Diagnostic Imaging for Retinoblastoma Cancer Staging: Guide for Providing Essential Insights for Ophthalmologists and Oncologists.

Retinoblastoma is the most common cause of all intraocular pediatric malignancies. It is caused by the loss of RB1 tumor suppressor gene function, although some tumors occur due to MYCN oncogene amplification with normal RB1 genes. Nearly half of all retinoblastomas occur due to a hereditary germline RB1 pathogenic variant, most of which manifest with bilateral tumors. This germline RB1 mutation also predisposes to intracranial midline embryonal tumors. Accurate staging of retinoblastoma is crucial in providing optimal vision-, eye-, and life-saving treatment. The AJCC Cancer Staging Manual has undergone significant changes, resulting in a universally accepted system with a multidisciplinary approach for managing retinoblastoma. The authors discuss the role of MRI and other diagnostic imaging techniques in the pretreatment assessment and staging of retinoblastoma. A thorough overview of the prevailing imaging standards and evidence-based perspectives on the benefits and drawbacks of these techniques is provided. Published under a CC BY 4.0 license. Test Your Knowledge questions for this article are available in the supplemental material.

Correlative Assessment of Machine Learning-Based Cobb Angle Measurements and Human-Based Measurements in Adolescent Idiopathic and Congenital Scoliosis.

Purpose: Scoliosis is a complex spine deformity with direct functional and cosmetic impacts on the individual. The reference standard for assessing scoliosis severity is the Cobb angle which is measured on radiographs by human specialists, carrying interobserver variability and inaccuracy of measurements. These limitations may result in lack of timely referral for management at a time the scoliotic deformity progression can be saved from surgery. We aimed to create a machine learning (ML) model for automatic calculation of Cobb angles on 3-foot standing spine radiographs of children and adolescents with clinical suspicion of scoliosis across 2 clinical scenarios (idiopathic, group 1 and congenital scoliosis, group 2). Methods: We retrospectively measured Cobb angles of 130 patients who had a 3-foot spine radiograph for scoliosis within a 10-year period for either idiopathic or congenital anomaly scoliosis. Cobb angles were measured both manually by radiologists and by an ML pipeline (segmentation-based approach-Augmented U-Net model with non-square kernels). Results: Our Augmented U-Net architecture achieved a Symmetric Mean Absolute Percentage Error (SMAPE) of 11.82% amongst a combined idiopathic and congenital scoliosis cohort. When stratifying for idiopathic and congenital scoliosis individually a SMAPE of 13.02% and 11.90% were achieved, respectively. Conclusion: The ML model used in this study is promising at providing automated Cobb angle measurement in both idiopathic scoliosis and congenital scoliosis. Nevertheless, larger studies are needed in the future to confirm the results of this study prior to translation of this ML algorithm into clinical practice.

The development of the pediatric stroke neuroimaging platform (PEDSNIP).

Childhood stroke occurs from birth to 18 years of age, ranks among the top ten childhood causes of death, and leaves lifelong neurological impairments. Arterial ischemic stroke in infancy and childhood occurs due to arterial occlusion in the brain, resulting in a focal lesion. Our understanding of mechanisms of injury and repair associated with focal injury in the developing brain remains rudimentary. Neuroimaging can reveal important insights into these mechanisms. In adult stroke population, multi-center neuroimaging studies are common and have accelerated the translation process leading to improvements in treatment and outcome. These studies are centered on the growing evidence that neuroimaging measures and other biomarkers (e.g., from blood and cerebrospinal fluid) can enhance our understanding of mechanisms of risk and injury and be used as complementary outcome markers. These factors have yet to be studied in pediatric stroke because most neuroimaging studies in this population have been conducted in single-centred, small cohorts. By pooling neuroimaging data across multiple sites, larger cohorts of patients can significantly boost study feasibility and power in elucidating mechanisms of brain injury, repair and outcomes. These aims are particularly relevant in pediatric stroke because of the decreased incidence rates and the lack of mechanism-targeted trials. Toward these aims, we developed the Pediatric Stroke Neuroimaging Platform (PEDSNIP) in 2015, funded by The Brain Canada Platform Support Grant, to focus on three identified neuroimaging priorities. These were: developing and harmonizing multisite clinical protocols, creating the infrastructure and methods to import, store and organize the large clinical neuroimaging dataset from multiple sites through the International Pediatric Stroke Study (IPSS), and enabling central searchability. To do this, developed a two-pronged approach that included building 1) A Clinical-MRI Data Repository (standard of care imaging) linked to clinical data and longitudinal outcomes and 2) A Research-MRI neuroimaging data set acquired through our extensive collaborative, multi-center, multidisciplinary network. This dataset was collected prospectively in eight North American centers to test the feasibility and implementation of harmonized advanced Research-MRI, with the addition of clinical information, genetic and proteomic studies, in a cohort of children presenting with acute ischemic stroke. Here we describe the process that enabled the development of PEDSNIP built to provide the infrastructure to support neuroimaging research priorities in pediatric stroke. Having built this Platform, we are now able to utilize the largest neuroimaging and clinical data pool on pediatric stroke data worldwide to conduct hypothesis-driven research. We are actively working on a bioinformatics approach to develop predictive models of risk, injury and repair and accelerate breakthrough discoveries leading to mechanism-targeted treatments that improve outcomes and minimize the burden following childhood stroke. This unique transformational resource for scientists and researchers has the potential to result in a paradigm shift in the management, outcomes and quality of life in children with stroke and their families, with far-reaching benefits for other brain conditions of people across the lifespan.

