Artificial intelligence for radiological paediatric fracture assessment: a systematic review.

BACKGROUND: Majority of research and commercial efforts have focussed on use of artificial intelligence (AI) for fracture detection in adults, despite the greater long-term clinical and medicolegal implications of missed fractures in children. The objective of this study was to assess the available literature regarding diagnostic performance of AI tools for paediatric fracture assessment on imaging, and where available, how this compares with the performance of human readers. MATERIALS AND METHODS: MEDLINE, Embase and Cochrane Library databases were queried for studies published between 1 January 2011 and 2021 using terms related to 'fracture', 'artificial intelligence', 'imaging' and 'children'. Risk of bias was assessed using a modified QUADAS-2 tool. Descriptive statistics for diagnostic accuracies were collated. RESULTS: Nine eligible articles from 362 publications were included, with most (8/9) evaluating fracture detection on radiographs, with the elbow being the most common body part. Nearly all articles used data derived from a single institution, and used deep learning methodology with only a few (2/9) performing external validation. Accuracy rates generated by AI ranged from 88.8 to 97.9%. In two of the three articles where AI performance was compared to human readers, sensitivity rates for AI were marginally higher, but this was not statistically significant. CONCLUSIONS: Wide heterogeneity in the literature with limited information on algorithm performance on external datasets makes it difficult to understand how such tools may generalise to a wider paediatric population. Further research using a multicentric dataset with real-world evaluation would help to better understand the impact of these tools.

Diagnostic assessment of foetal brain malformations with intra-uterine MRI versus perinatal post-mortem MRI.

PURPOSE: To evaluate differences in diagnostic yield of intra-uterine foetal (iuMR) and post-mortem MRI (PMMR) for complex brain malformations, using autopsy as the reference standard. METHODS: In this retrospective, multicentre study spanning 2 years, we reviewed 13 terminated singleton pregnancies with a prenatal ultrasound finding of complex foetal cerebral abnormalities, referred for both iuMR and PMMR. The iuMR and PMMR studies of the brain were reported independently by two groups of radiologists, blinded to each other's reports. Descriptive statistics were used to compare differences in intracranial abnormalities with autopsy (and genetic testing, where present) as reference standard. RESULTS: The median gestational age at termination was 24.6 weeks (IQR 22-29) with median time between delivery and PMMR of 133 h (IQR 101-165). There was full concordance between iuMR and PMMR findings and autopsy in 2/13 (15.3%) cases. Partial concordance between both imaging modalities was present in 6/13 (46.2%) and total discordance in the remainder (5/13, 38.5%). When compared to autopsy, PMMR missed important key findings specifically for neuronal migration and cerebellar anomalies, whereas iuMR appeared to overcall CSF space abnormalities which were less crucial to reaching the final overall diagnosis. CONCLUSIONS: iuMR should be performed to improve foetal phenotyping where there is a prenatal ultrasound for complex foetal brain abnormalities. Reliance on PMMR alone is likely to result in misdiagnosis in a majority of cases.

Feasibility of Postmortem Imaging Assessment of Brain: Liver Volume Ratios with Pathological Validation.

INTRODUCTION: Organ volumes at postmortem magnetic resonance imaging (PMMR) should reflect autopsy organ weights, and thus brain:liver volume ratios on imaging could be a surrogate for weight volume ratios at autopsy to indicate fetal growth restriction (FGR). This study aims to determine whether imaging-based organ volume ratios can replace autopsy organ weight ratios. Materials and Meth ods: An unselected cohort of perinatal deaths underwent PMMR prior to autopsy. Semiautomated brain and liver volumes were compared to autopsy organ weights and ratios. Ratios were compared using Bland-Altman plots, and intra- and interobserver variability was assessed. RESULTS: A total 49 fetuses (25 male, 51%) at 17-42 weeks gestation were -assessed. There was a reasonable correlation between autopsy-derived brain:liver weight ratios (AB:LwR) and imaging-derived brain:liver volume ratios (IB:LvR; r = 0.8). The mean difference between AB:LwR and IB:LvR was +0.7 (95% limits of agreement range -1.5 to +2.9). In a small subset where FGR was present, the optimal IB:LvR ≥5.5 gave 83.3% sensitivity and 86.0% specificity for diagnosis. There was acceptable agreement within readers (mean difference in IB:LvRs 0.77 ± 2.21) and between readers -0.36 ± 0.68. CONCLUSION: IB:LvR provides a surrogate evaluation of AB:LwRs, and may be used as a marker of FGR where autopsy is declined.

Smartphone applications in paediatric radiology: availability and authority.

BACKGROUND: With the widespread ownership of smartphones, many health care professionals question the degree to which medically related smartphone applications are reliable. OBJECTIVES: To assess the variety of smartphone applications relating to paediatric radiology and the presence of health care professional involvement in their development. As a secondary objective, we explore whether there are gaps within the paediatric radiology app market. MATERIALS AND METHODS: The most popular smartphone marketplaces (Apple iTunes App Store, Blackberry Mobile Market, Google Play Android Market, Nokia Ovi, Samsung and Microsoft Windows Marketplace) were searched for terms relating to paediatric radiology. Cost, review ratings, number of downloads, health care involvement and target audience were recorded. RESULTS: Nine paediatric radiology applications were found in the Apple iTunes App Store and nine in the Google Play Android Market. The target audiences for all applications were health care professionals. None were available for patients or their caregivers. All applications were reported to have medical expertise in their development. CONCLUSION: All paediatric radiology applications were developed with the aid of a health care professional. Due to the small number available online, there is a potential gap in the marketplace for further applications in this field, possibly aimed at patients and their families.