, however we only observed a correlation between the heterogeneity in GLUT1 and p53 and between Ki-67 and EGFR. Heterogeneity in FDG uptake and diffusion correlated with heterogeneity in cell density.CONCLUSION: Considerable heterogeneity of IHC biomarkers was found, however, only few and weak correlations between the studied IHC markers were observed. The studied functional imaging biomarkers showed weak associations with heterogeneity in some of the IHC biomarkers. Thus, biological heterogeneity is