Imaging of Abusive Head Trauma in Children.

In this article, we describe relevant anatomy, mechanisms of injury, and imaging findings of abusive head trauma (AHT). We also briefly address certain mimics of AHT, controversies, pearls, and pitfalls. Concepts of injury, its evolution, and complex nature of certain cases are highlighted with the help of case vignettes.

Automated Adolescence Scoliosis Detection Using Augmented U-Net With Non-square Kernels.

Purpose: Scoliosis is a deformity of the spine, and as a measure of scoliosis severity, Cobb angle is fundamental to the diagnosis of deformities that require treatment. Conventional Cobb angle measurement and assessment is usually done manually, which is inherently time-consuming, and associated with high inter- and intra-observer variability. While there exist automatic scoliosis measurement methods, they suffer from insufficient accuracy. In this work, we propose a two-step segmentation-based deep learning architecture to automate Cobb angle measurement for scoliosis assessment using X-Ray images. Methods: The proposed architecture involves two steps. In the first step, we utilize a novel Augmented U-Net architecture to generate segmentations of vertebrae. The second step includes a non-learning-based pipeline to extract landmark coordinates from the segmented vertebrae and filter undesirable landmarks. Results: Our proposed Augmented U-Net architecture achieved a Symmetric Mean Absolute Percentage Error of 9.2%, with approximately 90% of estimations having less than 10 degrees difference compared with the AASCE-MICCAI challenge 2019 dataset ground truths. We further validated the model using an internal dataset and achieved almost the same level of performance. Conclusion: The proposed architecture is robust in providing automated spinal vertebrae segmentations and Cobb angle measurement, and is potentially generalizable to real-world clinical settings.

Infection and inflammation: radiological insights into patterns of pediatric immune-mediated CNS injury.

The central nervous system (CNS) undergoes constant immune surveillance enabled via regionally specialized mechanisms. These include selectively permissive barriers and modifications to interlinked innate and adaptive immune systems that detect and remove an inciting trigger. The end-points of brain injury and edema from these triggers are varied but often follow recognizable patterns due to shared underlying immune drivers. Imaging provides insights to understanding these patterns that often arise from unique interplays of infection, inflammation and genetics. We review the current updates in our understanding of these intersections and through examples of cases from our practice, highlight that infection and inflammation follow diverse yet convergent mechanisms that can challenge the CNS in children.

Radiomic Features Based on MRI Predict Progression-Free Survival in Pediatric Diffuse Midline Glioma/Diffuse Intrinsic Pontine Glioma.

Purpose: Biopsy-based assessment of H3 K27 M status helps in predicting survival, but biopsy is usually limited to unusual presentations and clinical trials. We aimed to evaluate whether radiomics can serve as prognostic marker to stratify diffuse intrinsic pontine glioma (DIPG) subsets. Methods: In this retrospective study, diagnostic brain MRIs of children with DIPG were analyzed. Radiomic features were extracted from tumor segmentations and data were split into training/testing sets (80:20). A conditional survival forest model was applied to predict progression-free survival (PFS) using training data. The trained model was validated on the test data, and concordances were calculated for PFS. Experiments were repeated 100 times using randomized versions of the respective percentage of the training/test data. Results: A total of 89 patients were identified (48 females, 53.9%). Median age at time of diagnosis was 6.64 years (range: 1-16.9 years) and median PFS was 8 months (range: 1-84 months). Molecular data were available for 26 patients (29.2%) (1 wild type, 3 K27M-H3.1, 22 K27M-H3.3). Radiomic features of FLAIR and nonenhanced T1-weighted sequences were predictive of PFS. The best FLAIR radiomics model yielded a concordance of .87 [95% CI: .86-.88] at 4 months PFS. The best T1-weighted radiomics model yielded a concordance of .82 [95% CI: .8-.84] at 4 months PFS. The best combined FLAIR + T1-weighted radiomics model yielded a concordance of .74 [95% CI: .71-.77] at 3 months PFS. The predominant predictive radiomic feature matrix was gray-level size-zone. Conclusion: MRI-based radiomics may predict progression-free survival in pediatric diffuse midline glioma/diffuse intrinsic pontine glioma.

