Resistance, rebound, and recurrence regrowth patterns in pediatric low-grade glioma treated by MAPK inhibition: A modified Delphi approach to build international consensus-based definitions-International Pediatric Low-Grade Glioma Coalition.

Pediatric low-grade glioma (pLGG) is the most common childhood brain tumor group. The natural history, when curative resection is not possible, is one of a chronic disease with periods of tumor stability and episodes of tumor progression. While there is a high overall survival rate, many patients experience significant and potentially lifelong morbidities. The majority of pLGGs have an underlying activation of the RAS/MAPK pathway due to mutational events, leading to the use of molecularly targeted therapies in clinical trials, with recent regulatory approval for the combination of BRAF and MEK inhibition for BRAFV600E mutated pLGG. Despite encouraging activity, tumor regrowth can occur during therapy due to drug resistance, off treatment as tumor recurrence, or as reported in some patients as a rapid rebound growth within 3 months of discontinuing targeted therapy. Definitions of these patterns of regrowth have not been well described in pLGG. For this reason, the International Pediatric Low-Grade Glioma Coalition, a global group of physicians and scientists, formed the Resistance, Rebound, and Recurrence (R3) working group to study resistance, rebound, and recurrence. A modified Delphi approach was undertaken to produce consensus-based definitions and recommendations for regrowth patterns in pLGG with specific reference to targeted therapies.

Identification of Multiclass Pediatric Low-Grade Neuroepithelial Tumor Molecular Subtype with ADC MR Imaging and Machine Learning.

BACKGROUND AND PURPOSE: Molecular biomarker identification increasingly influences the treatment planning of pediatric low-grade neuroepithelial tumors (PLGNTs). We aimed to develop and validate a radiomics-based ADC signature predictive of the molecular status of PLGNTs. MATERIALS AND METHODS: In this retrospective bi-institutional study, we searched the PACS for baseline brain MRIs from children with PLGNTs. Semiautomated tumor segmentation on ADC maps was performed using the semiautomated level tracing effect tool with 3D Slicer. Clinical variables, including age, sex, and tumor location, were collected from chart review. The molecular status of tumors was derived from biopsy. Multiclass random forests were used to predict the molecular status and fine-tuned using a grid search on the validation sets. Models were evaluated using independent and unseen test sets based on the combined data, and the area under the receiver operating characteristic curve (AUC) was calculated for the prediction of 3 classes: KIAA1549-BRAF fusion, BRAF V600E mutation, and non-BRAF cohorts. Experiments were repeated 100 times using different random data splits and model initializations to ensure reproducible results. RESULTS: Two hundred ninety-nine children from the first institution and 23 children from the second institution were included (53.6% male; mean, age 8.01 years; 51.8% supratentorial; 52.2% with KIAA1549-BRAF fusion). For the 3-class prediction using radiomics features only, the average test AUC was 0.74 (95% CI, 0.73-0.75), and using clinical features only, the average test AUC was 0.67 (95% CI, 0.66-0.68). The combination of both radiomics and clinical features improved the AUC to 0.77 (95% CI, 0.75-0.77). The diagnostic performance of the per-class test AUC was higher in identifying KIAA1549-BRAF fusion tumors among the other subgroups (AUC = 0.81 for the combined radiomics and clinical features versus 0.75 and 0.74 for BRAF V600E mutation and non-BRAF, respectively). CONCLUSIONS: ADC values of tumor segmentations have differentiative signals that can be used for training machine learning classifiers for molecular biomarker identification of PLGNTs. ADC-based pretherapeutic differentiation of the BRAF status of PLGNTs has the potential to avoid invasive tumor biopsy and enable earlier initiation of targeted therapy.

Assessing the Emergence and Evolution of Artificial Intelligence and Machine Learning Research in Neuroradiology.

