Analysis of MRI brain biometrics in fetuses monitored for intra uterine growth restriction and their prognostic value: Results of a prospective multicenter study.

OBJECTIVE: Show a prognostic value of brain changes in fetuses with intra uterine growth restriction (IUGR) on early neonatal outcome. STUDY DESIGN: We prospectively recruited pregnant women whose fetuses presented fetal weight < 5th centile. A brain MRI was performed between 28 and 32 weeks of gestation (WG). Several brain biometrics were measured (as fronto-occipital diameter (FOD) and transverse cerebellar diameter (TCD)). Neonatal prognosis was evaluated according to a composite criterion. RESULTS: Of the 78 patients included, 62 had a fetal brain MRI. The mean centile value of FOD was lower in the unfavorable outcome group (n = 9) compared to the favorable outcome group (n = 53) (24.5 ± 16.8 vs. 8.6 ± 13.2, p = 0.004). The ROC curve for predicting risk of unfavorable neonatal outcome based on FOD presented an area under the curve of 0.81 (95 % CI, [0.63---0.99]) and a threshold determined at the 3rd centile was associated with sensitivity of 0.78 and a specificity of 0.89. In multivariate analysis, a FOD less than the 3rd centile was significantly associated with an unfavorable neonatal risk. There also was a reduction in TCD (25.5 ± 21.5 vs. 10.4 ± 10.4, p = 0.03) in the unfavorable neonatal outcome group. CONCLUSION: We found an association between a reduction in FOD and TCD in fetal MRIs conducted between 28 and 32 WG in fetuses monitored for IUGR with an unfavorable neonatal outcome. Our results suggest that these biometric changes could constitute markers of poor neonatal prognosis.

External validation of an artificial intelligence solution for the detection of elbow fractures and joint effusions in children.

PURPOSE: The purpose of this study was to conduct an external validation of an artificial intelligence (AI) solution for the detection of elbow fractures and joint effusions using radiographs from a real-life cohort of children. MATERIALS AND METHODS: This single-center retrospective study was conducted on 758 radiographic sets (1637 images) obtained from consecutive emergency room visits of 712 children (mean age, 7.27 ± 3.97 [standard deviation] years; age range, 7 months and 10 days to 15 years and 10 months), referred for a trauma of the elbow. For each set, fracture and/or effusion detection by eleven senior radiologists (reference standard) and AI solution was recorded. Diagnostic performance of the AI solution was measured via four different approaches: fracture detection (presence/absence of fracture as binary variable), fracture enumeration, fracture localization and lesion detection (fracture and/or a joint effusion used as constructed binary variable). RESULTS: The sensitivity of the AI solution for each of the four approaches was >89%. Greatest sensitivity of the AI solution was obtained for lesion detection (95.0%; 95% confidence interval: 92.1-96.9). The specificity of the AI solution ranged between 63% (for lesion detection) and 77% (for fracture detection). For all four approaches, the negative predictive values were >92% and the positive predictive values ranged between 54% (for fracture enumeration and localization) and 73% (for lesion detection). Specificity was lower for plastered children for all approaches (P < 0.001). CONCLUSION: The AI solution demonstrates high performances for detecting elbow's fracture and/or joint effusion in children. However, in our context of use, 8% of the radiographic sets ruled-out by the algorithm concerned children with a genuine traumatic elbow lesion.

MRI quantitative muscle characterization in children with X-linked hypophosphatemia.

INTRODUCTION: Children with X Linked Hypophosphatemia (XLH) suffer from carential ricket, bone deformities and lameness. No previous study demonstrated a morphological distinction in muscles in these patients. The aim of this prospective study was to characterize, using Magnetic Resonance Imaging (MRI), the muscle morphology of pelvis, thigh and leg in children with XLH and to compare it with typically developed (TD) children. HYPOTHESIS: We hypothesized that lower limbs muscles in children with XLH are different from TD children and could explain limp walking. MATERIAL AND METHODS: Three-dimensional reconstructions of the muscles were performed in 11 patients with XLH and 15 TD children. Muscle lengths, sections and volumes were calculated and normalized with height and weight. Mean age was 10. RESULTS: Lengths were all smaller in children with XLH except for the Medius/minimus gluteus muscles (p=0.64). The difference seemed higher in muscles with a long tendinous part as semitendinosus (0.139 vs 0,164; p<0.01). All volumes were significantly inferior in children with XLH. This preliminary study showed significant differences in muscle structures between patients with XLH and TD children. DISCUSSION: Medius/minimus gluteus seemed to be particularly developed in children with XLH. Nevertheless it is not possible to conclude if it is related to XLH or a consequence of bone deformities. LEVEL OF PROOF: IV.

