Deep-Learning Models for Abdominal CT Organ Segmentation in Children: Development and Validation in Internal and Heterogeneous Public Datasets.

Background: Deep-learning abdominal organ segmentation algorithms have shown excellent results in adults; validation in children is sparse. Objective: To develop and validate deep-learning models for liver, spleen, and pancreas segmentation on pediatric CT examinations. Methods: This retrospective study developed and validated deep-learning models for liver, spleen, and pancreas segmentation using 1731 CT examinations (1504 training, 221 testing), derived from three internal institutional pediatric (age ≤18) datasets (n=483) and three public datasets comprising pediatric and adult examinations with various pathologies (n=1248). Three deep-learning model architectures (SegResNet, DynUNet, and SwinUNETR) from the Medical Open Network for AI (MONAI) framework underwent training using native training (NT), relying solely on institutional datasets, and transfer learning (TL), incorporating pre-training on public datasets. For comparison, TotalSegmentator (TS), a publicly available segmentation model, was applied to test data without further training. Segmentation performance was evaluated using mean Dice similarity coefficient (DSC), with manual segmentations as reference. Results: For internal pediatric data, DSC for normal liver was 0.953 (TS), 0.964-0.965 (NT models), and 0.965-0.966 (TL models); normal spleen, 0.914 (TS), 0.942-0.945 (NT models), and 0.937-0.945 (TL models); normal pancreas, 0.733 (TS), 0.774-0.785 (NT models), and 0.775-0.786 (TL models); pancreas with pancreatitis, 0.703 (TS), 0.590-0.640 (NT models), and 0.667-0.711 (TL models). For public pediatric data, DSC for liver was 0.952 (TS), 0.876-0.908 (NT models), and 0.941-0.946 (TL models); spleen, 0.905 (TS), 0.771-0.827 (NT models), and 0.897-0.926 (TL models); pancreas, 0.700 (TS), 0.577-0.648 (NT models), and 0.693-0.736 (TL models). For public primarily adult data, DSC for liver was 0.991 (TS), 0.633-0.750 (NT models), and 0.926-0.952 (TL models); spleen, 0.983 (TS), 0.569-0.604 (NT models), and 0.923-0.947 (TL models); pancreas, 0.909 (TS), 0.148-0.241 (NT models), and 0.699-0.775 (TL models). DynUNet-TL was selected as the best-performing NT or TL model and was made available as an opensource MONAI bundle (https://github.com/cchmc-dll/pediatric_abdominal_segmentation_bundle.git). Conclusion: TL models trained on heterogeneous public datasets and fine-tuned using institutional pediatric data outperformed internal NT models and TotalSegmentator across internal and external pediatric test data. Segmentation performance was better in liver and spleen than in pancreas. Clinical Impact: The selected model may be used for various volumetry applications in pediatric imaging.

An adult and pediatric size-based contrast administration reduction phantom study for single and dual-energy CT through preservation of contrast-to-noise ratio.

BACKGROUND: Global shortages of iodinated contrast media (ICM) during COVID-19 pandemic forced the imaging community to use ICM more strategically in CT exams. PURPOSE: The purpose of this work is to provide a quantitative framework for preserving iodine CNR while reducing ICM dosage by either lowering kV in single-energy CT (SECT) or using lower energy virtual monochromatic images (VMI) from dual-energy CT (DECT) in a phantom study. MATERIALS AND METHODS: In SECT study, phantoms with effective diameters of 9.7, 15.9, 21.1, and 28.5 cm were scanned on SECT scanners of two different manufacturers at a range of tube voltages. Statistical based iterative reconstruction and deep learning reconstruction were used. In DECT study, phantoms with effective diameters of 20, 29.5, 34.6, and 39.7 cm were scanned on DECT scanners from three different manufacturers. VMIs were created from 40 to 140 keV. ICM reduction by lowering kV levels for SECT or switching from SECT to DECT was calculated based on the linear relationship between iodine CNR and its concentration under different scanning conditions. RESULTS: On SECT scanner A, while matching CNR at 120 kV, ICM reductions of 21%, 58%, and 72% were achieved at 100, 80, and 70 kV, respectively. On SECT scanner B, 27% and 80% ICM reduction was obtained at 80 and 100 kV. On the Fast-kV switch DECT, with CNR matched at 120 kV, ICM reductions were 35%, 30%, 23%, and 15% with VMIs at 40, 50, 60, and 68 keV, respectively. On the dual-source DECT, ICM reductions were 52%, 48%, 42%, 33%, and 22% with VMIs at 40, 50, 60, 70, and 80 keV. On the dual-layer DECT, ICM reductions were 74%, 62%, 45%, and 22% with VMIs at 40, 50, 60, and 70 keV. CONCLUSIONS: Our work provided a quantitative baseline for other institutions to further optimize their scanning protocols to reduce the use of ICM.

