Research status of artificial intelligence and bone age assessment based on deep learning / 中华实用儿科临床杂志

Bone age can objectively reflect the human body growth and accurately assess the physical development level.Bone age assessment plays an important role in the growth and development, disease diagnosis and the monitoring of therapeutic efficacy in children and adolescents.In recent years, the artificial intelligence technology has been developed continuously.Applying artificial intelligence technology is expected to realize the automatic assessment of bone age.At present, the artificial intelligence technology of bone age assessment is mainly based on the deep learning (DL) algorithm.Although there have been many research on DL and bone age assessment, most are still in the experimental stage.This study reviews the research and progress of artificial intelligence technology based on DL applied to bone age assessment, aiming to provide reference and research ideas for relevant staff.

Application of knee joint imaging in bone age assement in adolescent children / 国际儿科学杂志

Bone age is a quantitative representation of the skeletal development pattern.X-ray imaging of the wrist with the Greulich-Pyle method is commonly used to assess bone age in clinic.In adolescent children, the sensitivity and specificity of the the Greulich-Pyle method are not sufficient because the bones of the wrist are already mature.In contrast, epiphyseal morphological changes in the knee joint throughout adolescence can provide information for the assessment of bone age in adolescent children, and the feasibility of knee joint bone age assessment has been verified.With the application of artificial intelligence (AI) in the medical field, the accuracy of AI interpretation of bone age is also recognized.One of the important uses of bone age assessment in adolescent children is to predict the remaining growth potential.Based on knee images, exploring the use of AI to build a model for predicting residual growth potential is a more meaningful research direction for clinical purposes.This paper reviews the anatomical characteristics of the knee joint, the application of knee joint imaging and the research progress of AI in bone age assessment.

Bone Age Assessment from Lateral Cephalograms Using Deep Learning Algorithms in the Indian Population

Purpose: The assessment of bone age has applications in a wide variety of fields: from orthodontics to immigration. The traditional non?automated methods are time?consuming and subject to inter? and intra?observer variability. This is the first study of its kind done on the Indian population. In this study, we analyse different pre?processing techniques and architectures to determine the degree of maturation (i.e. cervical vertebral maturation [CVM]) from cephalometric radiographs using machine learning algorithms. Methods: Cephalometric radiographs—labelled with the correct CVM stage using Baccetti et al. method—from 383 individuals aged between 10 and 36 years were used in the study. Data expansion and in?place data augmentation were used to handle high data imbalances. Different pre?processing techniques like Sobel filters and canny edge detectors were employed. Several deep learning convolutional neural network (CNN) architectures along with numerous pre?trained models like ResNet?50 and VGG?19 were analysed for their efficacy on the dataset. Results: Models with 6 and 8 convolutional layers trained on 64 × 64–size grayscale images trained the fastest and achieved the highest accuracy of 94%. Pre?trained ResNet?50 with the first 49 layers frozen and VGG?19 with 10 layers frozen to training had remarkable performances on the dataset with accuracies of 91% and 89%, respectively. Conclusions: Custom deep CNN models with 6–8 layers on 64 × 64–sized greyscale images were successfully used to achieve high accuracies to classify the majority classes. This study is a launchpad in the development of an automated method for bone age assessment from lateral cephalograms for clinical purposes.

Near-Adult Heights and Adult Height Predictions Using Automated and Conventional Greulich–Pyle Bone Age Determinations in Children with Chronic Endocrine Diseases

Objectives To validate adult height predictions (BX) using automated and Greulich–Pyle bone age determinations in children with chronic endocrine diseases. Methods Heights and near-adult heights were measured in 82 patients (48 females) with chronic endocrinopathies at the age of 10.45±2.12 y and at time of transition to adult care (17.98±3.02 y). Further, bone age (BA) was assessed using the conventional Greulich–Pyle (GP) method by three experts, and by BoneXpert™. PAH were calculated using conventional BP tables and BoneXpert™. Results The conventional and the automated BA determinations revealed a mean diference of 0.25±0.72 y (p=0.0027). The automated PAH by BoneXpert™ were 156.26 ± 0.86 cm (SDS ? 2.01 ± 1.07) in females and 171.75 ± 1.6 cm (SDS ? 1.29 ± 1.06) in males, compared to 153.95 ± 1.12 cm (SDS ? 2.56 ± 1.5) in females and 169.31 ± 1.6 cm (SDS?1.66±1.56) in males by conventional BP, respectively and in comparison to near-adult heights 156.38±5.84 cm (SDS?1.91±1.15) in females and 168.94±8.18 cm (SDS?1.72±1.22) in males, respectively. Conclusion BA ratings and adult height predictions by BoneXpert™ in children with chronic endocrinopathies abolish rater-dependent variability and enhance reproducibility of estimates thereby refning care in growth disorders. Conventional methods may outperform automated analyses in specifc cases.

