Validation of Deep Learning-based Augmentation for Reduced 18F-FDG Dose for PET/MRI in Children and Young Adults with Lymphoma.

PURPOSE: To investigate if a deep learning convolutional neural network (CNN) could enable low-dose fluorine 18 (18F) fluorodeoxyglucose (FDG) PET/MRI for correct treatment response assessment of children and young adults with lymphoma. MATERIALS AND METHODS: In this secondary analysis of prospectively collected data (ClinicalTrials.gov identifier: NCT01542879), 20 patients with lymphoma (mean age, 16.4 years ± 6.4 [standard deviation]) underwent 18F-FDG PET/MRI between July 2015 and August 2019 at baseline and after induction chemotherapy. Full-dose 18F-FDG PET data (3 MBq/kg) were simulated to lower 18F-FDG doses based on the percentage of coincidence events (representing simulated 75%, 50%, 25%, 12.5%, and 6.25% 18F-FDG dose [hereafter referred to as 75%Sim, 50%Sim, 25%Sim, 12.5%Sim, and 6.25%Sim, respectively]). A U.S. Food and Drug Administration-approved CNN was used to augment input simulated low-dose scans to full-dose scans. For each follow-up scan after induction chemotherapy, the standardized uptake value (SUV) response score was calculated as the maximum SUV (SUVmax) of the tumor normalized to the mean liver SUV; tumor response was classified as adequate or inadequate. Sensitivity and specificity in the detection of correct response status were computed using full-dose PET as the reference standard. RESULTS: With decreasing simulated radiotracer doses, tumor SUVmax increased. A dose below 75%Sim of the full dose led to erroneous upstaging of adequate responders to inadequate responders (43% [six of 14 patients] for 75%Sim; 93% [13 of 14 patients] for 50%Sim; and 100% [14 of 14 patients] below 50%Sim; P < .05 for all). CNN-enhanced low-dose PET/MRI scans at 75%Sim and 50%Sim enabled correct response assessments for all patients. Use of the CNN augmentation for assessing adequate and inadequate responses resulted in identical sensitivities (100%) and specificities (100%) between the assessment of 100% full-dose PET, augmented 75%Sim, and augmented 50%Sim images. CONCLUSION: CNN enhancement of PET/MRI scans may enable 50% 18F-FDG dose reduction with correct treatment response assessment of children and young adults with lymphoma.Keywords: Pediatrics, PET/MRI, Computer Applications Detection/Diagnosis, Lymphoma, Tumor Response, Whole-Body Imaging, Technology AssessmentClinical trial registration no: NCT01542879 Supplemental material is available for this article. © RSNA, 2021.

Therapy Response Assessment of Pediatric Tumors with Whole-Body Diffusion-weighted MRI and FDG PET/MRI.

Background Whole-body diffusion-weighted (DW) MRI can help detect cancer with high sensitivity. However, the assessment of therapy response often requires information about tumor metabolism, which is measured with fluorine 18 fluorodeoxyglucose (FDG) PET. Purpose To compare tumor therapy response with whole-body DW MRI and FDG PET/MRI in children and young adults. Materials and Methods In this prospective, nonrandomized multicenter study, 56 children and young adults (31 male and 25 female participants; mean age, 15 years ± 4 [standard deviation]; age range, 6-22 years) with lymphoma or sarcoma underwent 112 simultaneous whole-body DW MRI and FDG PET/MRI between June 2015 and December 2018 before and after induction chemotherapy (ClinicalTrials.gov identifier: NCT01542879). The authors measured minimum tumor apparent diffusion coefficients (ADCs) and maximum standardized uptake value (SUV) of up to six target lesions and assessed therapy response after induction chemotherapy according to the Lugano classification or PET Response Criteria in Solid Tumors. The authors evaluated agreements between whole-body DW MRI- and FDG PET/MRI-based response classifications with Krippendorff α statistics. Differences in minimum ADC and maximum SUV between responders and nonresponders and comparison of timing for discordant and concordant response assessments after induction chemotherapy were evaluated with the Wilcoxon test. Results Good agreement existed between treatment response assessments after induction chemotherapy with whole-body DW MRI and FDG PET/MRI (α = 0.88). Clinical response prediction according to maximum SUV (area under the receiver operating characteristic curve = 100%; 95% confidence interval [CI]: 99%, 100%) and minimum ADC (area under the receiver operating characteristic curve = 98%; 95% CI: 94%, 100%) were similar (P = .37). Sensitivity and specificity were 96% (54 of 56 participants; 95% CI: 86%, 99%) and 100% (56 of 56 participants; 95% CI: 54%, 100%), respectively, for DW MRI and 100% (56 of 56 participants; 95% CI: 93%, 100%) and 100% (56 of 56 participants; 95% CI: 54%, 100%) for FDG PET/MRI. In eight of 56 patients who underwent imaging after induction chemotherapy in the early posttreatment phase, chemotherapy-induced changes in tumor metabolism preceded changes in proton diffusion (P = .002). Conclusion Whole-body diffusion-weighted MRI showed significant agreement with fluorine 18 fluorodeoxyglucose PET/MRI for treatment response assessment in children and young adults. © RSNA, 2020 Online supplemental material is available for this article.

