Search

PURPOSE: To develop a deep learning approach that enables ultra-low-dose, 1% of the standard clinical dosage (3 MBq/kg), ultrafast whole-body PET reconstruction in cancer imaging. MATERIALS AND METHODS: In this Health Insurance Portability and Accountability Act–compliant study, serial fluorine 18–labeled fluorodeoxyglucose PET/MRI scans of pediatric patients with lymphoma were retrospectively collected from two cross-continental medical centers between July 2015 and March 2020. Global similarity between baseline and follow-up scans was used to develop Masked-LMCTrans, a longitudinal multimodality coattentional convolutional neural network (CNN) transformer that provides interaction and joint reasoning between serial PET/MRI scans from the same patient. Image quality of the reconstructed ultra-low-dose PET was evaluated in comparison with a simulated standard 1% PET image. The performance of Masked-LMCTrans was compared with that of CNNs with pure convolution operations (classic U-Net family), and the effect of different CNN encoders on feature representation was assessed. Statistical differences in the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and visual information fidelity (VIF) were assessed by two-sample testing with the Wilcoxon signed rank t test. RESULTS: The study included 21 patients (mean age, 15 years ± 7 [SD]; 12 female) in the primary cohort and 10 patients (mean age, 13 years ± 4; six female) in the external test cohort. Masked-LMCTrans–reconstructed follow-up PET images demonstrated significantly less noise and more detailed structure compared with simulated 1% extremely ultra-low-dose PET images. SSIM, PSNR, and VIF were significantly higher for Masked-LMCTrans–reconstructed PET (P < .001), with improvements of 15.8%, 23.4%, and 186%, respectively. CONCLUSION: Masked-LMCTrans achieved high image quality reconstruction of 1% low-dose whole-body PET images. Keywords: Pediatrics, PET, Convolutional Neural Network (CNN), Dose Reduction Supplemental material is available for this article. © RSNA, 2023

Supplementary Data from Combination of Ribociclib and Gemcitabine for the Treatment of Medulloblastoma

Supplementary Figure from Combination of Ribociclib and Gemcitabine for the Treatment of Medulloblastoma

PURPOSE: To evaluate if ferumoxytol can improve the detection of bone marrow metastases at diffusion-weighted (DW) MRI in pediatric and young adult patients with cancer. MATERIALS AND METHODS: In this secondary analysis of a prospective institutional review board–approved study (ClinicalTrials.gov identifier NCT01542879), 26 children and young adults (age range: 2–25 years; 18 males) underwent unenhanced or ferumoxytol-enhanced whole-body DW MRI between 2015 and 2020. Two reviewers determined the presence of bone marrow metastases using a Likert scale. One additional reviewer measured signal-to-noise ratios (SNRs) and tumor-to-bone marrow contrast. Fluorine 18 ((18)F) fluorodeoxyglucose (FDG) PET and follow-up chest CT, abdominal and pelvic CT, and standard (non–ferumoxytol enhanced) MRI served as the reference standard. Results of different experimental groups were compared using generalized estimation equations, Wilcoxon rank sum test, and Wilcoxon signed rank test. RESULTS: The SNR of normal bone marrow was significantly lower at ferumoxytol-enhanced MRI compared with unenhanced MRI at baseline (21.380 ± 19.878 vs 102.621 ± 94.346, respectively; P = .03) and after chemotherapy (20.026 ± 7.664 vs 54.110 ± 48.022, respectively; P = .006). This led to an increased tumor-to-marrow contrast on ferumoxytol-enhanced MRI scans compared with unenhanced MRI scans at baseline (1397.474 ± 938.576 vs 665.364 ± 440.576, respectively; P = .07) and after chemotherapy (1099.205 ± 864.604 vs 500.758 ± 439.975, respectively; P = .007). Accordingly, the sensitivity and diagnostic accuracy for detecting bone marrow metastases were 96% (94 of 98) and 99% (293 of 297), respectively, with the use of ferumoxytol-enhanced MRI compared with 83% (106 of 127) and 95% (369 of 390) with the use of unenhanced MRI. CONCLUSION: Use of ferumoxytol helped improve the detection of bone marrow metastases in children and young adults with cancer. Keywords: Pediatrics, Molecular Imaging–Cancer, Molecular Imaging–Nanoparticles, MR–Diffusion Weighted Imaging, MR Imaging, Skeletal-Appendicular, Skeletal-Axial, Bone Marrow, Comparative Studies, Cancer Imaging, Ferumoxytol, USPIO © RSNA, 2023 ClinicalTrials.gov registration no. NCT01542879 See also the commentary by Holter-Chakrabarty and Glover in this issue.