Study on the correlation of bone age and bone mineral density with age, height and weight in children with short stature / 公共卫生与预防医学

Objective To study the correlation of bone age and bone mineral density with age, height and weight of short children. Methods Sixty-four short children who were consulted and treated at the author's hospital from January 2016 to October 2018 were selected as research subjects. The general information including age, sex, height and weight of the children were recorded. The ultrasound bone density test was carried out at the same time. The bone mineral density and bone age were evaluated through plain carpal bone radiograph. The relationship between different bone age and bone mineral density value with age, height and weight was analyzed. Results The actual age of the enrolled children was positively correlated with bone mineral density and bone age (boys r=0.658, 0.919, girls r=0.641, 0.906). The height of the enrolled children was positively correlated with bone mineral density and bone age (boy r=0.561, 0.326, girls r=0.586, 0.349). The weight of the enrolled children was positively correlated with bone mineral density and bone age (boys r=0.340, 0.314, girls r=0.395, 0.282). Conclusion The bone age and bone mineral density of short children were positively correlated with their age, height and weight. In clinical diagnosis and treatment, the use of bone age and bone mineral density as a guide can produce more significant effects, which can be used as scientific indicators for the evaluation and prediction of short children.

Technical Realization of Integrating Bone Age Artificial Intelligence Assessment System with Hospital RIS-PACS Network / 中国医疗器械杂志

OBJECTIVE@#To explore the integration method and technical realization of artificial intelligence bone age assessment system with the hospital RIS-PACS network and workflow.@*METHODS@#Two sets of artificial intelligence based on bone age assessment systems (CHBoneAI 1.0/2.0) were developed. The intelligent system was further integrated with RIS-PACS based on the http protocol in Python flask web framework.@*RESULTS@#The two sets of systems were successfully integrated into the local network and RIS-PACS in hospital. The deployment has been smoothly running for nearly 3 years. Within the current network setting, it takes less than 3 s to complete bone age assessment for a single patient.@*CONCLUSIONS@#The artificial intelligence based bone age assessment system has been deployed in clinical RIS-PACS platform and the "running in parallel", which is marking a success of Stage-I and paving the way to Stage-II where the intelligent systems can evolve to become more powerful in particular of the system self-evolution and the "running alternatively".

Comparison of the greulich-pyle method, the chn method and the China 05 method for assessing bone age in children and adolescents / 中国组织工程研究

BACKGROUND: In China, three bone age assessment methods have been widely used in the medical and sports fields, including the Greulich-Pyle atlas method (GP method), CHN scoring method (CHN method), and China 05 method. A large-sample empirical study is required to determine which method is more suitable for assessing bone age of children and adolescents. OBJECTIVE: To provide a scientific evidence for appropriate bone age evaluation standards for children and adolescents in the eastern developed areas, by comparing the GGP method, CHN method and China 05 method based on samples of healthy children from Shanghai. METHODS: A total of 4 152 healthy children and adolescents (2 185 boys and 1 967 girls) from the urban area of Shanghai were selected for the study. Their digital X-ray of the left hand and wrist were collected and evaluated by the GGP method, CHN method and China 05 method. The difference between the bone age and the chronological age was used to assess the applicability of different bone age standards. The study was approved by the Ethics Committee of Shanghai Research Institute of Sports Science, and informed consent was given by all parents of the enrolled students. RESULTS AND CONCLUSION: For the GP method, the difference between bone age and chronological age in both genders at the age of ≥ 8 years was-0.12 to-0.65 year with significant difference, except for 8-year-old girls. The significant age difference at the age of ≥ 9 years was 0.18 to 1.62 year, except for the 9-year-old age group. For the CHN method, the difference between bone age and chronological age among 6-17-year-old boys and 6-16-year-old girls was 0.42 to 1.56 years (P 0.05), and-0.60 in 18-year-old boys (P < 0.01); the age difference among 6-17-year-old girls was-0.01 to 0.56 year, and the difference was not significant in most age groups. Among the three methods, the result of China 05 method is relatively better, which is the best method that matches the current development of teenagers in Shanghai, suggesting that the China 05 method is more suitable for the eastern developed areas with economic level similar to Shanghai. All the three methods have some limitations. Considering the long-term growth trend of adolescents, it is necessary to revise the current bone age evaluation standards.

