Validating scoring systems for fracture healing in infants and young children: pilot study

Dating birth-related clavicular fractures: pediatric radiologists versus artificial intelligence

BACKGROUND

Fracture dating from skeletal surveys is crucial in the diagnosis and investigation of infant abuse. However, this task is challenging because of the subjective nature of the radiologic interpretation and the lack of ground truth. Researchers have used birth-related clavicle fractures as a surrogate to study the radiographic pattern of healing; however, they did not elucidate the accuracy performance of the radiologists in dating fractures.

OBJECTIVE

To determine the accuracy of radiologists in dating birth-related clavicle fractures and compare their performance to that achieved by computer algorithm.

MATERIALS AND METHODS

We used a previously assembled birth-related clavicle fracture database consisting of 416 anteroposterior clavicle radiographs as the study cohort. The average and standard deviation of the fracture age within this database were 24 days and 18 days, respectively. Three blinded radiologists independently estimated the ages of the clavicle fractures depicted in the radiographs within the database. We compared these estimation results to those made by a recently published deep-learning (DL) model conducted with the identical infant cohort. We calculated standard error metrics to compare the accuracy performances of the radiologists and the computer model.

RESULTS

The intra- and inter-reader agreements of the fracture age estimates by the radiologists were moderate to good. The radiologists estimated the fracture ages with a mean absolute error (MAE) of 6.1-7.1 days, and standard deviation of the absolute error of 6.3-8.3 days. The accuracy performances of the three radiologists were not significantly different from one another. In comparison, the DL model estimated the age of clavicle fractures with an MAE of 4.2 days, significantly lower than all of the radiologists (P < 0.001).

CONCLUSION

Three experienced pediatric radiologists dated clavicular fractures with moderate-good intra- and inter-reader agreements. The correlations between the radiologists' estimates and the ground truth were moderate to good. The fracture ages assigned by the DL model showed superior correlation with the ground truth compared to radiologists' dating estimates.

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.

Osteoimmunology: The effect of autoimmunity on fracture healing and skeletal analysis

Understanding factors that affect bone response to trauma is integral to forensic skeletal analysis. It is essential in forensic anthropology to identify if impaired fracture healing impacts assessment of post-traumatic time intervals and whether a correction factor is required. This paper presents a synthetic review of the intersection of the literature on the immune system, bone biology, and osteoimmunological research to present a novel model of interactions that may affect fracture healing under autoimmune conditions. Results suggest that autoimmunity likely impacts fracture healing, the pathogenesis however, is under researched, but likely multifactorial. With autoimmune diseases being relatively common, significant clinical history should be incorporated when assessing skeletal remains. Future research includes the true natural healing rate of bone; effect of autoimmunity on this rate; variation of healing with different autoimmune diseases; and if necessary, development of a correction factor on the natural healing rate to account for impairment in autoimmunity.