Search

Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001 through December 2015) from a national brain tumor consortium (n = 184; median age, 7 years [range, 1-23 years]; 94 male patients) and a pediatric cancer center (n = 100; median age, 8 years [range, 1-19 years]; 47 male patients) to develop and evaluate deep learning neural networks for pediatric low-grade glioma segmentation using a stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally tested on an independent test set and subjected to randomized blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain stepwise transfer learning (median Dice score coefficient, 0.88 [IQR, 0.72-0.91] vs 0.812 [IQR, 0.56-0.89] for baseline model; P = .049). With external testing, the AI model yielded excellent accuracy using reference standards from three clinical experts (median Dice similarity coefficients: expert 1, 0.83 [IQR, 0.75-0.90]; expert 2, 0.81 [IQR, 0.70-0.89]; expert 3, 0.81 [IQR, 0.68-0.88]; mean accuracy, 0.82). For clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score, 9 [IQR, 7-9] vs 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% vs 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level automated pediatric brain tumor autosegmentation and volumetric measurement with a high level of clinical acceptability. Keywords: Stepwise Transfer Learning, Pediatric Brain Tumors, MRI Segmentation, Deep Learning Supplemental material is available for this article. © RSNA, 2024.

BackgroundActivation of the mammalian target of rapamycin (mTOR) pathway is observed in neurofibromatosis type 1 (NF1) associated low-grade gliomas (LGGs), but agents that inhibit this pathway, including mTOR inhibitors, have not been studied in this population. We evaluate the efficacy of the orally administered mTOR inhibitor everolimus for radiographically progressive NF1-associated pediatric LGGs.MethodsChildren with radiologic-progressive, NF1-associated LGG and prior treatment with a carboplatin-containing chemotherapy were prospectively enrolled on this phase II clinical trial to receive daily everolimus. Whole blood was analyzed for everolimus and markers of phosphatidylinositol-3 kinase (PI3K)/mTOR pathway inhibition. Serial MRIs were obtained during treatment. The primary endpoint was progression-free survival at 48 weeks.ResultsTwenty-three participants (median age, 9.4 y; range, 3.2-21.6 y) were enrolled. All participants were initially evaluable for response; 1 patient was removed from study after development of a malignant peripheral nerve sheath tumor. Fifteen of 22 participants (68%) demonstrated a response, defined as either shrinkage (1 complete response, 2 partial response) or arrest of tumor growth (12 stable disease). Of these, 10/15 remained free of progression (median follow-up, 33 mo). All remaining 22 participants were alive at completion of therapy. Treatment was well tolerated; no patient discontinued therapy due to toxicity. Pharmacokinetic parameters and pre-dose concentrations showed substantial between-subject variability. PI3K/mTOR pathway inhibition markers demonstrating blood mononuclear cell mTOR pathway inactivation was achieved in most participants.ConclusionIndividuals with recurrent/progressive NF1-associated LGG demonstrate significant disease stability/shrinkage during treatment with oral everolimus with a well-tolerated toxicity profile. Everolimus is well suited for future consideration as upfront or combination therapy in this patient population.

KIF26B is a member of the kinesin superfamily with evolutionarily conserved functions in controlling aspects of embryogenesis, including the development of the nervous system, though its function is incompletely understood. We describe an infant with progressive microcephaly, pontocerebellar hypoplasia, and arthrogryposis secondary to the involvement of anterior horn cells and ventral (motor) nerves. We performed whole exome sequencing on the trio and identified a de novo KIF26B missense variant, p.Gly546Ser, in the proband. This variant alters a highly conserved amino acid residue that is part of the phosphate-binding loop motif and motor-like domain and is deemed pathogenic by several in silico methods. Functional analysis of the variant protein in cultured cells revealed a reduction in the KIF26B protein's ability to promote cell adhesion, a defect that potentially contributes to its pathogenicity. Overall, KIF26B may play a critical role in the brain development and, when mutated, cause pontocerebellar hypoplasia with arthrogryposis.

Sensory integration is the province of the parietal lobe. The non-dominant hemisphere is responsible for both body sides, while the dominant hemisphere is responsible for the contralateral hemi-body. Furthermore, the posterior cingulate cortex (PCC) participates in a network involved in spatial orientation, attention, and spatial and episodic memory. Laser interstitial thermotherapy (LiTT) is a minimally invasive surgery for focal drug-resistant epilepsy (DRE) that can target deeper brain regions, and thus, region-specific symptoms can emerge. Here, we present an 18-year-old right-handed male with focal DRE who experienced seizures characterized by sensations of déjà vu, staring spells, and language disruption. A comprehensive evaluation localized the seizure focus and revealed a probable focal cortical dysplasia (FCD) in the left posterior cingulate gyrus. The patient underwent uneventful LiTT of the identified lesion. Post-operatively, he developed transient ipsilateral spatial neglect and contralateral sensory loss, as well as acalculia. His sensory symptoms gradually improved after the surgery, and he remained seizure-free after the intervention for at least 10 months (until the time of this writing). This rare case of ipsilateral spatial and visual hemineglect post-LiTT in epilepsy underscores the importance of recognizing atypical neurosurgical outcomes and considering individual variations in brain anatomy and function. Understanding the dynamics of cortical connectivity and handedness, particularly in pediatric epilepsy, may be crucial in anticipating and managing neurocognitive effects following epilepsy surgery. [ABSTRACT FROM AUTHOR]

There is a high incidence of autism in tuberous sclerosis complex. Given the evidence of impaired face processing in autism, the authors sought to investigate electrophysiological markers of face processing in children with tuberous sclerosis complex. The authors studied 19 children with tuberous sclerosis complex under age 4, and 20 age-matched controls, using a familiar-unfamiliar faces paradigm. Of the children, 6 with tuberous sclerosis complex (32%) had autism. Children with tuberous sclerosis complex showed a longer N290 latency than controls (276 ms vs 259 ms, P = .05) and also failed to show the expected hemispheric differences in face processing. The longest N290 latency was seen in (1) children with autism and tuberous sclerosis complex and (2) children with temporal lobe tubers. This study is the first to quantify atypical face processing in children with tuberous sclerosis complex. This functional impairment may provide insight into a mechanism underlying a pathway to autism in tuberous sclerosis complex.

The purpose of this study was to examine the relationship between language pathways and autism spectrum disorders (ASDs) in patients with tuberous sclerosis complex (TSC). An advanced diffusion-weighted magnetic resonance imaging (MRI) was performed on 42 patients with TSC and 42 age-matched controls. Using a validated automatic method, white matter language pathways were identified and microstructural characteristics were extracted, including fractional anisotropy (FA) and mean diffusivity (MD). Among 42 patients with TSC, 12 had ASD (29%). After controlling for age, TSC patients without ASD had a lower FA than controls in the arcuate fasciculus (AF); TSC patients with ASD had even a smaller FA, lower than the FA for those without ASD. Similarly, TSC patients without ASD had a greater MD than controls in the AF; TSC patients with ASD had even a higher MD, greater than the MD in those without ASD. It remains unclear why some patients with TSC develop ASD, while others have better language and socio-behavioral outcomes. Our results suggest that language pathway microstructure may serve as a marker of the risk of ASD in TSC patients. Impaired microstructure in language pathways of TSC patients may indicate the development of ASD, although prospective studies of language pathway development and ASD diagnosis in TSC remain essential.