Correlation analysis of serum vitamin and trace element levels and bone age in short stature children / 公共卫生与预防医学

Objective To investigate the serum vitamin and trace element levels in children with short stature and their correlation with bone age. Methods Levels of serum VA and VD, and trace elements Ca, Fe, Zn, Mg, Cu, Pb and Cd were measured in 322 children who were referred for height consultation. Bone ages were evaluated and the correlation between bone age and serum vitamin and trace element levels was analyzed. Results The VA and VD deficiency rates of these 322 children were 22.05% and 34.16%, respectively. The deficiency rates of trace elements Ca, Fe and Zn were14.29%, 21.43% and 6.83%, respectively. The Pb excess rate was as high as 42.55%. The rates of bone age (BA) retardation in Group Ⅰ (short) and Group Ⅱ (slightly short) were 49.38% and 37.57%, respectively, which was significantly higher than that of Group Ⅲ (normal). The Ca level of BA retardation children was lower than that of the normal BA children in Group I. The VD level of BA retardation children was lower than that of the normal BA children in Group Ⅱ. BA was negatively correlated with VD, Ca, and Cu levels in children (r=-0.241; r=-0.136; r=-0.162), and positively correlated with Fe (r=0.286) . Conclusion There were significant abnormalities of vitamins and trace elements in short children. Children's bone age had a certain correlation with serum vitamin D, calcium, copper, and iron levels. Serum vitamin and trace element levels in children should be monitored to guide a reasonable diet to better promote child growth and development.

Study on myopia and bone age of children in Wenzhou / 国际眼科杂志(Guoji Yanke Zazhi)

@#AIM:To explore the relationship among bone age, age, height, weight and ocular biological parameters of myopic children in Whenzhou.<p>METHODS: Totally 410 cases(820 eyes)of myopic children with age distribution of 5-11 years old were collected. The height, weight, bone age and axial length(AL)of each child were measured, and body mass index(BMI)was calculated. Refractive was measured by medical optometry after rapid mydriasis, and the spherical equivalent(SE)was calculated. Children of each age group were divided into groups according to bone age difference(biological age-life age), and the prevalence of myopia in each group was statistically analyzed and compared among different bone age groups.<p>RESULTS: There was an association among the age, height, weight, BMI, SE and axis length(<i>r</i>s=0.853, 0.776, 0.291, -0.274 and 0.312; <i>P</i><0.05). There was no significant correlation between the age and the bone age(<i>rs</i>=0.045, <i>P</i>>0.05). 40.5% of myopic children are ahead of their bone age, 40.2% of them are in the normal range, 19.3% of them are behind(χ2=21.576, <i>P</i><0.05). Among the myopic children aged 5-11, 46.3% were boys and 53.7% were girls(χ2=17.322, <i>P</i><0.01). The proportion of girls was much higher than boys in children with advanced bone age.<p>CONCLUSION: There was an association between the age and height, weight, BMI, SE, axis length in Whenzhou. Among the children with low age myopia, there are more children with advanced bone age, especially girls.