Comparison of ferumoxytol- and gadolinium chelate-enhanced MRI for assessment of sarcomas in children and adolescents.

OBJECTIVES: We compared the value of ferumoxytol (FMX)- and gadolinium (Gd)-enhanced MRI for assessment of sarcomas in paediatric/adolescent patients and hypothesised that tumour size and morphological features can be equally well assessed with both protocols. METHODS: We conducted a retrospective study of paediatric/adolescent patients with newly diagnosed bone or soft tissue sarcomas and both pre-treatment FMX- and Gd-MRI scans, which were maximal 4 weeks apart. Both protocols included T1- and T2-weighted sequences. One reader assessed tumour volumes, signal-to-noise ratios (SNR) of the primary tumour and adjacent tissues and contrast-to-noise ratios (CNR) of FMX- and Gd-MRI scans. Additionally, four readers scored FMX- and Gd-MRI scans according to 15 diagnostic parameters, using a Likert scale. The results were pooled across readers and compared between FMX- and Gd-MRI scans. Statistical methods included multivariate analyses with different models. RESULTS: Twenty-two patients met inclusion criteria (16 males, 6 females; mean age 15.3 ± 5.0). Tumour volume was not significantly different on T1-LAVA (p = 0.721), T1-SE (p = 0.290) and T2-FSE (p = 0.609) sequences. Compared to Gd-MRI, FMX-MRI demonstrated significantly lower tumour SNR on T1-LAVA (p < 0.001), equal tumour SNR on T1-SE (p = 0.104) and T2-FSE (p = 0.305), significantly higher tumour-to-marrow CNR (p < 0.001) on T2-FSE as well as significantly higher tumour-to-liver (p = 0.021) and tumour-to-vessel (p = 0.003) CNR on T1-LAVA images. Peritumoural and marrow oedema enhanced significantly more on Gd-MRI compared to FMX-MRI (p < 0.001/p = 0.002, respectively). Tumour thrombi and neurovascular bundle involvement were assessed with a significantly higher confidence on FMX-MRI (both p < 0.001). CONCLUSIONS: FMX-MRI provides equal assessment of the extent of bone and soft tissue sarcomas compared to Gd-MRI with improved tumour delineation and improved evaluation of neurovascular involvement and tumour thrombi. Therefore, FMX-MRI is a possible alternative to Gd-MRI for tumour staging in paediatric/adolescent sarcoma patients. KEY POINTS: • Ferumoxytol can be used as an alterative to gadolinium chelates for MRI staging ofpaediatric sarcomas. • Ferumoxytol-enhanced MRI provides equal assessment of tumour size and other diagnostic parameters compared to gadolinium chelate-enhanced MRI. • Ferumoxytol-enhanced MRI provides improved delineation of sarcomas from bone marrow, liver and vessels compared to gadolinium chelate-enhanced MRI.

A PET/MR Imaging Approach for the Integrated Assessment of Chemotherapy-induced Brain, Heart, and Bone Injuries in Pediatric Cancer Survivors: A Pilot Study.

Purpose To develop a positron emission tomography (PET)/magnetic resonance (MR) imaging protocol for evaluation of the brain, heart, and joints of pediatric cancer survivors for chemotherapy-induced injuries in one session. Materials and Methods Three teams of experts in neuroimaging, cardiac imaging, and bone imaging were tasked to develop a 20-30-minute PET/MR imaging protocol for detection of chemotherapy-induced tissue injuries of the brain, heart, and bone. In an institutional review board-approved, HIPAA-compliant, prospective study from April to July 2016, 10 pediatric cancer survivors who completed chemotherapy underwent imaging of the brain, heart, and bone with a 3-T PET/MR imager. Cumulative chemotherapy doses and clinical symptoms were correlated with the severity of MR imaging abnormalities by using linear regression analyses. MR imaging measures of brain perfusion and metabolism were compared among eight patients who were treated with methotrexate and eight untreated age-matched control subjects by using Wilcoxon rank-sum tests. Results Combined brain, heart, and bone examinations were completed within 90 minutes. Eight of 10 cancer survivors had abnormal findings on brain, heart, and bone images, including six patients with and two patients without clinical symptoms. Cumulative chemotherapy doses correlated significantly with MR imaging measures of left ventricular ejection fraction and end-systolic volume, but not with the severity of brain or bone abnormalities. Methotrexate-treated cancer survivors had significantly lower cerebral blood flow and metabolic activity in key brain areas compared with control subjects. Conclusion The feasibility of a single examination for assessment of chemotherapy-induced injuries of the brain, heart, and joints was shown. Earlier detection of tissue injuries may enable initiation of timely interventions and help to preserve long-term health of pediatric cancer survivors. © RSNA, 2017 Online supplemental material is available for this article.