International Consensus Statement on the Radiological Screening of Contact Children in the Context of Suspected Child Physical Abuse.

Importance: Physical abuse is a common but preventable cause of long-term childhood morbidity and mortality. Despite the strong association between abuse in an index child and abuse in contact children, there is no guidance outlining how to screen the latter, significantly more vulnerable group, for abusive injuries. Consequently, the radiological assessment of contact children is often omitted, or variably performed, allowing occult injuries to go undetected and increasing the risk of further abuse. Objective: To report an evidence-based and consensus-derived set of best practices for the radiological screening of contact children in the context of suspected child physical abuse. Evidence Review: This consensus statement is supported by a systematic review of the literature and the clinical opinion of an internationally recognized group of 26 experts. The modified Delphi consensus process comprised 3 meetings of the International Consensus Group on Contact Screening in Suspected Child Physical Abuse held between February and June 2021. Findings: Contacts are defined as the asymptomatic siblings, cohabiting children, or children under the same care as an index child with suspected child physical abuse. All contact children should undergo a thorough physical examination and a history elicited prior to imaging. Contact children younger than 12 months should have neuroimaging, the preferred modality for which is magnetic resonance imaging, and skeletal survey. Contact children aged 12 to 24 months should undergo skeletal survey. No routine imaging is indicated in asymptomatic children older than 24 months. Follow-up skeletal survey with limited views should be performed if abnormal or equivocal at presentation. Contacts with positive findings should be investigated as an index child. Conclusions and Relevance: This Special Communication reports consensus recommendations for the radiological screening of contact children in the context of suspected child physical abuse, establishing a recognized baseline for the stringent evaluation of these at-risk children and providing clinicians with a more resilient platform from which to advocate for them.

Controversial aspects of imaging in child abuse: a second roundtable discussion from the ESPR child abuse taskforce.

This second roundtable discussion was convened at the 56th European Society of Paediatric Radiology (ESPR) 2022 Annual Meeting in Marseille, France, to discuss controversial aspects of imaging in child abuse. The following topics were discussed: Fracture dating-the published literature is broadly similar with respect to the identification of the radiographic stages of bony healing. The non-expert/general radiologist is encouraged to use broad descriptors of fracture healing (acute, healing or old) within their reports, rather than attempting to date fractures. The more experienced/expert radiologist, who may provide a timeframe/range to assist the courts, should be aware that any published timeframes are not absolute and that recent research indicates that the rate of healing may differ according to the bone affected and the age of the patient. Whole spine imaging in suspected abusive head trauma-this is recommended to enable a complete assessment of the neuraxis when abusive head trauma is suspected or diagnosed, particularly in the presence of intracranial and cervical subdural haemorrhage and cervical ligamentous injury. Cranial imaging in suspected physical abuse-both computed tomography (CT) and magnetic resonance imaging (MRI) remain complimentary depending on the clinical context in which they are used with CT remaining first-line in the assessment of children with (suspected abusive) head trauma prior to an early MRI. MRI is superior in its assessment of parenchymal injury and may be employed as first-line in age appropriate asymptomatic siblings of a child with suspected physical abuse.

Benign enlargement of the subarachnoid spaces and subdural collections-when to evaluate for abuse.

In infants without a history of trauma, subdural haemorrhages should raise the concern for an abusive head injury, particularly when they are associated with bridging vein clotting/rupture or with septations. However, non-haemorrhagic, fluid-appearing subdural collections (also called hygromas) may also be the result of abuse. Subdural collections have also been uncommonly observed in patients with benign enlargement of the subarachnoid spaces (BESS) and a few large-scale studies accurately investigate the incidence and the significance. Currently, there is a wide variation of practices in children with BESS and subdural collections. Due to the social risks associated with abuse evaluation and the perceived risk of radiation exposure, there might be a reluctance to fully evaluate these children in some centres. The diagnosis of physical abuse cannot be substantiated nor safely excluded in infants with BESS and subdural collection(s), without investigation for concomitant traumatic findings. The exact prevalence of occult injuries and abuse in these infants is unknown. In macrocephalic infants with subdural collections and imaging features of BESS, thorough investigations for abuse are warranted and paediatricians should consider performing full skeletal surveys even when fundoscopy, social work consult, and detailed clinical evaluation are unremarkable.