Reduced count pediatric whole-body 18F-FDG PET imaging reconstruction with a Bayesian penalized likelihood algorithm.

BACKGROUND: Advanced positron emission tomography (PET) image reconstruction methods promise to allow optimized PET/CT protocols with improved image quality, decreased administered activity and/or acquisition times. OBJECTIVE: To evaluate the impact of reducing counts (simulating reduced acquisition time) in block sequential regularized expectation maximization (BSREM) reconstructed pediatric whole-body 18F-fluorodeoxyglucose (FDG) PET images, and to compare BSERM with ordered-subset expectation maximization (OSEM) reconstructed reduced-count images. MATERIALS AND METHODS: Twenty children (16 male) underwent clinical whole-body 18F-FDG PET/CT examinations using a 25-cm axial field-of-view (FOV) digital PET/CT system at 90 s per bed (s/bed) with BSREM reconstruction (ß=700). Reduced count simulations with varied BSREM ß levels were generated from list-mode data: 60 s/bed, ß=800; 50 s/bed, ß=900; 40 s/bed, ß=1000; and 30 s/bed, ß=1300. In addition, a single OSEM reconstruction was created at 60 s/bed based on prior literature. Qualitative (Likert scores) and quantitative (standardized uptake value [SUV]) analyses were performed to evaluate image quality and quantitation across simulated reconstructions. RESULTS: The mean patient age was 9.0 ± 5.5 (SD) years, mean weight was 38.5 ± 24.5 kg, and mean administered 18F-FDG activity was 4.5 ± 0.7 (SD) MBq/kg. Between BSREM reconstructions, no qualitative measure showed a significant difference versus the 90 s/bed ß=700 standard (all P>0.05). SUVmax values for lesions were significantly lower from 90 s/bed, ß=700 only at a simulated acquisition time of 30 s/bed, ß=1300 (P=0.001). In a side-by-side comparison of BSREM versus OSEM reconstructions, 40 s/bed, ß=1000 images were generally preferred over 60 s/bed TOF OSEM images. CONCLUSION: In children who undergo whole-body 18F-FDG PET/CT on a 25-cm FOV digital PET/CT scanner, reductions in acquisition time or, by corollary, administered radiopharmaceutical activity of >50% from a clinical standard of 90 s/bed may be possible while maintaining diagnostic quality when a BSREM reconstruction algorithm is used.

Implementation of AI image reconstruction in CT-how is it validated and what dose reductions can be achieved.

CT reconstruction has undergone a substantial change over the last decade with the introduction of iterative reconstruction (IR) and now with deep learning reconstruction (DLR). In this review, DLR will be compared to IR and filtered back-projection (FBP) reconstructions. Comparisons will be made using image quality metrics such as noise power spectrum, contrast-dependent task-based transfer function, and non-prewhitening filter detectability index (dNPW'). Discussion on how DLR has impacted CT image quality, low-contrast detectability, and diagnostic confidence will be provided. DLR has shown the ability to improve in areas that IR is lacking, namely: noise magnitude reduction does not alter noise texture to the degree that IR did, and the noise texture found in DLR is more aligned with noise texture of an FBP reconstruction. Additionally, the dose reduction potential for DLR is shown to be greater than IR. For IR, the consensus was dose reduction should be limited to no more than 15-30% to preserve low-contrast detectability. For DLR, initial phantom and patient observer studies have shown acceptable dose reduction between 44 and 83% for both low- and high-contrast object detectability tasks. Ultimately, DLR is able to be used for CT reconstruction in place of IR, making it an easy "turnkey" upgrade for CT reconstruction. DLR for CT is actively being improved as more vendor options are being developed and current DLR options are being enhanced with second generation algorithms being released. DLR is still in its developmental early stages, but is shown to be a promising future for CT reconstruction.

Opposing effects of KDM6A and JDP2 on glucocorticoid sensitivity in T-ALL.