Congenital midline spinal hamartoma in an infant with DICER1 syndrome: A case report.

Congenital spinal hamartomas are rare benign tumors. They are mostly seen in infants and are typically asymptomatic at presentation. Spinal hamartomas have not been associated with any known cancer predisposition syndrome. DICER1 syndrome is a well-characterized cancer predisposition syndrome caused by a germline mutation in the DICER1 gene, which shows variable expressivity. To our knowledge, spinal hamartoma has never been described in individuals with DICER1 syndrome. Here, we describe a rare association of congenital spinal hamartoma and DICER1 syndrome in a 5-week-old infant, with molecular findings suggestive of the implication of DICER1 in the pathogenesis of this tumor.

Cerebral White Matter Tract Anatomy.

Advances in MR imaging techniques have allowed for detailed in vivo depiction of white matter tracts. The study of white matter structure and connectivity is of paramount importance in leukodystrophies, demyelinating disorders, neoplasms, and various cognitive, neuropsychiatric, and developmental disorders. The advent of advanced "function-preserving" surgical techniques also makes it imperative to understand white matter anatomy and connectivity, to provide accurate road maps for tumor and epilepsy surgery. In this review, we will describe cerebral white matter anatomy with the help of conventional MRI and diffusion tensor imaging.

MRI based radiomics enhances prediction of neurodevelopmental outcome in very preterm neonates.

To predict adverse neurodevelopmental outcome of very preterm neonates. A total of 166 preterm neonates born between 24-32 weeks' gestation underwent brain MRI early in life. Radiomics features were extracted from T1- and T2- weighted images. Motor, cognitive, and language outcomes were assessed at a corrected age of 18 and 33 months and 4.5 years. Elastic Net was implemented to select the clinical and radiomic features that best predicted outcome. The area under the receiver operating characteristic (AUROC) curve was used to determine the predictive ability of each feature set. Clinical variables predicted cognitive outcome at 18 months with AUROC 0.76 and motor outcome at 4.5 years with AUROC 0.78. T1-radiomics features showed better prediction than T2-radiomics on the total motor outcome at 18 months and gross motor outcome at 33 months (AUROC: 0.81 vs 0.66 and 0.77 vs 0.7). T2-radiomics features were superior in two 4.5-year motor outcomes (AUROC: 0.78 vs 0.64 and 0.8 vs 0.57). Combining clinical parameters and radiomics features improved model performance in motor outcome at 4.5 years (AUROC: 0.84 vs 0.8). Radiomic features outperformed clinical variables for the prediction of adverse motor outcomes. Adding clinical variables to the radiomics model enhanced predictive performance.

Fronto-Parietal and White Matter Haemodynamics Predict Cognitive Outcome in Children with Moyamoya Independent of Stroke.

Moyamoya disease is a major arteriopathy characterised by progressive steno-occlusion of the arteries of the circle of Willis. Studies in adults with moyamoya suggest an association between abnormal fronto-parietal and white matter regional haemodynamics and cognitive impairments, even in the absence of focal infarction. However, these associations have not been investigated in children with moyamoya. We examined the relationship between regional haemodynamics and ratings of intellectual ability and executive function, using hypercapnic challenge blood oxygen level-dependent magnetic resonance imaging of cerebrovascular reactivity in a consecutive cohort of children with confirmed moyamoya. Thirty children were included in the final analysis (mean age: 12.55 ± 3.03 years, 17 females, 15 idiopathic moyamoya and 15 syndromic moyamoya). Frontal haemodynamics were abnormal in all regardless of stroke history and comorbidity, but occipital lobe haemodynamics were also abnormal in children with syndromic moyamoya. Executive function deficits were noted in both idiopathic and syndromic moyamoya, whereas intellectual ability was impaired in syndromic moyamoya, even in the absence of stroke. Analysis of the relative effect of regional abnormal haemodynamics on cognitive outcomes demonstrated that executive dysfunction was predominantly explained by right parietal and white matter haemodynamics independent of stroke and comorbidity, while posterior circulation haemodynamics predicted intellectual ability. These results suggest that parietal and posterior haemodynamics play a compensatory role in overcoming frontal vulnerability and cognitive impairment.