French survey of sedation practices for pediatric magnetic resonance and computed tomography imaging.

BACKGROUND: Pediatric magnetic resonance imaging (MRI) and computed tompgraphy (CT) require patient immobility and therefore often require sedation or general anesthesia of patients. Consensus on these procedures is lacking in France. OBJECTIVE: Thus, the aim of this study was to describe the current sedation practices for pediatric MRI and CT in France. MATERIAL AND METHODS: From January 2019 to December 2019, an online questionnaire was delivered by electronic mail to a representative radiologist in 60 pediatric radiology centers registered by the French-speaking pediatric and prenatal imaging society. Questions included protocols, drugs used, monitoring and side effects. RESULTS: Representatives of 40 of the 60 (67%) radiology centers responded to the survey. Among them, 31 performed sedation including 17 (55%) centers where radiologists performed sedation without anesthesiologists present during the procedure. The premedication drugs were hydroxyzine (n = 8, 80%) and melatonin (n = 2, 20%), Sedation drugs used for children ages 0 to 6 years old were pentobarbital (n = 9, 60%), midazolam (n = 2, 13%), chloral hydrate (n = 2, 13%), diazepam (n = 1, 6.5%) and chlorpromazine (n = 1, 6.5%). A written sedation protocol was available in 10/17 (59%) centers. In 6/17 (35%) centers, no monitoring was used during the procedures. Blood pressure monitoring and capnography were rarely used (< 10%) and post-sedation monitoring was heterogeneous. No life-threatening adverse effect was reported, but 6 centers reported at least one incident per year. CONCLUSION: For half of the responding radiology centers, radiologists performed sedation alone in agreement with the local anesthesiology team. Sedation procedures and monitoring were heterogenous among centers. Adjustment and harmonization of the practices according to the capacity of each center may be useful.

The monthly incidence of abusive head trauma, inflicted skeletal trauma, and unexplained skin lesion in children in six French university hospitals during the COVID-19 pandemic.

INTRODUCTION: The COVID-19 pandemic was a stressful period. Lockdowns may have added to parental difficulty leading to an increase in violence. This study aimed to compare the monthly incidence of high suspicion of child physical abuse before and during the COVID-19 pandemic. MATERIAL: We have retrospectively reviewed imaging examinations of children having a skeletal X-ray examination in six university hospitals with high suspicion of abusive head traumatism (AHT), inflicted skeletal trauma (IST) and unexplained skin lesions (USL) between March 2020 and June 2021 and compared with the similar period from 2018 to 2019. The monthly incidence of the different physical maltreatment was analyzed using a QuasiPoisson regression model. RESULTS: We included 178 children (n = 127 boys, 71.3 %), 110 during the pandemic period, median age 5 months. AHT was diagnosed in 91 children, 55 had inflicted skeletal trauma (IST) and 46 had unexplained skin lesions (USL). Among the 91 patients with AHT, 86 had a subdural hematoma (95.6 %) and 40 had bridging veins thrombosis (44 %). The ophthalmological examination performed on 89 children (97.9 %) revealed retinal hemorrhages in 57 children (89.8 %). The incidence of AHT doubled during the months of COVID-19 lockdowns (rate ratio = 2; 95 % CI [1.1; 3.6], p = 0.03). No difference in monthly incidence was observed for IST and USL groups. CONCLUSION: A significant increase in AHT was observed during the months with lockdowns and curfews during the COVID-19 pandemic. This highlights the need for developing a national strategy to prevent physical abuse in children in this context.

Changes in adipose bone marrow and bone morphology in X-linked hypophosphatemic rickets.