BACKGROUND AND PURPOSE: Interest in artificial intelligence (AI) and machine learning (ML) has been growing in neuroradiology, but there is limited knowledge on how this interest has manifested into research and specifically, its qualities and characteristics. This study aims to characterize the emergence and evolution of AI/ML articles within neuroradiology and provide a comprehensive overview of the trends, challenges, and future directions of the field. MATERIALS AND METHODS: We performed a bibliometric analysis of the American Journal of Neuroradiology (AJNR): the journal was queried for original research articles published since inception (Jan. 1, 1980) to Dec. 3, 2022 that contained any of the following key terms: "machine learning", "artificial intelligence", "radiomics", "deep learning", "neural network", "generative adversarial network", "object detection", or "natural language processing". Articles were screened by two independent reviewers, and categorized into Statistical Modelling (Type 1), AI/ML Development (Type 2), both representing developmental research work but without a direct clinical integration, or End-user Application (Type 3) which is the closest surrogate of potential AI/ML integration into day-to-day practice. To better understand the limiting factors to Type 3 articles being published, we analyzed Type 2 articles as they should represent the precursor work leading to Type 3. RESULTS: A total of 182 articles were identified with 79% being non-integration focused (Type 1 n = 53, Type 2 n = 90) and 21% (n = 39) being Type 3. The total number of articles published grew roughly five-fold in the last five years, with the non-integration focused articles mainly driving this growth. Additionally, a minority of Type 2 articles addressed bias (22%) and explainability (16%). These articles were primarily led by radiologists (63%), with most of them (60%) having additional postgraduate degrees. CONCLUSIONS: AI/ML publications have been rapidly increasing in neuroradiology with only a minority of this growth being attributable to end-user application. Areas identified for improvement include enhancing the quality of Type 2 articles, namely external validation, and addressing both bias and explainability. These results ultimately provide authors, editors, clinicians, and policymakers important insights to promote a shift towards integrating practical AI/ML solutions in neuroradiology. ABBREVIATIONS: AI = artificial intelligence; ML = machine learning.

Impact of adult-onset multiple sclerosis on MRI-based intracranial volume: A study in clinically discordant monozygotic twins.

OBJECTIVE: Intracranial volume (ICV) represents the maximal brain volume for an individual, attained prior to late adolescence and remaining constant throughout life after. Thus, ICV serves as a surrogate marker for brain growth integrity. To assess the potential impact of adult-onset multiple sclerosis (MS) and its preceding prodromal subclinical changes on ICV in a large cohort of monozygotic twins clinically discordant for MS. METHODS: FSL software was used to derive ICV estimates from 3D-T1-weighted-3 T-MRI images by using an atlas scaling factor method. ICV were compared between clinically affected and healthy co-twins. All twins were compared to a large healthy reference cohort using standardized ICV z-scores. Mixed models assessed the impact of age at MS diagnosis on ICV. RESULTS: 54 twin-pairs (108 individuals/80female/42.45 ± 11.98 years), 731 individuals (375 non-twins, 109/69 monozygotic/dizygotic twin-pairs; 398female/29.18 ± 0.13 years) and 35 healthy local individuals (20male/31.34 ± 1.53 years). In 45/54 (83 %) twin-pairs, both clinically affected and healthy co-twins showed negative ICV z-scores, i.e., ICVs lower than the average of the healthy reference cohort (M = -1.53 ± 0.11, P<10-5). Younger age at MS diagnosis was strongly associated with lower ICVs (t = 3.76, P = 0.0003). Stratification of twin-pairs by age at MS diagnosis of the affected co-twin (≤30 versus > 30 years) yielded lower ICVs in those twin pairs with younger age at diagnosis (P = 0.01). Comparison within individual twin-pairs identified lower ICVs in the MS-affected co-twins with younger age at diagnosis compared to their corresponding healthy co-twins (P = 0.003). CONCLUSION: We offer for the first-time evidence for strong associations between adult-onset MS and lower ICV, which is more pronounced with younger age at diagnosis. This suggests pre-clinical alterations in early neurodevelopment associated with susceptibility to MS both in individuals with and without clinical manifestation of the disease.