Factors associated with Advanced Bone Age in Overweight and Obese Children / 대한소아소화기영양학회지

Correlación entre la edad cronológica y dental con los estadios de maduración vertebral en pacientes de 5 a 15 años / Correlation between the chronological and dental age with the vertebral maturation stages in patients from 5 to 15 years old

El uso de un método rápido y efectivo para la estimación de la maduración esquelética de los pacientes pediátricos es fundamental para la aplicación oportuna de tratamientos ortopédicos/ortodónticos. En Odontología Pediátrica, la toma de una radiografía panorámica, como método diagnóstico de rutina, puede servir para estimar con precisión el estadio de maduración en estos pacientes, mediante el cálculo de la edad dental. El objetivo del presente trabajo fue determinar la correlación entre las edades cronológica y dental con los estadios de maduración esquelética de las vértebras cervicales, a través del método estadístico no paramétrico con Rho de Spearman. Se utilizó un diseño observacional, transversal y analítico. La muestra consistió en 516 expedientes de pacientes entre los 5 y 15 años de edad, sistémicamente sanos, con radiografías panorámica y lateral de cráneo, tomadas en la misma fecha. Se determinó la edad cronológica de cada paciente según su historia clínica. Se realizó el cálculo de la edad dental de cada paciente con el método de Demirjian, y se determinó el estadio de maduración de vértebras cervicales con el método de Lamparski. Se determinó una correlación de 72 % entre la edad cronológica y la maduración ósea vertebral; una correlación del 66 % entre la edad dental y la maduración ósea, y una correlación del 86 % entre la edad cronológica y la dental. De acuerdo con estos resultados, tanto la edad cronológica y dental presentan una alta correlación con la edad de maduración vertebral. Se concluye así que la edad dental y cronológica son indicadores apropiados para estimar el estadio de maduración esquelética de los pacientes pediátricos.

The use of fast and effective methods for estimating the skeletal maturity for pediatric patients, is fundamental for the opportune application of orthopedic/orthodontic treatments. In pediatric dentistry, the panoramic radiography as a routine diagnostic method, can be used to estimate the stage of maturation in these patients, through the calculation of dental age. The aim of the present study is to determine the correlation between the chronological and dental ages, with the cervical vertebrae stages of skeletal maturity, through the non-parametric Spearman statistical method. An observational, transversal, and analytical design was employed. The sample consisted of 516 records from patients between 5 and 15 years of age, systemically healthy, with panoramic and lateral skull radiographs taken on the same date. The chronological age of each patient was determined according to the clinical history. Dental age of each patient was calculated with the Demirjian approach, and the stage of maturation of cervical vertebrae was determined by means of the Lamparski method. The results showed a correlation of 72 % between chronological age and bone maturation, a correlation of 66 % between dental age and bone maturation, and a correlation of 86 % between chronological and dental age. It is concluded that both chronological and dental age exhibit a high correlation with the correspondent stage of vertebral maturity. Thus, dental and chronological age are appropriate indicators to estimate, with high precision the stage of skeletal maturation in pediatric patients.

Accuracy of deep learning based bone age assessment system of children and adolescents in Guizhou / 中国医学影像技术

Objective: To explore the clinical applicability of a deep learning based bone age assessment system of children and adolescents in Guizhou. Methods: The left hand-wrist radiographs of 148 children and adolescents aged from 2 years to 17 years were assessed independently by three experts who were trained with the CH 05 RUS-CHN method, their mean estimates results were used as the reference standard. The estimates of the deep learning model (model group) and two residents (control group) were evaluated compared with the reference standard, respectively. mean absolute error (MAE) of bone age estimates and the percentage of samples with absolute error (AE) ≤1.0 year were calculated. Results: MAE of the model group was 0.295 [95%CI (0.238, 0.352)] years, with absolute error ≤1 years of 93.92% (139/148). Doctor A of the control group recorded MAE was 0.438 [95%CI (0.369, 0.508)] years, with 89.19% absolute error ≤1.0 years of 89.19% (132/148); doctor B recorded MAE of 0.360 [95%CI (0.295, 0.425)] years, with absolute error ≤1.0 years of 89.86% (133/148). The MAE of model group was significantly lower than that of doctor A (t=-3.071, P=0.002), but not for the doctor B (t=-1.563, P=0.120). Conclusion: When bone age assessed with the CH 05 RUS-CHN method for Guizhou children and adolescents, the deep learning model can estimate bone age with accuracy similar to or even better than that of control group radiologists.