INTRODUCTION: X-linked hypophosphatemic (XLH) rickets causes significant bone deformities in the lower limbs resulting from a bone mineralization defect. According to Frost's Mechanostat theory, compensatory modeling of the bones takes place during increased mechanical loads. In addition, mechanical stimuli modulate the differentiation of mesenchymal stem cells; common precursors to bone marrow adipocytes and osteoblasts. HYPOTHESIS: Bone deformities of the lower limbs lead to increased femoral bone mass and decreased fatty infiltration of the bone marrow (FIBM) in children with XLH rickets compared to a control group. PATIENTS AND METHODS: Eleven children (10.3years [6-17]) with XLH rickets and 22 healthy children (10.2years [5-15.5]) underwent lower limb Magnetic Resonance Imaging. A calculation of FIBM was performed at the mid-femur, as well as a calculation of the total bone cross-sectional area (CSA), the cortical CSA, the anteroposterior and mediolateral axes of the femur, bone marrow and the thickness of the femoral cortices. RESULTS: Total bone CSA, total cortical CSA and bone marrow CSA were higher in the XLH group than in the control group (p<0.05). The mid-lateral diameters of the femur and bone marrow were more elongated than those of the control group (p<0.001). Only the anterior cortex was thinned in the XLH group (p=0.001), while there was no difference with the control group for the posterior, medial and lateral cortices. The total percentage of FIBM was 72.81% [±3.95] and 77.4% [±5.52] for the XLH and control groups respectively (p<0.001). DISCUSSION: The increase in bone mass in the XLH population reflects an adaptation of bone tissue to the bone deformities present in this pathology. The decrease in FIBM indicates a lower risk of osteoporosis in the XLH population and may constitute a new monitoring parameter in this pathology. LEVEL OF STUDY: III; Case-control study.

Analysis of whole-body MRI artifacts in a pediatric population with a special emphasis on the effect of hands position.

PURPOSE: The purpose of this retrospective study was to determine the prevalence of artifacts on whole-body (WB) magnetic resonance imaging (MRI) examination in pediatric patients and identify their causes. MATERIALS AND METHODS: A total of 107 pediatric patients who underwent a total of 107 WB-MRI examinations, including short-tau inversion recovery (STIR) and T1-weighted sequences, were included. There were 62 girls and 45 boys with a mean age of 11 ± 3 (SD) years (age range: 2-16 years). WB-MRI examinations were analyzed for the presence of artifacts on STIR and T1-weighted sequences. Artifacts were further assigned to one of eight categories (motion, partial volume, cross-talk, phase sampling, susceptibility, equipment, noise, and "other") and 19 anatomical sites by a 4-year resident. Prevalence of artifacts were analyzed especially according to hands position during the examination for the upper limbs and patients' age. Age was expressed as a binary variable using median age (10 years) as the cut-off value. All qualitative variables were compared using chi-square test. RESULTS: A total of 3436 artifacts were found. The STIR sequences showed more "noise" artifacts (93/1038; 8.96%) and more "cross-talk" (102/1038; 9.83%) artifacts than T1-weighted sequences (12/1038 [1.16%] and 7/1038 [0.67%], respectively) (P < 0.001 for both). T1-weighted sequences showed more "equipment" (84/1038; 8.09%) and "stair-step" (a subset of "other") (41/1038; 3.95%) artifacts than the STIR sequences (39/1038 [3.76%] and 21/1038 [2.02%], respectively) (P < 0.001 and P = 0.01, respectively). T1-weighted sequences showed fewer artifacts on the wrists when the hands were under the bottom (P = 0.001). T1-weighted sequences showed less "equipment" artifacts when the hands were alongside the body (22/296; 7%) than on the abdomen (48/432; 11%) or under the bottom (14/128; 11%) (P < 0.001). STIR sequences showed more "motion" artifacts when the hands were on the abdomen (54/432; 13%) than alongside the body (30/296; 10%) or under the bottom (15/128; 12%) (P < 0.001). WB-MRI examinations had more "susceptibility" artifacts (38/960; 4%) and more "equipment" artifacts (81/960; 8.4%) in patients older than 10 years than in those under 10 years (23/752 [3.1%] and 42/752 [5.6%]) (P = 0.01 and P < 0.001, respectively). CONCLUSION: Artifacts on WB-MRI do not affect coronal STIR and T1-weighted sequences equally, so the use of both sequence types appears useful. Hands position should be considered with respect to both diagnostic benefit and safety.

Prospective Analysis of Muscle Adiposity in Children With X-linked Hypophosphatemic Rickets vs Control Children.

Context: Children with X-linked hypophosphatemic (XLH) rickets have muscle weakness that severely impairs their function. Intermuscular and intramuscular adipose tissue (IMAT and intraMAT, respectively) may contribute to this muscle weakness. Objective: This work aimed to compare IMAT and intraMAT in XLH children vs typically developing (TD) children. Methods: A prospective, monocentric cohort study was conducted of XLH (n = 11; aged 10.3 years [6-17]) and TD children (n = 22; aged 10.2 years [5-15.5]). All children underwent magnetic resonance imaging of the lower limbs; IMAT and intraMAT percentages were calculated after manual contouring of each muscle of the thigh and the deep fascia at mid-thigh level. Results: XLH children were comparable in age but shorter and heavier than TD children (P = .001 and P = .03, respectively). They had smaller muscle length and volume than TD children (P < .001) but there was no statistically significant difference in muscle cross-sectional area between the groups (P = .833). The total percentage of IMAT was higher in XLH children (8.66% vs 3.60% in TD children; P < .0001). In addition, though the total percentage of intraMAT did not differ significantly (12.58% and 10.85% in XLH and TD children, respectively; P = .143) intraMAT was statistically significantly higher in XLH children than TD children in 4 of the 13 muscles studied. Conclusion: Our results show that IMAT is higher in young children with XLH, independently of obesity and overweight. Further, these results will facilitate both the early prevention of functional and metabolic consequences of the increase in adipose tissue in XLH children.