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.

Health Inequity and Time From Pediatric Stroke Onset to Arrival.

BACKGROUND: Time from stroke onset to hospital arrival determines treatment and impacts outcome. Structural, socioeconomic, and environmental factors are associated with health inequity and onset-to-arrival in adult stroke. We aimed to assess the association between health inequity and onset-to-arrival in a pediatric comprehensive stroke center. METHODS: A retrospective observational study was conducted on a consecutive cohort of children (>28 days-18 years) diagnosed with acute arterial ischemic stroke (AIS) between 2004 and 2019. Neighborhood-level material deprivation was derived from residential postal codes and used as a proxy measure for health inequity. Patients were stratified by level of neighborhood-level material deprivation, and onset-to-arrival was categorized into 3 groups: <6, 6 to 24, and >24 hours. Association between neighborhood-level material deprivation and onset-to-arrival was assessed in multivariable ordinal logistic regression analyses adjusting for sociodemographic and clinical factors. RESULTS: Two hundred and twenty-nine children were included (61% male; median age [interquartile range] at stroke diagnosis 5.8-years [1.1-11.3]). Over the 16-year study period, there was an increase in proportion of children diagnosed with AIS living in the most deprived neighborhoods and arriving at the emergency room within 6 hours (P=0.01). Among Asian patients, a higher proportion lived in the most deprived neighborhoods (P=0.02) and level of material deprivation was associated with AIS risk factors (P=0.001). CONCLUSIONS: Our study suggests an increase in pediatric stroke in deprived neighborhoods and certain communities, and earlier arrival times to the emergency room over time. However, whether these changes are due to an increase in incidence of childhood AIS or increased awareness and diagnosis is yet to be determined. The association between AIS risk factors and material deprivation highlights the intersectionality of clinical factors and social determinants of health. Finally, whether material deprivation impacts onset-to-arrival is likely complex and requires further examination.

Brain Volumes in Opsoclonus-Myoclonus Ataxia Syndrome: A Longitudinal Study.

INTRODUCTION: Little is known about the longitudinal trajectory of brain growth in children with opsoclonus-myoclonus ataxia syndrome. We performed a longitudinal evaluation of brain volumes in pediatric opsoclonus-myoclonus ataxia syndrome patients compared with age- and sex-matched healthy children. PATIENTS AND METHODS: This longitudinal case-control study included brain magnetic resonance imaging (MRI) scans from consecutive pediatric opsoclonus-myoclonus ataxia syndrome patients (2009-2020) and age- and sex-matched healthy control children. FreeSurfer analysis provided automatic volumetry of the brain. Paired t tests were performed on the curvature of growth trajectories, with Bonferroni correction. RESULTS: A total of 14 opsoclonus-myoclonus ataxia syndrome patients (12 female) and 474 healthy control children (406 female) were included. Curvature of the growth trajectories of the cerebral white and gray matter, cerebellar white and gray matter, and brainstem differed significantly between opsoclonus-myoclonus ataxia syndrome patients and healthy control children (cerebral white matter, P = .01; cerebral gray matter, P = .01; cerebellar white matter, P < .001; cerebellar gray matter, P = .049; brainstem, P < .01). DISCUSSION/CONCLUSION: We found abnormal brain maturation in the supratentorial brain, brainstem, and cerebellum in children with opsoclonus-myoclonus ataxia syndrome.

Pedicle screw accuracy placed with assistance of machine vision technology in patients with neuromuscular scoliosis.