Glucocorticoids (GCs) are the cornerstone of acute lymphoblastic leukemia (ALL) therapy. Although mutations in NR3C1, which encodes the GC receptor (GR), and other genes involved in GC signaling occur at relapse, additional mechanisms of adaptive GC resistance are uncertain. We transplanted and treated 10 primary mouse T-lineage acute lymphoblastic leukemias (T-ALLs) initiated by retroviral insertional mutagenesis with GC dexamethasone (DEX). Multiple distinct relapsed clones from 1 such leukemia (T-ALL 8633) exhibited discrete retroviral integrations that upregulated Jdp2 expression. This leukemia harbored a Kdm6a mutation. In the human T-ALL cell line CCRF-CEM, enforced JDP2 overexpression conferred GC resistance, whereas KDM6A inactivation unexpectedly enhanced GC sensitivity. In the context of KDM6A knockout, JDP2 overexpression induced profound GC resistance, counteracting the sensitization conferred by KDM6A loss. These resistant "double mutant" cells with combined KDM6A loss and JDP2 overexpression exhibited decreased NR3C1 mRNA and GR protein upregulation upon DEX exposure. Analysis of paired samples from 2 patients with KDM6A-mutant T-ALL in a relapsed pediatric ALL cohort revealed a somatic NR3C1 mutation at relapse in 1 patient and a markedly elevated JDP2 expression in the other. Together, these data implicate JDP2 overexpression as a mechanism of adaptive GC resistance in T-ALL, which functionally interacts with KDM6A inactivation.

Computed tomography-based measurements of normative liver and spleen volumes in children.

BACKGROUND: Quantification of organ size has utility in clinical care and research for diagnostics, prognostics and surgical planning. Volumetry is regarded as the best measure of organ size and change in size over time. Scarce reference values exist for liver and spleen volumes in healthy children. OBJECTIVE: To report liver and spleen volumes for a sample of children defined by manual segmentation of contrast-enhanced CT images with the goal of defining normal values and thresholds that might indicate disease. MATERIALS AND METHODS: This retrospective study included clinically acquired contrast-enhanced CTs of the abdomen/pelvis for children and adolescents imaged between January 2018 and July 2021. Liver and spleen volumes were derived through manual segmentation of CTs reconstructed at 2.5-, 3- or 5-mm slice thickness. A subset of images (5%, n=16) was also segmented using 0.5-mm slice thickness reconstructions to define agreement based on image slice thickness. We used Pearson correlation and multivariable regression to assess associations between organ volumes and patient characteristics. We generated reference intervals for the 5th, 25th, 50th (median), 75th and 95th percentiles for organ volumes as a function of age and weight using quantile regression models. Finally, we calculated Bland-Altman plots and intraclass correlation coefficients (ICC) to quantify agreement. RESULTS: We included a total of 320 children (mean age ± standard deviation [SD] = 9±4.6 years; mean weight 38.1±18.8 kg; 160 female). Liver volume ranged from 340-2,002 mL, and spleen volume ranged from 28-480 mL. Patient weight (kg) (ß=12.5), age (months) (ß=1.7) and sex (female) (ß = -35.3) were independent predictors of liver volume, whereas patient weight (kg) (ß=2.4) and age (months) (ß=0.3) were independent predictors of spleen volume. There was excellent absolute agreement (ICC=0.99) and minimal absolute difference (4 mL) in organ volumes based on reconstructed slice thickness. CONCLUSION: We report reference liver and spleen volumes for children without liver or spleen disease. These results provide reference ranges and potential thresholds to identify liver and spleen size abnormalities that might reflect disease in children.

Uncovering novel mutational signatures by de novo extraction with SigProfilerExtractor.

Mutational signature analysis is commonly performed in cancer genomic studies. Here, we present SigProfilerExtractor, an automated tool for de novo extraction of mutational signatures, and benchmark it against another 13 bioinformatics tools by using 34 scenarios encompassing 2,500 simulated signatures found in 60,000 synthetic genomes and 20,000 synthetic exomes. For simulations with 5% noise, reflecting high-quality datasets, SigProfilerExtractor outperforms other approaches by elucidating between 20% and 50% more true-positive signatures while yielding 5-fold less false-positive signatures. Applying SigProfilerExtractor to 4,643 whole-genome- and 19,184 whole-exome-sequenced cancers reveals four novel signatures. Two of the signatures are confirmed in independent cohorts, and one of these signatures is associated with tobacco smoking. In summary, this report provides a reference tool for analysis of mutational signatures, a comprehensive benchmarking of bioinformatics tools for extracting signatures, and several novel mutational signatures, including one putatively attributed to direct tobacco smoking mutagenesis in bladder tissues.