Asynchronous pineoblastoma is more likely after early diagnosis of retinoblastoma: a meta-analysis.

PURPOSE: To determine the risk of patients with an early diagnosis of heritable retinoblastoma being diagnosed with TRb (or pineoblastoma) asynchronously in a later stage and its effect on screening. METHODS: We updated the search (PubMed and Embase) for published literature as performed by our research group in 2014 and 2019. Trilateral retinoblastoma (TRb) patients were eligible for inclusion if identifiable as unique and the age at which TRb was diagnosed was available. The search yielded 97 new studies. Three new studies and eight new patients were included. Combined with 189 patients from the previous meta-analysis, the database included 197 patients. The main outcome was the percentage of asynchronous TRb in patients diagnosed before and after preset age thresholds of 6 and 12 months of age at retinoblastoma diagnosis. RESULTS: Seventy-nine per cent of patients with pineoblastoma are diagnosed with retinoblastoma before the age of 12 months. However, baseline MRI screening at time of retinoblastoma diagnosis fails to detect the later diagnosed pineal TRb in 89% of patients. We modelled that an additional MRI performed at the age of 29 months picks up 53% of pineoblastomas in an asymptomatic phase. The detection rate increased to 72%, 87% and 92%, respectively, with 2, 3 and 4 additional MRIs. CONCLUSIONS: An MRI of the brain in heritable retinoblastoma before the age of 12 months misses most pineoblastomas, while retinoblastomas are diagnosed most often before the age of 12 months. Optimally timed additional MRI scans of the brain can increase the asymptomatic detection rate of pineoblastoma.

Neuroradiological Mimics of Periventricular Leukomalacia.

AIM: Periventricular leukomalacia (PVL) is a term reserved to describe white matter injury in the premature brain. In this review article, the authors highlight the common and rare pathologies mimicking the chronic stage of PVL and propose practical clinico-radiological criteria that would aid in diagnosis and management. METHODS AND RESULTS: The authors first describe the typical brain MRI (magnetic resonance imaging) features of PVL. Based on their clinical presentation, pathologic entities and their neuroimaging findings were clustered into distinct categories. Three clinical subgroups were identified: healthy children, children with stable/nonprogressive neurological disorder, and those with progressive neurological disorder. The neuroradiological discriminators are described in each subgroup with relevant differential diagnoses. The mimics were broadly classified into normal variants, acquired, and inherited disorders. CONCLUSIONS: The term "PVL" should be used appropriately as it reflects its pathomechanism. The phrase "white matter injury of prematurity" or "brain injury of prematurity" is more specific. Discrepancies in imaging and clinical presentation must be tread with caution and warrant further investigations to exclude other possibilities.

Clinical and Angioarchitectural Features of Hemorrhagic Brain Arterio-Venous Malformations in Adults and Children: Contrasts and Implications on Outcome.

BACKGROUND: Hemorrhage from brain arteriovenous malformations (bAVMs) is estimated at 3% per annum. Features influencing risk of hemorrhage include perforator/posterior circulation supply, associated aneurysms, and deep drainage. Children are more likely to present with bAVM bleeds. OBJECTIVE: To analyze differences in bAVM angioarchitecture between children and adults and describe predictors of poor outcome. METHODS: Data were collected from adult and pediatric tertiary referral hospitals. Demographic data, bleed location, treatment, and follow-up modified Rankin Scale (mRS) were collected. Angioarchitectural assessment included aneurysm presence, nidus morphology, perinidal angiogenesis, intranidal shunting, steal phenomenon, venous ectasia, venous stenosis, venous reflux, and pseudophlebitic pattern. Regression analyses conducted to determine predictors of mRS > 2. RESULTS: A total of 270 adult and 135 pediatric ruptured bAVMs were assessed. Median age was 42 (adults) and 10.9 (children) yr. Intranidal aneurysms were more frequent in children (P = .012), whereas prenidal aneurysms were more common in adults (P < .01). Children demonstrated more perinidal angiogenesis (P = .04), whereas steal phenomenon was commoner in adults (P < .01). Venous ectasia (P < .01), reflux (P < .01), and pseudophlebitic pattern (P = .012) were more frequent in adults. Children had better outcome (mRS score ≤ 2) (P < .01). Older age (odds ratio [OR] = 1.02), eloquent location (OR = 2.5), multicompartmental hemorrhage (OR = 1.98), venous reflux (OR = 2.5), diffuse nidus (OR = 1.83), pseudophlebitic pattern (OR = 1.96), intranidal shunts (OR = 2), and no treatment (OR = 3.68) were significant predictors of mRS > 2. CONCLUSION: Children are more likely to have intranidal aneurysms and perinidal angiogenesis, whereas adults have more prenidal aneurysms, venous ectasia, corticovenous reflux, and pseudophlebitic pattern. Eloquent location, diffuse nidus, intranidal shunts, venous reflux, and pseudophlebitic pattern predict poorer outcome.