INTRODUCTION: Pedicle screws are the primary method of vertebral fixation in scoliosis surgery, but there are lingering concerns over potential malposition. The rates of pedicle screw malposition in pediatric spine surgery vary from 10% to 21%. Malpositioned screws can lead to potentially catastrophic neurological, vascular, and visceral complications. Pedicle screw positioning in patients with neuromuscular scoliosis is challenging due to a combination of large curves, complex pelvic anatomy, and osteopenia. This study aimed to determine the rate of pedicle screw malposition, associated complications, and subsequent revision from screws placed with the assistance of machine vision navigation technology in patients with neuromuscular scoliosis undergoing posterior instrumentation and fusion. METHOD: A retrospective analysis of the records of patients with neuromuscular scoliosis who underwent thoracolumbar pedicle screw insertion with the assistance of machine-vision image guidance navigation was performed. Screws were inserted by either a staff surgeon, orthopaedic fellow, or orthopaedic resident. Post-operative ultra-low dose CT scans were used to assess pedicle screw accuracy. The Gertzbein classification was used to grade any pedicle breaches (grade 0, no breach; grade 1, <2 mm; grade 2, 2-4 mm; grade 3, >4 mm). A screw was deemed accurate if no breach was identified (grade 0). RESULTS: 25 patients were included in the analysis, with a mean age of 13.6 years (range 11 to 18 years; 13/25 (52.0%) were female. The average pre-operative supine Cobb angle was 90.0 degrees (48-120 degrees). A total of 687 screws from 25 patients were analyzed (402 thoracic, 241 lumbosacral, 44 S2 alar-iliac (S2AI) screws). Surgical trainees (fellows and orthopaedic residents) inserted 46.6% (320/687) of screws with 98.8% (4/320) accuracy. The overall accuracy of pedicle screw insertion was 98.0% (Grade 0, no breach). All 13 breaches that occurred in the thoracic and lumbar screws were Grade 1. Of the 44 S2AI screws placed, one screw had a Grade 3 breach (2.3%) noted on intra-operative radiographs following rod placement and correction. This screw was subsequently revised. None of the breaches resulted in neuromonitoring changes, vessel, or visceral injuries. CONCLUSION: Machine vision navigation technology combined with careful free-hand pedicle screw insertion techniques demonstrated high levels of pedicle screw insertion accuracy, even in patients with challenging anatomy.

Brain Tumor Imaging in Adolescents and Young Adults: 2021 WHO Updates for Molecular-based Tumor Types.

Published in 2021, the fifth edition of the World Health Organization (WHO) classification of tumors of the central nervous system (CNS) introduced new molecular criteria for tumor types that commonly occur in either pediatric or adult age groups. Adolescents and young adults (AYAs) are at the intersection of adult and pediatric care, and both pediatric-type and adult-type CNS tumors occur at that age. Mortality rates for AYAs with CNS tumors have increased by 0.6% per year for males and 1% per year for females from 2007 to 2016. To best serve patients, it is crucial that both pediatric and adult radiologists who interpret neuroimages are familiar with the various pediatric- and adult-type brain tumors and their typical imaging morphologic characteristics. Gliomas account for approximately 80% of all malignant CNS tumors in the AYA age group, with the most common types observed being diffuse astrocytic and glioneuronal tumors. Ependymomas and medulloblastomas also occur in the AYA population but are seen less frequently. Importantly, biologic behavior and progression of distinct molecular subgroups of brain tumors differ across ages. This review discusses newly added or revised gliomas in the fifth edition of the CNS WHO classification, as well as other CNS tumor types common in the AYA population.

Artificial Intelligence in the Future Landscape of Pediatric Neuroradiology: Opportunities and Challenges.