Group3 (G3) medulloblastoma (MB) is one of the deadliest forms of the disease for which novel treatment is desperately needed. Here we evaluate ribociclib, a highly selective CDK4/6 inhibitor, with gemcitabine in mouse and human G3MBs. Ribociclib central nervous system (CNS) penetration was assessed by in vivo microdialysis and by IHC and gene expression studies and found to be CNS-penetrant. Tumors from mice treated with short term oral ribociclib displayed inhibited RB phosphorylation, downregulated E2F target genes, and decreased proliferation. Survival studies to determine the efficacy of ribociclib and gemcitabine combination were performed on mice intracranially implanted with luciferase-labeled mouse and human G3MBs. Treatment of mice with the combination of ribociclib and gemcitabine was well tolerated, slowed tumor progression and metastatic spread, and increased survival. Expression-based gene activity and cell state analysis investigated the effects of the combination after short- and long-term treatments. Molecular analysis of treated versus untreated tumors showed a significant decrease in the activity and expression of genes involved in cell-cycle progression and DNA damage response, and an increase in the activity and expression of genes implicated in neuronal identity and neuronal differentiation. Our findings in both mouse and human patient-derived orthotopic xenograft models suggest that ribociclib and gemcitabine combination therapy warrants further investigation as a treatment strategy for children with G3MB.

Deep learning may enable a reduction in dose of fluorine 18 fluorodeoxyglucose in integrated PET/MRI scans of children and young adults with lymphoma for treatment response assessment without compr...

Most circulating tumor DNA (ctDNA) assays are designed to detect recurrent mutations. Pediatric sarcomas share few recurrent mutations but rather are characterized by translocations and copy-number changes. We applied Cancer Personalized Profiling by deep Sequencing (CAPP-Seq) for detection of translocations found in the most common pediatric sarcomas. We also applied ichorCNA to the combined off-target reads from our hybrid capture to simultaneously detect copy-number alterations (CNA). We analyzed 64 prospectively collected plasma samples from 17 patients with pediatric sarcoma. Translocations were detected in the pretreatment plasma of 13 patients and were confirmed by tumor sequencing in 12 patients. Two of these patients had evidence of complex chromosomal rearrangements in their ctDNA. We also detected copy-number changes in the pretreatment plasma of 7 patients. We found that ctDNA levels correlated with metastatic status and clinical response. Furthermore, we detected rising ctDNA levels before relapse was clinically apparent, demonstrating the high sensitivity of our assay. This assay can be utilized for simultaneous detection of translocations and CNAs in the plasma of patients with pediatric sarcoma. While we describe our experience in pediatric sarcomas, this approach can be applied to other tumors that are driven by structural variants.

PURPOSE: Tumor response assessments on positron emission tomography (PET)/magnetic resonance imaging (MRI) scans requires correct quantification of radiotracer uptake in tumors and normal organs. Historically, MRI scans have been enhanced with gadolinium (Gd) based contrast agents, which are now controversial due to brain deposition. Recently, ferumoxytol nanoparticles have been identified as an alternative to Gd-based contrast agents, because they provide strong tissue enhancement on MR images but are not deposited in the brain. However, it is not known if the strong T1- and T2-contrast obtained with iron oxide nanoparticles such as ferumoxytol could affect MR-based attenuation correction of PET data. The purpose of our study was to investigate, if a ferumoxytol administration prior to a 2-deoxy-2-[(18)F]fluoro-D-glucose [(18)F]FDG PET/MR scan would change standardized uptake values (SUV) of normal organs. PROCEDURES: 30 pediatric patients (6-18 years) with malignant tumors underwent [(18)F]FDG-PET/MR scans (dose 3 MBq/kg). Fifteen patients received an intravenous ferumoxytol injection (5 mg Fe/kg) prior to the [(18)F]FDG-PET/MR scans (group 1). 15 additional age- and sex-matched patients received unenhanced [(18)F]FDG-PET/MR scans (group 2). For attenuation correction of PET data, we used a Dixon-based gradient echo sequence (TR 4.2 ms, TE 1. 1, 2.3 ms, FA 5), which accounted for soft tissue, lung, fat and background air. We used a mixed linear effects model to compare the tissue MRI enhancement, quantified as the signal-to-noise ratio (SNR), as well as tissue radiotracer signal, quantified as SUVmean and SUVmax, between group1 and group 2. Alpha was assumed at 0.05. RESULTS: The MRI enhancement of the blood and solid extra-cerebral organs, quantified as SNR, was significantly higher on ferumoxytol-enhanced MRI scans compared to unenhanced scans (p < 0.001). However, SUVmean and SUVmax values, corrected based on the patients body weight or body surface area, were not significantly different between the two groups (p > 0.05). CONCLUSION: Ferumoxytol administration prior to a [(18)F]FDG PET/MR scan did not change standardized uptake values (SUV) of solid extra-cerebral organs. This is important, because it allows to inject ferumoxytol contrast prior to a PET/MRI procedure and thereby, significantly accelterate image acquisition times.