Imaging findings in abusive head trauma (AHT).

Brain imaging plays a key role in accurately identifying abusive head trauma (AHT). An exact and rapid diagnosis is needed due to the extreme severity of AHT, since there is a risk of neurological sequelae and potentially fatal recurrence. Several medical specialists will work collaboratively to detect and confirm abuse in children: the radiologist has a leading role in this approach. This article describes the most common neuro-imaging patterns of AHT, including extra axial, intra axial, bony, and ligamentous lesions, with a special focus on the dating issue and the differential diagnosis.

Arteriovenous Cerebral High Flow Shunts in Children: From Genotype to Phenotype.

Objective: To study the genotypes and phenotypes of cerebral arteriovenous fistulas that drain or do not drain through the vein of Galen, and true vein of Galen aneurysmal malformations, in order to determine whether genotyping could help improve classification of these malformations and their management. Methods: We carried out a retrospective review of genetic and phenotypic data in databases of four centers. All children with cerebral arteriovenous fistula or vein of Galen aneurysmal malformations aged below 18 years at onset were included. We recorded the nature of the genetic variant or absence of variant, age at onset, type of malformation, symptoms at onset (hemorrhage, neurological deficit, hydrocephalus, incidental, and heart failure), type of venous drainage and the long-term outcome. Results: One hundred and fifteen children were included. Autosomal dominant variants were identified in 39% of patients. The most frequent variant affected was the RASA1 gene (25%) followed by EPHB4 (8%) and the HHT-associated genes (5%). HHT gene variants were only observed in pial arteriovenous fistula not draining into the vein of Galen; on the contrary, EPHB4 variants were only seen in genuine vein of Galen aneurysmal malformation. RASA1 variants were identified in all types of shunts. Conclusions: EPHB4 variants seem specific to the vein of Galen aneurysmal malformation, RASA1 variants are associated with either pial arteriovenous fistulas or with genuine VGAM and HHT gene variants seem specific to pial arteriovenous fistulas. The genetic data helps to classify these malformations and to guide treatment toward lowest risk of post-operative cerebral ischemic-hemorrhagic complications.

Is bridging vein rupture/thrombosis associated with subdural hematoma at birth?

BACKGROUND: The combination of bridging vein rupture/thrombosis and subdural hematoma in infants has recently gained attention as highly suggestive of abusive head trauma. While subdural hematomas are frequently observed at birth, there are no previous studies of bridging vein rupture/thrombosis prevalence in that context. OBJECTIVE: To evaluate the prevalence of bridging vein rupture/thrombosis in newborns with and without subdural hematoma. MATERIALS AND METHODS: This bicentric retrospective study (2012-2019) looked at all brain MRIs performed in neonates. We noted delivery method, demographic data and intracranial injuries and analyzed any clots at the vertex as potential markers of bridging vein rupture/thrombosis. RESULTS: We analyzed 412 MRIs in 412 neonates. Age was (mean ± standard deviation [SD]) 5.4±2.2 days and 312 (76%) infants were full term (38.3±2.9 weeks from last menstrual period). The delivery method was vaginal birth for 42% (n=174), cesarean section for 43% (n=179), and unknown for 14% (n=59). Subdural hematoma was present in 281 MRIs (68.0%, [95% confidence interval = 63.3-72.5]). Six MRIs showed at least one clot at the vertex, assumed to be possible bridging vein rupture/thrombosis (1.5%, [0.5-3.1%]). Only one MRI showed more than two clots at the vertex, in a context of maternal infection. There was no significant difference in terms of gestational age at birth, delivery method or the presence of subdural hematoma or parenchymal injuries between those 6 infants and the 406 others. CONCLUSION: Bridging vein rupture/thrombosis at birth is very rare and unlikely to be related to subdural hematoma.