This paper will review how artificial intelligence (AI) will play an increasingly important role in pediatric neuroradiology in the future. A safe, transparent, and human-centric AI is needed to tackle the quadruple aim of improved health outcomes, enhanced patient and family experience, reduced costs, and improved well-being of the healthcare team in pediatric neuroradiology. Equity, diversity and inclusion, data safety, and access to care will need to always be considered. In the next decade, AI algorithms are expected to play an increasingly important role in access to care, workflow management, abnormality detection, classification, response prediction, prognostication, report generation, as well as in the patient and family experience in pediatric neuroradiology. Also, AI algorithms will likely play a role in recognizing and flagging rare diseases and in pattern recognition to identify previously unknown disorders. While AI algorithms will play an important role, humans will not only need to be in the loop, but in the center of pediatric neuroimaging. AI development and deployment will need to be closely watched and monitored by experts in the field. Patient and data safety need to be at the forefront, and the risks of a dependency on technology will need to be contained. The applications and implications of AI in pediatric neuroradiology will differ from adult neuroradiology.

Accuracy of Information and References Using ChatGPT-3 for Retrieval of Clinical Radiological Information.

Purpose: To assess the accuracy of answers provided by ChatGPT-3 when prompted with questions from the daily routine of radiologists and to evaluate the text response when ChatGPT-3 was prompted to provide references for a given answer. Methods: ChatGPT-3 (San Francisco, OpenAI) is an artificial intelligence chatbot based on a large language model (LLM) that has been designed to generate human-like text. A total of 88 questions were submitted to ChatGPT-3 using textual prompt. These 88 questions were equally dispersed across 8 subspecialty areas of radiology. The responses provided by ChatGPT-3 were assessed for correctness by cross-checking them with peer-reviewed, PubMed-listed references. In addition, the references provided by ChatGPT-3 were evaluated for authenticity. Results: A total of 59 of 88 responses (67%) to radiological questions were correct, while 29 responses (33%) had errors. Out of 343 references provided, only 124 references (36.2%) were available through internet search, while 219 references (63.8%) appeared to be generated by ChatGPT-3. When examining the 124 identified references, only 47 references (37.9%) were considered to provide enough background to correctly answer 24 questions (37.5%). Conclusion: In this pilot study, ChatGPT-3 provided correct responses to questions from the daily clinical routine of radiologists in only about two thirds, while the remainder of responses contained errors. The majority of provided references were not found and only a minority of the provided references contained the correct information to answer the question. Caution is advised when using ChatGPT-3 to retrieve radiological information.

Increased confidence of radiomics facilitating pretherapeutic differentiation of BRAF-altered pediatric low-grade glioma.

OBJECTIVES: Currently, the BRAF status of pediatric low-grade glioma (pLGG) patients is determined through a biopsy. We established a nomogram to predict BRAF status non-invasively using clinical and radiomic factors. Additionally, we assessed an advanced thresholding method to provide only high-confidence predictions for the molecular subtype. Finally, we tested whether radiomic features provide additional predictive information for this classification task, beyond that which is embedded in the location of the tumor. METHODS: Random forest (RF) models were trained on radiomic and clinical features both separately and together, to evaluate the utility of each feature set. Instead of using the traditional single threshold technique to convert the model outputs to class predictions, we implemented a double threshold mechanism that accounted for uncertainty. Additionally, a linear model was trained and depicted graphically as a nomogram. RESULTS: The combined RF (AUC: 0.925) outperformed the RFs trained on radiomic (AUC: 0.863) or clinical (AUC: 0.889) features alone. The linear model had a comparable AUC (0.916), despite its lower complexity. Traditional thresholding produced an accuracy of 84.5%, while the double threshold approach yielded 92.2% accuracy on the 80.7% of patients with the highest confidence predictions. CONCLUSION: Models that included radiomic features outperformed, underscoring their importance for the prediction of BRAF status. A linear model performed similarly to RF but with the added benefit that it can be visualized as a nomogram, improving the explainability of the model. The double threshold technique was able to identify uncertain predictions, enhancing the clinical utility of the model. CLINICAL RELEVANCE STATEMENT: Radiomic features and tumor location are both predictive of BRAF status in pLGG patients. We show that they contain complementary information and depict the optimal model as a nomogram, which can be used as a non-invasive alternative to biopsy. KEY POINTS: • Radiomic features provide additional predictive information for the determination of the molecular subtype of pediatric low-grade gliomas patients, beyond what is embedded in the location of the tumor, which has an established relationship with genetic status. • An advanced thresholding method can help to distinguish cases where machine learning models have a high chance of being (in)correct, improving the utility of these models. • A simple linear model performs similarly to a more powerful random forest model at classifying the molecular subtype of pediatric low-grade gliomas but has the added benefit that it can be converted into a nomogram, which may facilitate clinical implementation by improving the explainability of the model.