The genomic landscape of pediatric acute lymphoblastic leukemia.

Acute lymphoblastic leukemia (ALL) is the most common childhood cancer. Here, using whole-genome, exome and transcriptome sequencing of 2,754 childhood patients with ALL, we find that, despite a generally low mutation burden, ALL cases harbor a median of four putative somatic driver alterations per sample, with 376 putative driver genes identified varying in prevalence across ALL subtypes. Most samples harbor at least one rare gene alteration, including 70 putative cancer driver genes associated with ubiquitination, SUMOylation, noncoding transcripts and other functions. In hyperdiploid B-ALL, chromosomal gains are acquired early and synchronously before ultraviolet-induced mutation. By contrast, ultraviolet-induced mutations precede chromosomal gains in B-ALL cases with intrachromosomal amplification of chromosome 21. We also demonstrate the prognostic significance of genetic alterations within subtypes. Intriguingly, DUX4- and KMT2A-rearranged subtypes separate into CEBPA/FLT3- or NFATC4-expressing subgroups with potential clinical implications. Together, these results deepen understanding of the ALL genomic landscape and associated outcomes.

Reducing Pediatric Intraoral Radiography Radiation Dose Using Reduced-Power Dental X-Ray Units: A Randomized Trial.

Purpose: To assess the diagnostic confidence of intraoral radiographic image quality while reducing the pediatric patient's radiation exposure using a longer position indicating device (PID), additional X-ray beam filtration and rectangular collimation while using modern, lower-power intraoral dental X-ray units.
Methods: A randomized prospective study scored bitewing intraoral dental images based on relevant clinical features. Observer studies with pediatric dentists and dental residents were conducted to verify whether diagnostic confidence remained unchanged after dose reduction modifications. The study involved a two-phase investigation to determine: (1) the best thickness of aluminum (Al) 2024-T3 alloy filter and (2) required increased exposure time to maintain intraoral radiographic image quality. A 30 cm PID with a rectangular collimator was used to further manage patient dose. For each phase, images from 125 patients were collected from February 2017 to September 2018 and analyzed.
Results: The results from the observer study using a 30 cm PID, 1.02 mm thick Al alloy filter, and a rectangular collimator resulted in a patient dose reduction between 64 percent (exposure time of 400 msec) to 77 percent (250 msec), without any statis- tically significant effect to the diagnostic confidence of the observers in evaluating the reduced radiation images.
Conclusion: Long recognized dose reduction methods, when implemented on a modern, low-power intraoral dental X-ray unit, do not impact confidence in bite- wing diagnostic images, but substantially reduce patient dose and should be adopted to increase patient safety, especially for children.

Application of reference air kerma alert levels for pediatric fluoroscopic examinations.

The purpose of this study was to provide an empirical model to develop reference air kerma (RAK) alert levels as a function of patient thickness or age for pediatric fluoroscopy for any institution to use in a Quality Assurance program. RAK and patient thickness were collected for 10&663 general fluoroscopic examinations and 1500 fluoroscopically guided interventions (FGIs). RAK and patient age were collected for 6137 fluoroscopic examinations with mobile-C-arms (MC). Coefficients of linear regression fits of logarithmic RAK as a function of patient thickness or age were generated for each fluoroscopy group. Regression fits of RAK for 50%, 90%, and 98% upper prediction levels were used as inputs to derive an empirical formula to estimate alert levels as a function of patient thickness. A methodology is presented to scale results from this study for any patient thickness or age for any institution, for example, the patient thickness dependent RAK alert level at the top 1% of expected RAK can be set using the 98% upper prediction interval boundary given by: RAK 98 % = e m . x avg + s 98 . c ̂ ${\rm{RAK}}_{98\% } = {e}^{m.{x}_{{\rm{avg}}} + {s}_{98}.\hat{c}}\ $ , where xavg is the institute's average patient thickness or age, and c ̂ $\hat{c}$ is the intercept based on the average RAK of the patient population calculated as c ̂ = ln ( RAK avg ) - m . x avg . RA K avg $\hat{c} = \ln ( {{\rm{RAK}}_{{\rm{avg}}}} )\ - m.{x}_{{\rm{avg}}}{\rm{.RA}}{{\rm{K}}}_{{\rm{avg}}}$ is the institution's average RAK (mGy). m and s98 are constants presented for each type of fluoroscope and RAK group and represent slope of the fit and scale factor, respectively. An empirical equation, which estimates alert levels expressed as air Kerma without backscatter at the interventional reference point as a function of patient thickness or age is provided for each fluoroscopic examination type. The empirical equations allow any facility with limited data to scale the results of this study's single facility data to model their practice's unique RAK alert levels and patient population demographics to establish pediatric alert levels for fluoroscopic procedures.