Harmonisation of imaging protocols, radiation doses and image quality in gastrointestinal fluoroscopy examinations - multicentre study.

BACKGROUND: Paediatric gastrointestinal fluoroscopy examinations can impart varying amounts of radiation for the same patient size and exam type. OBJECTIVE: To investigate the variability of imaging protocol, radiation dose and image quality in paediatric fluoroscopy examinations in order to provide recommendations for the harmonisation and optimisation of local practices. MATERIALS AND METHODS: Five paediatric radiology departments performing fluoroscopically-guided contrast enema, micturating cystourethrography and upper gastrointestinal tract examinations participated in this study. Information on imaging protocols and radiation doses was retrospectively collected for more than 2,400 examinations. Image quality was analysed on clinical and phantom images. RESULTS: Patient doses showed great variability among centers with up to a factor of 5 for similar fluoroscopy times. The five departments had imaging protocols with major differences in fluoroscopy dose regulation curves and additional filtration. Image quality analysis on phantoms and patients images showed no major improvement in contrast, spatial resolution or noise when increasing the radiation dose. Age-based diagnostic reference levels using both dose area product and fluoroscopy time were proposed per procedure type. CONCLUSION: Disparities between centers and no correlation of radiation dose with image quality criteria create margins for optimisation. These results highlight the need for guidelines on fluoroscopy image quality and dose reference levels in paediatric gastrointestinal examinations to harmonise practices and optimise patient dose.

External validation of a commercially available deep learning algorithm for fracture detection in children.

PURPOSE: The purpose of this study was to conduct an external validation of a fracture assessment deep learning algorithm (Rayvolve®) using digital radiographs from a real-life cohort of children presenting routinely to the emergency room. MATERIALS AND METHODS: This retrospective study was conducted on 2634 radiography sets (5865 images) from 2549 children (1459 boys, 1090 girls; mean age, 8.5 ± 4.5 [SD] years; age range: 0-17 years) referred by the pediatric emergency room for trauma. For each set was recorded whether one or more fractures were found, the number of fractures, and their location found by the senior radiologists and the algorithm. Using the senior radiologist diagnosis as the standard of reference, the diagnostic performance of deep learning algorithm (Rayvolve®) was calculated via three different approaches: a detection approach (presence/absence of a fracture as a binary variable), an enumeration approach (exact number of fractures detected) and a localization approach (focusing on whether the detected fractures were correctly localized). Subgroup analyses were performed according to the presence of a cast or not, age category (0-4 vs. 5-18 years) and anatomical region. RESULTS: Regarding detection approach, the deep learning algorithm yielded 95.7% sensitivity (95% CI: 94.0-96.9), 91.2% specificity (95% CI: 89.8-92.5) and 92.6% accuracy (95% CI: 91.5-93.6). Regarding enumeration and localization approaches, the deep learning algorithm yielded 94.1% sensitivity (95% CI: 92.1-95.6), 88.8% specificity (95% CI: 87.3-90.2) and 90.4% accuracy (95% CI: 89.2-91.5) for both approaches. Regarding age-related subgroup analyses, the deep learning algorithm yielded greater sensitivity and negative predictive value in the 5-18-years age group than in the 0-4-years age group for the detection approach (P < 0.001 and P = 0.002) and for the enumeration and localization approaches (P = 0.012 and P = 0.028). The high negative predictive value was robust, persisting in all of the subgroup analyses, except for patients with casts (P = 0.001 for the detection approach and P < 0.001 for the enumeration and localization approaches). CONCLUSION: The Rayvolve® deep learning algorithm is very reliable for detecting fractures in children, especially in those older than 4 years and without cast.

Imaging patterns in pediatric hypophosphatasia.

Hypophosphatasia is a rare genetic disorder of calcium and phosphate metabolism due to ALPL gene mutations, which leads to abnormal mineralization of the bones and teeth. Hypophosphatasia is characterized by low serum alkaline phosphatase activity and a number of clinical signs, including failure to thrive, bone pain and dental issues. The diagnosis is suspected based on clinical, laboratory and imaging findings and confirmed by genetic testing. Diagnosis in children is often delayed due to a lack of disease awareness, despite specific imaging findings that are a cornerstone of the diagnosis. The recent approval of enzyme replacement therapy (bone-targeted recombinant tissue nonspecific alkaline phosphatase) has given imaging an important role in monitoring treatment efficacy. The aim of this pictorial essay is to review the imaging features of hypophosphatasia at diagnosis and during follow-up, including whole-body magnetic resonance imaging patterns.