Search

Abstract Purpose For pediatric lymphoma, quantitative FDG PET/CT imaging features such as metabolic tumor volume (MTV) are important for prognosis and risk stratification strategies. However, feature extraction is difficult and time-consuming in cases of high disease burden. The purpose of this study was to fully automate the measurement of PET imaging features in PET/CT images of pediatric lymphoma. Methods 18F-FDG PET/CT baseline images of 100 pediatric Hodgkin lymphoma patients were retrospectively analyzed. Two nuclear medicine physicians identified and segmented FDG avid disease using PET thresholding methods. Both PET and CT images were used as inputs to a three-dimensional patch-based, multi-resolution pathway convolutional neural network architecture, DeepMedic. The model was trained to replicate physician segmentations using an ensemble of three networks trained with 5-fold cross-validation. The maximum SUV (SUVmax), MTV, total lesion glycolysis (TLG), surface-area-to-volume ratio (SA/MTV), and a measure of disease spread (Dmaxpatient) were extracted from the model output. Pearson’s correlation coefficient and relative percent differences were calculated between automated and physician-extracted features. Results Median Dice similarity coefficient of patient contours between automated and physician contours was 0.86 (IQR 0.78–0.91). Automated SUVmax values matched exactly the physician determined values in 81/100 cases, with Pearson’s correlation coefficient (R) of 0.95. Automated MTV was strongly correlated with physician MTV (R = 0.88), though it was slightly underestimated with a median (IQR) relative difference of − 4.3% (− 10.0–5.7%). Agreement of TLG was excellent (R = 0.94), with median (IQR) relative difference of − 0.4% (− 5.2–7.0%). Median relative percent differences were 6.8% (R = 0.91; IQR 1.6–4.3%) for SA/MTV, and 4.5% (R = 0.51; IQR − 7.5–40.9%) for Dmaxpatient, which was the most difficult feature to quantify automatically. Conclusions An automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.

Abstract Background We have previously developed a novel and highly consistent PET segmentation algorithm using a multi-level Otsu method (MO-PET). The aim of this study was to evaluate the reliability of MO-PET compared to conventional PET segmentation methods for measuring 18F-FDG (FDG) PET metabolic tumor volume (MTV) in patients with soft tissue sarcoma (STS). Clinical and imaging data were obtained from the Cancer Imaging Archive. Forty-eight STS patients with FDG PET/CT and MR prior to therapy were analyzed. MTV of the tumor using MO-PET was compared to other conventional methods (absolute SUV threshold values of 2.0, 2.5, or 3.0 and percentage of tumor SUVmax values of 30, 40, 50, or 60%) and gradient-based method (PET Edge™). The reference volume was defined as an MR-based gross tumor volume (GTV). Spearman, intra-class correlation, and Bland-Altman analysis were performed to evaluate the correlation and agreement of MTV to GTV. Results MTVs obtained using each conventional SUV parameter, PET Edge™, and MO-PET were highly correlated with the GTV in Spearman and intra-class correlation analysis (p