MRI-Based End-To-End Pediatric Low-Grade Glioma Segmentation and Classification.

Purpose: MRI-based radiomics models can predict genetic markers in pediatric low-grade glioma (pLGG). These models usually require tumour segmentation, which is tedious and time consuming if done manually. We propose a deep learning (DL) model to automate tumour segmentation and build an end-to-end radiomics-based pipeline for pLGG classification. Methods: The proposed architecture is a 2-step U-Net based DL network. The first U-Net is trained on downsampled images to locate the tumour. The second U-Net is trained using image patches centred around the located tumour to produce more refined segmentations. The segmented tumour is then fed into a radiomics-based model to predict the genetic marker of the tumour. Results: Our segmentation model achieved a correlation value of over 80% for all volume-related radiomic features and an average Dice score of .795 in test cases. Feeding the auto-segmentation results into a radiomics model resulted in a mean area under the ROC curve (AUC) of .843, with 95% confidence interval (CI) [.78-.906] and .730, with 95% CI [.671-.789] on the test set for 2-class (BRAF V600E mutation BRAF fusion) and 3-class (BRAF V600E mutation BRAF fusion and Other) classification, respectively. This result was comparable to the AUC of .874, 95% CI [.829-.919] and .758, 95% CI [.724-.792] for the radiomics model trained and tested on the manual segmentations in 2-class and 3-class classification scenarios, respectively. Conclusion: The proposed end-to-end pipeline for pLGG segmentation and classification produced results comparable to manual segmentation when it was used for a radiomics-based genetic marker prediction model.

Effects of Exercise on Structural and Functional Brain Patterns in Schizophrenia-Data From a Multicenter Randomized-Controlled Study.

BACKGROUND AND HYPOTHESIS: Aerobic exercise interventions in people with schizophrenia have been demonstrated to improve clinical outcomes, but findings regarding the underlying neural mechanisms are limited and mainly focus on the hippocampal formation. Therefore, we conducted a global exploratory analysis of structural and functional neural adaptations after exercise and explored their clinical implications. STUDY DESIGN: In this randomized controlled trial, structural and functional MRI data were available for 91 patients with schizophrenia who performed either aerobic exercise on a bicycle ergometer or underwent a flexibility, strengthening, and balance training as control group. We analyzed clinical and neuroimaging data before and after 6 months of regular exercise. Bayesian linear mixed models and Bayesian logistic regressions were calculated to evaluate effects of exercise on multiple neural outcomes and their potential clinical relevance. STUDY RESULTS: Our results indicated that aerobic exercise in people with schizophrenia led to structural and functional adaptations mainly within the default-mode network, the cortico-striato-pallido-thalamo-cortical loop, and the cerebello-thalamo-cortical pathway. We further observed that volume increases in the right posterior cingulate gyrus as a central node of the default-mode network were linked to improvements in disorder severity. CONCLUSIONS: These exploratory findings suggest a positive impact of aerobic exercise on 3 cerebral networks that are involved in the pathophysiology of schizophrenia. CLINICAL TRIALS REGISTRATION: The underlying study of this manuscript was registered in the International Clinical Trials Database, ClinicalTrials.gov (NCT number: NCT03466112, https://clinicaltrials.gov/ct2/show/NCT03466112?term=NCT03466112&draw=2&rank=1) and in the German Clinical Trials Register (DRKS-ID: DRKS00009804).