RESUMEN
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 biomarkers of AI were in good agreement with experts. Conclusion: Deep learning can be used to automate 18F-FDG PET/CT tumor-volume-derived imaging biomarkers, and the deep-learning-based volumes have the potential to assist clinical tumor volume delineation in radiation oncology.
RESUMEN
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-[18F]fluoro-d-glucose (18F-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.