Case report: Long term response to growth hormone in a child with Silver-Russell syndrome-like phenotype due to a novel paternally inherited IGF2 variant.

Silver-Russell syndrome (SRS, OMIM, 180860) is a rare genetic disorder with a wide spectrum of symptoms. The most common features are intrauterine growth retardation (IUGR), poor postnatal development, macrocephaly, triangular face, prominent forehead, body asymmetry, and feeding problems. The diagnosis of SRS is based on a combination of clinical features. Up to 60% of SRS patients have chromosome 7 or 11 abnormalities, and <1% show abnormalities in IGF2 signaling pathway genes (IGF2, HMGA2, PLAG1 and CDKN1C). The underlying genetic cause remains unknown in about 40% of cases (idiopathic SRS). We report a novel IGF2 variant c.[-6-2A>G] (NM_000612) in a child with severe IUGR and clinical features of SRS and confirm the utility of targeted exome sequencing in patients with negative results to common genetic analyses. In addition, we report that long-term growth hormone treatment improves height SDS in this patient.

Arginine Vasopressin Deficiency in Children with Craniopharyngioma and Cerebral Germ Cell Tumour: Two Sides of the Same Coin. Clinical and Radiological features.

INTRODUCTION: Paediatric brain tumours in the sellar-suprasellar region (SSR) are often associated with arginine vasopressin peptide deficiency (AVPD), either at diagnosis caused by the tumour itself or during follow-up as consequence of treatments. The purpose of this research is to retrospectively describe the neuroradiological characteristics and the timing of AVPD development in a cohort of paediatric patients with craniopharyngioma (CP) or germ cell tumours (GCT). METHODS: We evaluated brain MRI at tumour diagnosis and at the onset of AVPD, as well as recorded clinical, endocrinological and histopathological data, treatments, and outcome. RESULTS: Seventy-two patients with AVPD were included: 46 CP (M: F=25:21) and 26 GCT (M: F=18:8). CPs were suprasellar (63%), sellar (4%) or both (33%). GCTs were suprasellar (65%), pineal (24%) or bifocal (11%). No statistically significant differences were noted in tumour size between CP and GCT. Posterior pituitary bright spot absence was reported at diagnosis or at follow-up (as surgery consequence) in all patients with AVPD, indicating that the absence of hyperintensity is a cardinal feature of AVPD. When measurable, pituitary stalk was thickened in most GCT patients (61.5%). At AVPD diagnosis in GCT, the mean age was 11.9 years; 18 (69%) patients had AVPD at the time of tumour diagnosis, 5 (19.3%) before the diagnosis with a latency of 24.4 months (range 4-48), and 3 (11.5%) during follow-up (mean 24 months, range 4-60) due to tumour recurrence. GCT patients presented with severe endocrinological manifestations (18/26), headache and vomiting (10/26), visual impairment (5/26) and behavioural changes with fatigue (1/26). In CP, the mean age at AVPD diagnosis was 10.3 years; 7 (15.2%) patients had AVPD at time of tumour diagnosis, 37 (80.5%) developed it shortly after neurosurgery and 2 patients (4.3%) after 2 and 4 months from surgery, respectively. Clinically, headache and visual abnormalities were the most frequent clinical symptoms at diagnosis of CP (39/46, 84.8%), with hydrocephalus (16/46, 35%) and displacement of optic chiasm (29/46, 63%) at the initial MRI. While the vast majority of CP patients (93%) received only surgery, all GCT patients received radiation therapy in addition to or instead of surgery. CONCLUSION: An early differential diagnosis in children with AVPD and brain tumours is supported by a good understanding of the clinical features and imaging findings. Expert follow-up is necessary.

Artificial intelligence applied in acute ischemic stroke: from child to elderly.

This review will summarize artificial intelligence developments in acute ischemic stroke in recent years and forecasts for the future. Stroke is a major healthcare concern due to its effects on the patient's quality of life and its dependence on the timing of the identification as well as the treatment. In recent years, attention increased on the use of artificial intelligence (AI) systems to help categorize, prognosis, and to channel these patients toward the right therapeutic procedure. Machine learning (ML) and in particular deep learning (DL) systems using convoluted neural networks (CNN) are becoming increasingly popular. Various studies over the years evaluated the use of these methods of analysis and prediction in the assessment of stroke patients, and at the same time, several applications and software have been developed to support the neuroradiologists and the stroke team to improve patient outcomes.