Validation of Convolutional Neural Networks for Fast Determination of Whole-Body Metabolic Tumor Burden in Pediatric Lymphoma.

18F-FDG PET/CT quantification of whole-body tumor burden in lymphoma is not routinely performed because of the lack of fast methods. Although the semiautomatic method is fast, it is not fast enough to quantify tumor burden in daily clinical practice. Our purpose was to evaluate the performance of convolutional neural network (CNN) software in localizing neoplastic lesions in whole-body 18F-FDG PET/CT images of pediatric lymphoma patients. Methods: The retrospective image dataset, derived from the data pool of the International Atomic Energy Agency (coordinated research project E12017), included 102 baseline staging 18F-FDG PET/CT studies of pediatric lymphoma patients (mean age, 11 y). The images were quantified to determine the whole-body tumor burden (whole-body metabolic tumor volume [wbMTV] and whole-body total lesion glycolysis [wbTLG]) using semiautomatic software and CNN-based software. Both were displayed as semiautomatic wbMTV and wbTLG and as CNN wbMTV and wbTLG. The intraclass correlation coefficient (ICC) was applied to evaluate concordance between the CNN-based software and the semiautomatic software. Results: Twenty-six patients were excluded from the analysis because the software was unable to perform calculations for them. In the remaining 76 patients, CNN and semiautomatic wbMTV tumor burden metrics correlated strongly (ICC, 0.993; 95% CI, 0.989 - 0.996; P < 0.0001), as did CNN and semiautomatic wbTLG (ICC, 0.999; 95% CI, 0.998-0.999; P < 0.0001). However, the time spent calculating these metrics was significantly (<0.0001) less by CNN (mean, 19 s; range, 11-50 s) than by the semiautomatic method (mean, 21.6 min; range, 3.2-62.1 min), especially in patients with advanced disease. Conclusion: Determining whole-body tumor burden in pediatric lymphoma patients using CNN is fast and feasible in clinical practice.

Is True Whole-Body 18F-FDG PET/CT Required in Pediatric Lymphoma? An IAEA Multicenter Prospective Study.

Guidelines recommend true whole-body 18F-FDG PET/CT scans from vertex to toes in pediatric lymphoma patients, although this suggestion has not been validated in large clinical trials. The objective of the study was to evaluate the incidence and clinical impact of lesions outside the "eyes to thighs" regular field of view (R-FOV) in 18F-FDG PET/CT staging (sPET) and interim (iPET) scans in pediatric lymphoma patients. Methods: True whole-body sPET and iPET scans were prospectively obtained in pediatric lymphoma patients (11 worldwide centers). Expert panel central review of sPET and iPET scans were evaluated for lymphoma lesions outside the R-FOV and clinical relevance of these findings. Results: A total of 610 scans were obtained in 305 patients. The sPET scans did not show lesions outside the R-FOV in 91.8% of the patients, whereas in 8.2% patients the sPET scans demonstrated lesions also outside the R-FOV (soft tissue, bone, bone marrow, and skin); however, the presence of these lesions did not change the clinical stage of any patient and did not affect treatment decision. Among the 305 iPET scans, there were no new positive 18F-FDG-avid lesions outside the R-FOV, when compared with their paired sPET scans. A single lesion outside the R-FOV on iPET occurred in 1 patient (0.3%), with the primary lesion diagnosed in the femur on sPET that persisted on iPET. Conclusion: The identification of additional lesions outside the R-FOV (eyes to thighs) using 18F-FDG PET/CT has no impact in the definition of the clinical stage of disease and minimal impact in the treatment definition of patients with pediatric lymphoma. As so, R-FOV for both sPET and iPET scans could be performed.