Convergent evolution and multi-wave clonal invasion in H3 K27-altered diffuse midline gliomas treated with a PDGFR inhibitor.

The majority of diffuse midline gliomas, H3 K27-altered (DMG-H3 K27-a), are infiltrating pediatric brain tumors that arise in the pons with no effective treatment. To understand how clonal evolution contributes to the tumor's invasive spread, we performed exome sequencing and SNP array profiling on 49 multi-region autopsy samples from 11 patients with pontine DMG-H3 K27-a enrolled in a phase I clinical trial of PDGFR inhibitor crenolanib. For each patient, a phylogenetic tree was constructed by testing multiple possible clonal evolution models to select the one consistent with somatic mutations and copy number variations across all tumor regions. The tree was then used to deconvolute subclonal composition and prevalence at each tumor region to study convergent evolution and invasion patterns. Somatic variants in the PI3K pathway, a late event, are enriched in our cohort, affecting 70% of patients. Convergent evolution of PI3K at distinct phylogenetic branches was detected in 40% of the patients. 24 (~ 50%) of tumor regions were occupied by subclones of mixed lineages with varying molecular ages, indicating multiple waves of invasion across the pons and extrapontine. Subclones harboring a PDGFRA amplicon, including one that amplified a PDGRFAY849C mutant allele, were detected in four patients; their presence in extrapontine tumor and normal brain samples imply their involvement in extrapontine invasion. Our study expands the current knowledge on tumor invasion patterns in DMG-H3 K27-a, which may inform the design of future clinical trials.

Simulated Reduced-Count Whole-Body FDG PET: Evaluation in Children and Young Adults Imaged on a Digital PET Scanner.

BACKGROUND. Digital PET scanners with increased sensitivity may allow shorter scan acquisition times or reductions in administered radiopharmaceutical activities. OBJECTIVE. The purpose of this study was to evaluate in children and young adults the impact of shorter simulated acquisition times on the quality of whole-body FDG PET images obtained using a digital PET/CT system. METHODS. This retrospective study included 27 children and young adults (nine male and 18 female patients) who underwent clinically indicated whole-body FDG PET/CT examinations performed using a 25-cm axial FOV PET/CT system at 90 s per bed position (expressed hereafter as seconds per bed). Raw list-mode data were reprocessed to simulate acquisition times of 60, 55, 50, 45, 40, and 30 s/bed. Three radiologists independently reviewed reconstructed images and assigned Likert scores for lesion conspicuity, normal structure conspicuity, image quality, and image noise. A separate observer recorded the SUVmax, SUVmean, and SD of the SUV (SUVSD) for liver, thigh, and the most FDG-avid lesion. The SUVSD/SUVmean (the SUVSD divided by the SUVmean) was calculated as a surrogate of image noise. ANOVA, the Friedman test, and the Dunn test were used to compare qualitative measures (combining reader scores) and SUV measurements. RESULTS. The mean patient age was 10.8 ± 8.3 (SD) years, mean BMI was 18.7 ± 2.9, and mean administered FDG activity was 4.44 ± 0.37 MBq/kg (0.12 ± 0.01 mCi/kg). No qualitative measure showed a significant difference versus 90 s/bed for the simulated acquisition at 60 s/bed (all p > .05). Significant differences (all p < .05) versus 90 s/bed were observed for lesion conspicuity at at most 40 s/bed, conspicuity of normal structures and overall image quality at at most 45 s/bed, and image noise at at most 55 s/bed. SUVmean was not significantly different from 90 s/bed for any site for any reduced-count simulation (all p > .05). SUVSD/SUVmean and SUVmax showed gradual increases with decreasing acquisition times and were significantly different from 90 s/bed only for liver at 60 s/bed (for SUVmax: 1.00 ± 0.00 vs 1.05 ± 0.03, p = .02; for SUVSD/SUVmean: 0.09 ± 0.02 vs 0.11 ± 0.02, p = .04). CONCLUSION. Favorable findings for the simulated acquisition at 60 s/bed suggest that, in children and young adults who undergo imaging performed using a 25-cm FOV digital PET scanner, acquisition time or administered FDG activity may be decreased by approximately 33% from the clinical standard without significantly impacting image quality. CLINICAL IMPACT. A 25-cm axial FOV digital scanner may allow FDG PET/CT examinations to be performed with reduced radiation exposure or faster scan acquisition times.