Spitzoid melanoma is a specific morphologic variant of melanoma that most commonly affects children and adolescents, and ranges on the spectrum of malignancy from low grade to overtly malignant. These tumors are generally driven by fusions of ALK, RET, NTRK1/3, MET, ROS1 and BRAF1,2. However, in approximately 50% of cases no genetic driver has been established2. Clinical whole-genome and transcriptome sequencing (RNA-Seq) of a spitzoid tumor from an adolescent revealed a novel gene fusion of MAP3K8, encoding a serine-threonine kinase that activates MEK3,4. The patient, who had exhausted all other therapeutic options, was treated with a MEK inhibitor and underwent a transient clinical response. We subsequently analyzed spitzoid tumors from 49 patients by RNA-Seq and found in-frame fusions or C-terminal truncations of MAP3K8 in 33% of cases. The fusion transcripts and truncated genes all contained MAP3K8 exons 1–8 but lacked the autoinhibitory final exon. Data mining of RNA-Seq from the Cancer Genome Atlas (TCGA) uncovered analogous MAP3K8 rearrangements in 1.5% of adult melanomas. Thus, MAP3K8 rearrangements—uncovered by comprehensive clinical sequencing of a single case—are the most common genetic event in spitzoid melanoma, are present in adult melanomas and could be amenable to MEK inhibition. Rearrangements in MAP3K8 respond to MEK inhibition and represent the most common genetic driver in pediatric spitzoid melanoma, and in some adult melanomas lacking other MAPK alterations and for which clinical testing is warranted.

Medulloblastoma is the most common malignant pediatric brain tumor. Extensive molecular analysis by many groups around the world demonstrated four distinct subgroups, WNT, SHH, Group3 and Group4 that now all have been divided into 11 total subtypes, 8 for Grou3 and Group4 medulloblastoma. SHH with MYCN amplification and TP53 mutations and Group3 with MYC amplification are the most aggressive and the least curable with few to no therapeutic options for recurrent tumors. Over the last two decades, my group developed several murine models for Group3 with MYC and SHH with MYCN overexpression and p53 loss of function and patient-derived orthotopic xenografts that recapitulate the four tumor subgroups. In addition, several human Group3 medulloblastoma lines with MYC amplification have been established in 2D and 3D cultures. I will discuss how the development of these murine and human medulloblastoma models combined with high throughput drug screens and pre-clinical trials at St. Jude led to the identification of new therapies currently evaluated in clinical trials.

PURPOSE: To generate diagnostic (18)F-FDG PET images of pediatric cancer patients from ultra-low dose (18)F-FDG PET input images, using a novel artificial intelligence (AI) algorithm. METHODS: We used whole body (18)F-FDG-PET/MRI scans of 33 children and young adults with lymphoma (3–30 years) to developed a convolutional neural network (CNN), which combines inputs from simulated 6.25% ultra-low-dose (18)F-FDG PET scans and simultaneously acquired MRI scans to produce a standard dose (18)F-FDG PET scan. The image quality of ultra-low-dose PET scans, AI-augmented PET scans and clinical standard PET scans was evaluated by traditional metrics in computer vision, and by expert radiologists and nuclear medicine physicians, using Wilcoxon signed rank tests and weighted kappa statistics. RESULTS: The peak signal-to-noise ratio and structural similarity index were significantly higher, and the normalized root-mean-square error significantly lower on the AI-reconstructed PET images compared to simulated 6.25% dose images (p

