CONTEXT
Neuroradiological findings in Noonan syndrome (NS) remain insufficiently characterized.
OBJECTIVE
To characterize neuroimaging abnormalities in children with genetically confirmed NS and evaluate their associations with clinical phenotype.
DESIGN, SETTING, AND PARTICIPANTS
In this multicenter retrospective study, brain MRI scans and longitudinal clinical and genetic data were reviewed from children with genetically confirmed NS evaluated between 2008 and 2023 at seven pediatric endocrinology centers.
MAIN OUTCOME MEASURES
Prevalence and spectrum of neuroimaging abnormalities and their associations with genotype and clinical features.
RESULTS
The cohort included 130 individuals with NS (71 males; mean age at MRI, 9.7 years), most carrying PTPN11 variants (69.2%). Structural brain abnormalities were identified in 84.7% and included midbrain-hindbrain malformations (69.2%), callosal anomalies (52.3%), cortical malformations (50%), white matter abnormalities (48.4%), and cranio-cervical junction anomalies (40%). Brain tumors and Chiari I malformation were present in 12.3% and 10.7%, respectively. Seizures were associated with cortical tumors (p = 0.02) and callosal anomalies (p = 0.03), whereas developmental delay was associated with callosal anomalies (p = 0.02) and microcephaly (p < 0.01). Follow-up MRI, available in 41 patients over a mean duration of 6.3 years, showed interval changes in 48.7%, including tumor progression, progressive tonsillar descent, odontoid retroversion, and newly detected lesions.
CONCLUSIONS
In this selected cohort of children with NS who underwent brain MRI as part of routine clinical care, structural brain abnormalities were frequent and were associated with neurological manifestations. These findings support a role for RAS/MAPK pathway dysregulation in brain development and highlight the clinical value of MRI in selected patients with NS.
G. Patti, Nadia Gabriella Maiorano, F. Piccoli et al.· Journal of Clinical Endocrin...· 0 citations
PURPOSE
A deep learning algorithm for contrast amplification in brain MRI, trained exclusively on adult data, was tested for cross-population generalization to pediatric patients, including subjects aged 0-2 years.
METHODS
A retrospective monocentric dataset (n = 22 cases) comprising pediatric patients (0-17 years old) diagnosed with various brain tumors was used to evaluate the algorithm, which takes T1-weighted pre- and standard post-contrast images as input and generates an output image with amplified contrast, further post-processed with an HDR algorithm. Quantitative comparisons between standard and amplified images were performed using contrast-to-noise ratio (CNR), contrast enhancement percentage (CEP), and lesion-to-background ratio (LBR). Three neuroradiologists performed qualitative assessment using a 4-point Likert scale, focusing on lesion contrast and delineation. Anatomical similarity was assessed using SSIM and log-Jacobian range. Statistical significance was evaluated using two-tailed paired t-tests.
RESULTS
Compared to standard-dose images, contrast-amplified images showed significantly higher values for CNR (+ 186.5%), LBR (+ 61.9%), and CEP (+ 110.4%). Qualitative assessments demonstrated comparable lesion visualization, with improvements observed in selected cases. Reader 1 preferred the contrast-amplified image in 12 of 22 cases (54.5%), reader 2 favored it in 18 of 22 cases (81.8%) and reader 3 in 13/22 cases (59.1%). One reader reported improved overall image quality (mean score: 3.95 vs. 3.73). The average SSIM between amplified and standard-dose images was 0.98, and any significant anatomical differences were highlighted by the log-Jacobian range (p-value = 0.556).
CONCLUSION
An algorithm for contrast amplification based on deep learning, trained with adult data, significantly enhances quantitative contrast metrics in images from pediatric patients. It is preferred over standard-dose images in the majority of cases when used for pediatric brain MRI, indicating its promising application for cross-population applicability.
Anna Macula, G. Morana, Fiorenza Coppola et al.· Neuroradiology· 0 citations