Defining Normal Ranges of Skeletal Muscle Area and Skeletal Muscle Index in Children on CT Using an Automated Deep Learning Pipeline: Implications for Sarcopenia Diagnosis.

BACKGROUND. Skeletal muscle area (SMA), representing skeletal muscle cross-sectional area at the L3 vertebral level, and skeletal muscle index (SMI), representing height-normalized SMA, can serve as markers of sarcopenia. Normal SMA and SMI values have been reported primarily in adults. OBJECTIVE. The purpose of this study was to use an automated deep learning (DL) pipeline for muscle segmentation on abdominal CT to define normative age- and sex-based values for pediatric muscle cross-sectional area as a guide for diagnosis of sarcopenia in children. METHODS. This retrospective study reviewed records of patients who underwent abdominal CT at Cincinnati Children's Hospital Medical Center from January 1, 2009, to January 3, 2019. Patients were excluded on the basis of age outside of the eligible range (2.00-18.99 years), body mass index (BMI) outside of 5-95% age-based percentiles using CDC and WHO growth charts, known medical condition, medication use, support devices, surgery, or missing axial images at the L3 level. A previously validated automated DL pipeline was used to identify an axial slice at L3 and segment skeletal muscle to generate SMA and SMI. Pearson correlation coefficients were computed. Quantile regression analysis was used to plot SMA and SMI as functions of age and sex and to determine age- and sex-based percentile values. RESULTS. Of 8817 patients who underwent abdominal CT during the study period, 2168 (mean age, 12.3 ± 4.3 [SD] years; 1125 female patients, 1043 male patients) met inclusion criteria. Mean BMI-for-age percentile based on CDC and WHO growth charts was 64.8% ± 25.3% for female patients and 61.4% ± 25.8% for male patients. SMA showed strong correlation with weight, height, age, and BMI for male (0.79-0.94) and female (0.75-0.90) patients; SMI showed weak-to-moderate correlation with weight, height, age, and BMI for male (0.25-0.57) and female (0-0.43) patients. Normal SMA and SMI ranges for age and sex were expressed as curves and as a lookup table, identifying 54 male and 59 female patients with muscle measurements below the 5th percentile regression curve. CONCLUSION. By using an automated DL pipeline in a large sample of carefully selected children, normal ranges for SMA and SMI were calculated as functions of age and sex. CLINICAL IMPACT. The normative values should aid the diagnosis of sarcopenia in children.

Enhancer retargeting of CDX2 and UBTF::ATXN7L3 define a subtype of high-risk B-progenitor acute lymphoblastic leukemia.

Transcriptome sequencing has identified multiple subtypes of B-progenitor acute lymphoblastic leukemia (B-ALL) of prognostic significance, but a minority of cases lack a known genetic driver. Here, we used integrated whole-genome (WGS) and -transcriptome sequencing (RNA-seq), enhancer mapping, and chromatin topology analysis to identify previously unrecognized genomic drivers in B-ALL. Newly diagnosed (n = 3221) and relapsed (n = 177) B-ALL cases with tumor RNA-seq were studied. WGS was performed to detect mutations, structural variants, and copy number alterations. Integrated analysis of histone 3 lysine 27 acetylation and chromatin looping was performed using HiChIP. We identified a subset of 17 newly diagnosed and 5 relapsed B-ALL cases with a distinct gene expression profile and 2 universal and unique genomic alterations resulting from aberrant recombination-activating gene activation: a focal deletion downstream of PAN3 at 13q12.2 resulting in CDX2 deregulation by the PAN3 enhancer and a focal deletion of exons 18-21 of UBTF at 17q21.31 resulting in a chimeric fusion, UBTF::ATXN7L3. A subset of cases also had rearrangement and increased expression of the PAX5 gene, which is otherwise uncommon in B-ALL. Patients were more commonly female and young adult with median age 35 (range,12-70 years). The immunophenotype was characterized by CD10 negativity and immunoglobulin M positivity. Among 16 patients with known clinical response, 9 (56.3%) had high-risk features including relapse (n = 4) or minimal residual disease >1% at the end of remission induction (n = 5). CDX2-deregulated, UBTF::ATXN7L3 rearranged (CDX2/UBTF) B-ALL is a high-risk subtype of leukemia in young adults for which novel therapeutic approaches are required.