Medulloblastoma (MB) consists of four core molecular subgroups with distinct clinical features and prognoses. Treatment consists of surgery, followed by radiotherapy and cytotoxic chemotherapy. Despite this intensive approach, outcome remains dismal for patients with certain subtypes of MB, namely MYC-amplified Group 3 and TP53-mutated SHH. Using high-throughput assays, six human MB cell lines were screened against a library of 3208 unique compounds. We identified 45 effective compounds from the screen and found that inhibition cell cycle checkpoint kinases (CHK1 and 2) synergistically enhanced the cytotoxic activity of clinically-used chemotherapeutics cyclophosphamide, cisplatin, and gemcitabine. To identify the best-in-class inhibitor, multiple CHK1/2 inhibitors were assessed in mice bearing intracranial MB. When combined with DNA-damaging chemotherapeutics, CHK1/2 inhibition reduced tumor burden and significantly increased survival of animals with high-risk MB, across multiple different models. In total, we tested 14 different models, representing distinct MB subgroups, and data were validated in three independent laboratories. Pharmacodynamics studies confirmed central nervous system penetration. In mice, combination treatment significantly increased DNA damage and apoptosis compared to chemotherapy alone, and studies with cultured cells showed that CHK inhibition disrupted chemotherapy-induced cell cycle arrest. Our findings indicated CHK1/2 inhibition, specifically with LY2606368 (prexasertib), has strong chemosensitizing activity in MB that warrants further clinical investigation. Moreover, these data demonstrated that we developed a robust and collaborative preclinical assessment platform that can be used to identify potentially effective new therapies for clinical evaluation for pediatric MB.

Population-level estimates of the survival of children from low- and middle-income countries diagnosed with solid tumors do not currently exist, in contrast to outcomes of hematologic and central nervous system cancers, which have been collated from population-based cancer registries and published by the CONCORD Programme. To fill this knowledge gap, we conducted a systematic review of PubMed Legacy, Embase, Web of Science, Cochrane Central Registry of Controlled Trials, and three regional databases for publications that reported survival of children diagnosed age 0-14 years with any malignancy from January 2011 to December 2016. The search identified 4695 original records; 51 articles met inclusion criteria. The range of survival reported was broad; for instance, 5-year overall survival for retinoblastoma ranged from 48% in Central America to 98% in China. However, the paucity of published statistics prevented approaches for meta-analyses and emphasizes the need for more standardized data collection and reporting.

While pediatric oncology saw great advances in patient survival throughout the second half of the twentieth century with the adoption of combination chemotherapy and multimodal therapy (Smith et al. 2014), this effect has mostly plateaued over the past two decades. This is especially noticeable in high-risk metastatic and relapsed sarcomas, where there has been little progress in improving patient outcomes for over 30 years. Therefore, the success of immunotherapy across a broad spectrum of cancers, including malignancies resistant to other forms of conventional cytotoxic chemotherapy or targeted therapies (Brahmer et al. 2015; Postow et al. 2015; Brown et al. 2016; Robert et al. 2015), has sparked an interest in harnessing these therapies to treat pediatric sarcomas. In pediatric oncology in general, immunotherapy has already altered the landscape of relapsed B cell acute lymphoblastic leukemia (anti-CD19 CAR T cells (Lee et al. 2015; Maude et al. 2014, 2018; Gardner et al. 2017) and bispecific antibodies (Gore et al. 2018; von Stackelberg et al. 2016)) and high-risk neuroblastoma (anti-GD2 monoclonal antibodies (Yu et al. 2010; Kushner et al. 2018)). To date, the efficacy of immunotherapy in the treatment of pediatric sarcomas has been disappointing, and this approach has not yet benefited large numbers of patients. However, early results from several trials indicate that this powerful strategy will eventually bear fruit, adding to the multimodal armament needed to cure high-risk malignancies.

PURPOSE: To investigate if a deep learning convolutional neural network (CNN) could enable low-dose fluorine 18 ((18)F) 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 (18)F-FDG PET/MRI between July 2015 and August 2019 at baseline and after induction chemotherapy. Full-dose (18)F-FDG PET data (3 MBq/kg) were simulated to lower (18)F-FDG doses based on the percentage of coincidence events (representing simulated 75%, 50%, 25%, 12.5%, and 6.25% (18)F-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 (SUV(max)) 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 SUV(max) 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% (18)F-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 Assessment Clinical trial registration no: NCT01542879 Supplemental material is available for this article. © RSNA, 2021

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.