Hemorrhagic transformation and stroke recurrence in children with cardiac disease receiving antithrombotic therapy for secondary stroke prevention.

BACKGROUND: Antithrombotic therapy is currently recommended for stroke prevention in pediatric cardioembolic stroke where the recurrence risk is high; however, safety concerns remain. The primary objective of this study was to evaluate clinical and radiographic predictors of hemorrhagic transformation and stroke recurrence in children with cardiac disease to ascertain the safety and failure rates for secondary stroke prevention. METHODS: This was a single-center, retrospective analysis of a prospectively enrolled cohort of children with radiologically confirmed cardioembolic stroke from January 2003 to December 2017 treated with institutional guidelines. RESULTS: Eighty-two children met inclusion criteria (male 44 [54%]; neonates 23 [28%]; median age 0.43 years [0.08-4.23]). Hemorrhagic transformation occurred in 20 (24%) with the majority (75% of 20) being petechial and asymptomatic. One death (1%) was reported from hemorrhagic transformation. Four children (5%) had major extracranial hemorrhage. Most (95%) received antithrombic therapy, with anticoagulation being favored (82%). Greater stroke volume was associated with hemorrhagic transformation using the pediatric Alberta Stroke Program Early CT Score (6.1 ± 3.3 vs. 3.5 ± 2.3; p = .006). Stroke recurred in 11 (13%) children at a median 32 days (5.5-93) from the index event and the majority (90%) were on treatment at the time of recurrence. Children with univentricular physiology were less likely to have hemorrhagic transformation (RR 0.31; 95% CI 0.09-0.96, p = .04); however, they had higher rates of recurrent stroke before final palliative repair. CONCLUSIONS: In spite of the 24% hemorrhagic transformation rate, antithrombotic therapy has a positive risk-balance in certain cardioembolic stroke subgroups, particularly in those with single-ventricle physiology, when accounting for stroke volume.

Long Vascular Sheaths for Transfemoral Neuroendovascular Procedures in Children.

PURPOSE: To evaluate the safety and efficacy of long vascular sheaths for transfemoral neuroendovascular procedures in children. MATERIALS AND METHODS: A retrospective evaluation of transfemoral neuroendovascular procedures in children <18 years, using long sheaths was undertaken analyzing procedure type, fluoroscopic times, technical success, access site and systemic complications. Twenty-seven consecutive procedures were included over a 2-year period. Mean age was 8.4 years (standard deviation [SD] 6.3) (range 17.0 months-16.3 years). RESULTS: Patients were 44% female and mean weight was 35.0 kg (SD 22.8) (range 9.8-72.2 kg). A third of the procedures were performed in ≤15 kg children. The most common procedure was for embolization (n=13, 48.1%) and the most common indication was dual microcatheter technique (52%). The most common device used was the 5 Fr Cook Shuttle sheath. Mean fluoroscopy time was 61.9 minutes (SD 43.1). Of these procedures, 93% were technically successful. Femoral vasospasm, when present, was self-limiting. Complications (3/27, 11.1%) included groin hematoma (n=1), neck vessel spasm that resolved with verapamil (n=1), and intracranial thromboembolism (n=1), with no significant difference between the ≤15 kg and >15 kg subcohorts. There were no aorto-femoro-iliac or limb-ischemic complications. CONCLUSION: Long vascular sheaths without short femoral sheaths can be safely used for pediatric neuroendovascular procedures as they effectively increase inner diameter access without increasing the outer sheath diameter. This property increases the range of devices used and intracranial techniques that can be safely performed without arterial compromise, thus increasing the repertoire of the neurointerventionist.

Distinct Clinical and Radiographic Phenotypes in Pediatric Patients With Moyamoya.