Current and emerging artificial intelligence applications for pediatric abdominal imaging.

Artificial intelligence (AI) uses computers to mimic cognitive functions of the human brain, allowing inferences to be made from generally large datasets. Traditional machine learning (e.g., decision tree analysis, support vector machines) and deep learning (e.g., convolutional neural networks) are two commonly employed AI approaches both outside and within the field of medicine. Such techniques can be used to evaluate medical images for the purposes of automated detection and segmentation, classification tasks (including diagnosis, lesion or tissue characterization, and prediction), and image reconstruction. In this review article we highlight recent literature describing current and emerging AI methods applied to abdominal imaging (e.g., CT, MRI and US) and suggest potential future applications of AI in the pediatric population.

Detection of urinary tract calculi on CT images reconstructed with deep learning algorithms.

BACKGROUND: Deep learning Computed Tomography (CT) reconstruction (DLR) algorithms promise to improve image quality but the impact on clinical diagnostic performance remains to be demonstrated. We aimed to compare DLR to standard iterative reconstruction for detection of urolithiasis by unenhanced CT in children and young adults. METHODS: This was an IRB approved retrospective study involving post-hoc reconstruction of clinically acquired unenhanced abdomen/pelvis CT scans. Images were reconstructed with six different manufacturer-standard DLR algorithms and reformatted in 3 planes (axial, sagittal, and coronal) at 3 mm intervals. De-identified reconstructions were loaded as independent examinations for review by 3 blinded radiologists (R1, R2, R3) tasked with identifying and measuring all stones. Results were compared to the clinical iterative reconstruction images as a reference standard. IntraClass correlation coefficients and kappa (k) statistics were used to quantify agreement. RESULTS: CT data for 14 patients (mean age: 17.3 ± 3.4 years, 5 males and 9 females, weight class: 31-70 kg (n = 6), 71-100 kg (n = 7), > 100 kg (n = 1)) were reconstructed into 84 total exams. 7 patients had urinary tract calculi. Interobserver agreement on the presence of any urinary tract calculus was substantial to almost perfect (k = 0.71-1) for all DLR algorithms. Agreement with the reference standard on number of calculi was excellent (ICC = 0.78-0.96) and agreement on the size of the largest calculus was fair to excellent (ICC = 0.51-0.97) depending on reviewer and DLR algorithm. CONCLUSION: Deep learning reconstruction of unenhanced CT images allows similar renal stone detectability compared to iterative reconstruction.

Therapeutic and prognostic insights from the analysis of cancer mutational signatures.

The somatic mutations in each cancer genome are caused by multiple mutational processes, each of which leaves a characteristic imprint (or 'signature'), potentially caused by specific etiologies or exposures. Deconvolution of these signatures offers a glimpse into the evolutionary history of individual tumors. Recent work has shown that mutational signatures may also yield therapeutic and prognostic insights, including the identification of cell-intrinsic signatures as biomarkers of drug response and prognosis. For example, mutational signatures indicating homologous recombination deficiency are associated with poly(ADP)-ribose polymerase (PARP) inhibitor sensitivity, whereas APOBEC-associated signatures are associated with ataxia telangiectasia and Rad3-related kinase (ATR) inhibitor sensitivity. Furthermore, therapy-induced mutational signatures implicated in cancer progression have also been uncovered, including the identification of thiopurine-induced TP53 mutations in leukemia. In this review, we explore the various ways mutational signatures can reveal new therapeutic and prognostic insights, thus extending their traditional role in identifying disease etiology.

The landscape of coding RNA editing events in pediatric cancer.

