BACKGROUND The assessment of bone age and skeletal maturity and its comparison to chronological age is an important task in the medical environment for the diagnosis of pediatric endocrinology, orthodontics and orthopedic disorders, and legal environment in what concerns if an individual is a minor or not when there is a lack of documents. Being a time-consuming activity that can be prone to inter- and intra-rater variability, the use of methods which can automate it, like Machine Learning techniques, is of value. OBJECTIVE The goal of this paper is to present the state of the art evidence, trends and gaps in the research related to bone age assessment studies that make use of Machine Learning techniques. METHOD A systematic literature review was carried out, starting with the writing of the protocol, followed by searches on three databases: Pubmed, Scopus and Web of Science to identify the relevant evidence related to bone age assessment using Machine Learning techniques. One round of backward snowballing was performed to find additional studies. A quality assessment was performed on the selected studies to check for bias and low quality studies, which were removed. Data was extracted from the included studies to build summary tables. Lastly, a meta-analysis was performed on the performances of the selected studies. RESULTS 26 studies constituted the final set of included studies. Most of them proposed automatic systems for bone age assessment and investigated methods for bone age assessment based on hand and wrist radiographs. The samples used in the studies were mostly comprehensive or bordered the age of 18, and the data origin was in most of cases from United States and West Europe. Few studies explored ethnic differences. CONCLUSIONS There is a clear focus of the research on bone age assessment methods based on radiographs whilst other types of medical imaging without radiation exposure (e.g. magnetic resonance imaging) are not much explored in the literature. Also, socioeconomic and other aspects that could influence in bone age were not addressed in the literature. Finally, studies that make use of more than one region of interest for bone age assessment are scarce.

Juvenile idiopathic arthritis (JIA) is the most common paediatric rheumatic disease. It represents a group of heterogenous inflammatory disorders with unknown origin and is a diagnosis of exclusion in which imaging plays an important role. JIA is defined as arthritis of one or more joints that begins before the age of 16 years, persists for more than 6 weeks and is of unknown aetiology and pathophysiology. The clinical goal is early suppression of inflammation to prevent irreversible joint damage which has shifted the emphasis from detecting established joint damage to proactively detecting inflammatory change. This drives the need for imaging techniques that are more sensitive than conventional radiography in the evaluation of inflammatory processes as well as early osteochondral change. Physical examination has limited reliability, even if performed by an experienced clinician, emphasising the importance of imaging to aid in clinical decision-making. On behalf of the European Society of Musculoskeletal Radiology (ESSR) arthritis subcommittee and the European Society of Paediatric Radiology (ESPR) musculoskeletal imaging taskforce, based on literature review and/or expert opinion, we discuss paediatric-specific imaging characteristics of the most commonly involved, in literature best documented and clinically important joints in JIA, namely the temporomandibular joints (TMJs), spine, sacroiliac (SI) joints, wrists, hips and knees, followed by a clinically applicable point to consider for each joint. We will also touch upon controversies in the current literature that remain to be resolved with ongoing research. Key Points • Juvenile idiopathic arthritis (JIA) is the most common chronic paediatric rheumatic disease and, in JIA imaging, is increasingly important to aid in clinical decision-making. • Conventional radiographs have a lower sensitivity and specificity for detection of disease activity and early destructive change, as compared to MRI or ultrasound. Nonetheless, radiography remains important, particularly in narrowing the differential diagnosis and evaluating growth disturbances. • Mainly in peripheral joints, ultrasound can be helpful for assessment of inflammation and guiding joint injections. In JIA, MRI is the most validated technique. MRI should be considered as the modality of choice to assess the axial skeleton or where the clinical presentation overlaps with JIA.

Background: Individuals with cerebral palsy (CP) are less physically active, spend more time sedentary and have lower cardiorespiratory endurance as compared to typically developed individuals. RaceRunning enables highintensity exercise in individuals with CP with limited or no walking ability, using a three-wheeled running bike with a saddle and a chest plate for support, but no pedals. Training adaptations using this type of exercise are unknown. Methods: Fifteen adolescents/young adults (mean age 16, range 9-29, 7 females/8 males) with CP completed 12 weeks, two sessions/week, of RaceRunning training. Measurements of cardiorespiratory endurance (6-min RaceRunning test (6-MRT), average and maximum heart rate, rate of perceived exertion using the Borg scale (Borg-RPE)), skeletal muscle thickness (ultrasound) of the thigh (vastus lateralis and intermedius muscles) and lower leg (medial gastrocnemius muscle) and passive range of motion (pROM) of hip, knee and ankle were collected before and after the training period. Results: Cardiorespiratory endurance increased on average 34% (6-MRT distance; pre 576 ± 320 m vs. post 723 ± 368 m, p < 0.001). Average and maximum heart rate and Borg-RPE during the 6-MRT did not differ pre vs. post training. Thickness of the medial gastrocnemius muscle increased 9% in response to training (p < 0.05) on the more-affected side. Passive hip flexion increased (p < 0.05) on the less-affected side and ankle dorsiflexion decreased (p < 0.05) on the more affected side after 12 weeks of RaceRunning training. Conclusions: These results support the efficacy of RaceRunning as a powerful and effective training modality in individuals with CP, promoting both cardiorespiratory and peripheral adaptations.

BackgroundBone age assessment (BAA) is an important tool for diagnosis and in determining the time of treatment in a number of pediatric clinical scenarios, as well as in legal settings where it is used to estimate the chronological age of an individual where valid documents are lacking. Traditional methods for BAA suffer from drawbacks, such as exposing juveniles to radiation, intra- and interrater variability, and the time spent on the assessment. The employment of automated methods such as deep learning and the use of magnetic resonance imaging (MRI) can address these drawbacks and improve the assessment of age.ObjectiveThe aim of this paper is to propose an automated approach for age assessment of youth and young adults in the age range when the length growth ceases and growth zones are closed (14-21 years of age) by employing deep learning using MRI of the knee.MethodsThis study carried out MRI examinations of the knee of 402 volunteer subjects—221 males (55.0%) and 181 (45.0%) females—aged 14-21 years. The method comprised two convolutional neural network (CNN) models: the first one selected the most informative images of an MRI sequence, concerning age-assessment purposes; these were then used in the second module, which was responsible for the age estimation. Different CNN architectures were tested, both training from scratch and employing transfer learning.ResultsThe CNN architecture that provided the best results was GoogLeNet pretrained on the ImageNet database. The proposed method was able to assess the age of male subjects in the range of 14-20.5 years, with a mean absolute error (MAE) of 0.793 years, and of female subjects in the range of 14-19.5 years, with an MAE of 0.988 years. Regarding the classification of minors—with the threshold of 18 years of age—an accuracy of 98.1% for male subjects and 95.0% for female subjects was achieved.ConclusionsThe proposed method was able to assess the age of youth and young adults from 14 to 20.5 years of age for male subjects and 14 to 19.5 years of age for female subjects in a fully automated manner, without the use of ionizing radiation, addressing the drawbacks of traditional methods.