BACKGROUND: Given the expanding evidence of clinico-radiological differences between moyamoya disease (MMD) and moyamoya syndrome (MMS), we compared the clinical and radiographic features of childhood MMD and MMS to identify predictors of ischemic event recurrence. METHODS: We reviewed a pediatric moyamoya cohort followed between 2003 and 2019. Clinical and radiographic characteristics at diagnosis and follow-up were abstracted. Comparisons between MMD and MMS as well as between MMD and two MMS subgroups (neurofibromatosis [MMS-NF1] and sickle cell disease [MMS-SCD]) were performed. RESULTS: A total of 111 patients were identified. Patients with MMD presented commonly with transient ischemic attacks (TIAs) (35 % MMD versus 13% MMS-NF1 versus 9.5% MMS-SCD; P = 0.047). Symptomatic stroke presentation (MMD 37% versus MMS-NF1 4% versus 33%; P = 0.0147) and bilateral disease at diagnosis (MMD 73% versus MMS-NF1 22 % versus MMS-SCD 67%; P = 0.0002) were uncommon in MMS-NF1. TIA recurrence was common in MMD (hazard ratio 2.86; P = 0.001). The ivy sign was absent on neuroimaging in a majority of patients with MMS-SCD (MMD 67% versus MMS-NF1 52% versus MMS-SCD 9.5%; P = 0.0002). Predictors of poor motor outcome included early age at diagnosis (odds ratio [OR] 8.45; P = 0.0014), symptomatic stroke presentation (OR 6.6; P = 0.019), and advanced Suzuki stage (OR 3.59; P = 0.019). CONCLUSIONS: Moyamoya exhibits different phenotypes based on underlying etiologies. Frequent TIAs is a common phenotype of MMD and symptomatic stroke presentation a common feature of MMD and MMS-SCD, whereas unilateral disease and low infarct burden are common in MMS-NF1. In addition, absence of ivy sign is a common phenotype in MMS-SCD.

Abusive head trauma: Canadian and global perspectives.

Canada has come a long way since Dr. C. Henry Kempe first described battered-child syndrome in 1962. The year 1999 was crucial in Canada's battle against shaken baby syndrome/abusive head trauma (SBS/AHT), when the first national conference on the topic was held in Saskatoon. This was followed by the issuance of a national statement and multidisciplinary guidelines, recently updated in 2020. Incidence of AHT in Canada is similar to that found in population-based studies from Switzerland and New Zealand. The mainstay of prevention of AHT in Canada is education of parents and caregivers with respect to their response to infant crying. Population-based data for global incidence of AHT are lacking, largely because of social and cultural differences contributing to poor understanding of AHT as a medico-legal entity. India faces a distinct challenge in the battle against female feticide and infanticide.

Feasibility of ultrasound-assisted lumbar punctures performed by pediatric oncologists at the point of care.

BACKGROUND: Ultrasound assistance improves success rates and reduces adverse outcomes of lumbar punctures (LPs) among adult patients in the emergency room and the operating room, but has not been evaluated in pediatric patients with cancer. Our objectives were (1) to determine whether pediatric oncologists could perform ultrasound-assisted LPs following a structured teaching curriculum, and (2) to determine the feasibility of recruiting pediatric cancer patients to a clinical trial of this procedure. METHODS: Three pediatric oncologists completed a curriculum composed of didactic teaching followed by hands-on workshops. Each learner was evaluated during 20 attempts at three ultrasound tasks using the cumulative sum method. The three pediatric oncologists then performed ultrasound assessments prior to routinely scheduled LPs. Feasibility was defined as ability to perform at least 30 ultrasound-assisted LPs within 6 months. Secondary outcomes were the proportion of successful, bloody, or traumatic LPs, time required, and perceived helpfulness of ultrasound. RESULTS: All three pediatric oncologists achieved competence in the three tasks of ultrasound scanning within 20 evaluated attempts. We recruited 62 patients within 1 month, and 58 underwent an ultrasound-assisted LP. All LPs were successful. Two LPs (4%) had ≥500 red blood cells (RBCs)/µl, and nine (16%) had ≥10 RBCs/µl. Median time to conduct the scan was 1.9 minutes (range 0.8-4.0 minutes). In 37 (64%) of the LPs, ultrasound assistance was considered helpful or very helpful. CONCLUSIONS: Pediatric oncologists readily achieved competence in ultrasound-assisted LPs, and ultrasound was commonly perceived as helpful. It is feasible to proceed to a randomized trial of this procedure in pediatric cancer.