BACKGROUND: RNA editing leads to post-transcriptional variation in protein sequences and has important biological implications. We sought to elucidate the landscape of RNA editing events across pediatric cancers. METHODS: Using RNA-Seq data mapped by a pipeline designed to minimize mapping ambiguity, we investigated RNA editing in 711 pediatric cancers from the St. Jude/Washington University Pediatric Cancer Genome Project focusing on coding variants which can potentially increase protein sequence diversity. We combined de novo detection using paired tumor DNA-RNA data with analysis of known RNA editing sites. RESULTS: We identified 722 unique RNA editing sites in coding regions across pediatric cancers, 70% of which were nonsynonymous recoding variants. Nearly all editing sites represented the canonical A-to-I (n = 706) or C-to-U sites (n = 14). RNA editing was enriched in brain tumors compared to other cancers, including editing of glutamate receptors and ion channels involved in neurotransmitter signaling. RNA editing profiles of each pediatric cancer subtype resembled those of the corresponding normal tissue profiled by the Genotype-Tissue Expression (GTEx) project. CONCLUSIONS: In this first comprehensive analysis of RNA editing events in pediatric cancer, we found that the RNA editing profile of each cancer subtype is similar to its normal tissue of origin. Tumor-specific RNA editing events were not identified indicating that successful immunotherapeutic targeting of RNA-edited peptides in pediatric cancer should rely on increased antigen presentation on tumor cells compared to normal but not on tumor-specific RNA editing per se.

The chemotherapeutic CX-5461 primarily targets TOP2B and exhibits selective activity in high-risk neuroblastoma.

Survival in high-risk pediatric neuroblastoma has remained around 50% for the last 20 years, with immunotherapies and targeted therapies having had minimal impact. Here, we identify the small molecule CX-5461 as selectively cytotoxic to high-risk neuroblastoma and synergistic with low picomolar concentrations of topoisomerase I inhibitors in improving survival in vivo in orthotopic patient-derived xenograft neuroblastoma mouse models. CX-5461 recently progressed through phase I clinical trial as a first-in-human inhibitor of RNA-POL I. However, we also use a comprehensive panel of in vitro and in vivo assays to demonstrate that CX-5461 has been mischaracterized and that its primary target at pharmacologically relevant concentrations, is in fact topoisomerase II beta (TOP2B), not RNA-POL I. This is important because existing clinically approved chemotherapeutics have well-documented off-target interactions with TOP2B, which have previously been shown to cause both therapy-induced leukemia and cardiotoxicity-often-fatal adverse events, which can emerge several years after treatment. Thus, while we show that combination therapies involving CX-5461 have promising anti-tumor activity in vivo in neuroblastoma, our identification of TOP2B as the primary target of CX-5461 indicates unexpected safety concerns that should be examined in ongoing phase II clinical trials in adult patients before pursuing clinical studies in children.

Novel temporal and spatial patterns of metastatic colonization from breast cancer rapid-autopsy tumor biopsies.

BACKGROUND: Metastatic breast cancer is a deadly disease with a low 5-year survival rate. Tracking metastatic spread in living patients is difficult and thus poorly understood. METHODS: Via rapid autopsy, we have collected 30 tumor samples over 3 timepoints and across 8 organs from a triple-negative metastatic breast cancer patient. The large number of sites sampled, together with deep whole-genome sequencing and advanced computational analysis, allowed us to comprehensively reconstruct the tumor's evolution at subclonal resolution. RESULTS: The most unique, previously unreported aspect of the tumor's evolution that we observed in this patient was the presence of "subclone incubators," defined as metastatic sites where substantial tumor evolution occurs before colonization of additional sites and organs by subclones that initially evolved at the incubator site. Overall, we identified four discrete waves of metastatic expansions, each of which resulted in a number of new, genetically similar metastasis sites that also enriched for particular organs (e.g., abdominal vs bone and brain). The lung played a critical role in facilitating metastatic spread in this patient: the lung was the first site of metastatic escape from the primary breast lesion, subclones at this site were likely the source of all four subsequent metastatic waves, and multiple sites in the lung acted as subclone incubators. Finally, functional annotation revealed that many known drivers or metastasis-promoting tumor mutations in this patient were shared by some, but not all metastatic sites, highlighting the need for more comprehensive surveys of a patient's metastases for effective clinical intervention. CONCLUSIONS: Our analysis revealed the presence of substantial tumor evolution at metastatic incubator sites in a patient, with potentially important clinical implications. Our study demonstrated that sampling of a large number of metastatic sites affords unprecedented detail for studying metastatic evolution.