Construction and clinical preliminary validation of an automaticbone age assessment model based on deep learning / 中华放射学杂志

Objective@#To build an automatic bone age assessment system based on China 05 Bone Age Standard and the latest deep learning technology, and preliminary clinical verification was carried out.@*Methods@#The left-hand radiographs of 5 000 children with suspected metabolic disorders were acquired from Wuxi Children′s Hospital. Among these cases, 2 351 patients were randomly chosen as training set, and 101 patients were randomly used as validation set. Four professional pediatric radiologists annotated the development stage according to the China 05 RUS-CHN standard with double-blind method. The mean value of the bone age assessed by experts was the reference standard which was used to train and validate the deep learning mothods based artificial intelligence (AI) model. Accuracy, mean absolute error (MAE), root mean squared error (RMSE) and time efficiency of bone age assessment were compared by using Chi-square test and t test and F test between resident doctors and AI model in the validation set.@*Results@#The MAE and RMSE was (0.37±0.35) years and 0.50 years between AI model and reference standard, respeactively. When the error range was within ±1.0, ±0.7 and ±0.5 years, the accuracy of model on the validation set was 94.1% (95/101), 89.1% (90/101), 74.3% (75/101) respectively. The accuracy between two resident doctors and AI prediction wasn′t statistical significant (P>0.05).@*Conclusion@#The AI model of bone age assessment based on deep learning is feasible and has the characteristics of high accuracy and efficiency.

Morning basal luteinizing hormone, a good screening tool for diagnosing central precocious puberty

PURPOSE: The standard method used to diagnose central precocious puberty (CPP) is the gonadotropin releasing hormone stimulation test (GnRHST). However, this test is inconvenient for children because it is time-consuming and requires multiple samples. This study aimed to determine the reliability of morning unstimulated luteinizing hormone (mLH) level when screening for CPP, with an emphasis on the influence of diurnal variation. METHODS: This study included 160 girls with signs of early puberty (SMR 2) under 8 years of age. They were classified as CPP or non-CPP based on their standard GnRHST. The auxological, biochemical, and hormonal characteristics of subjects were retrospectively evaluated. The prognostic value of single morning unstimulated gonadotropin level was examined for use in CPP screening. RESULTS: Of 160 patients, 121 (75.6%) presented with CPP, and 39 (24.4%) were determined to be prepubertal. The mLH/mFSH (morning unstimulated follicular stimulating hormone) ratio showed significant differences between the 2 groups (P<0.001). The mLH was correlated with GnRHST variables (r=0.532, P<0.001). The mLH cutoff point when screening for CPP was 0.22 IU/L, which had sensitivity and specificity of 69.4% and 82.1%, respectively. In regression analysis, bone age (BA) (odds ratio [OR], 1.018; 95% confidence interval [CI], 0.967–1.071; P=0.506) and body mass index (BMI) (OR, 0.874; 95% CI, 0.583–1.310; P=0.515) were not significant predictors. The mLH≥0.22 IU/L group (OR, 9.596; 95% CI, 3.853–23.900; P<0.001) was highly suggestive of CPP. CONCLUSIONS: In this study, single morning unstimulated luteinizing hormone had clinical efficacy for CPP screening, but BA advanced over chronological age and BMI was not useful for CPP screening.

Correlación en la determinación de la edad ósea radiológica mediante el método de Greulich y Pyle versus la evaluación automatizada utilizando el software BoneXpert / Correlation in radiological bone age determination using the Greulich and Pyle method versus automated evaluation using BoneXpert software

Resumen: Objetivo: Determinar el grado de correlación en la valoración de la edad ósea radiológica mediante el método de Greulich y Pyle versus la evaluación automatizada por el programa computacional BoneXpert® entre los años 2013-2016. Material y Método: Estudio de correlación de técnicas diag nósticas de 1500 radiografías de carpo para evaluar la edad ósea, en pacientes menores de 16 años pertenecientes a Clínica Alemana de Santiago. Las radiografías con evaluación de la edad ósea por el Atlas de Greulich y Pyle (GP) por 1 de 7 radiólogos pediatras fueron sometidas al programa BoneX pert (BE) para la evaluación automatizada de la edad ósea. Se tomó 100 casos al azar para un análisis/ re-análisis del método BE, para conocer su precisión. Se analizó el nivel de correlación de las medicio nes por coeficiente de correlación (r de Pearson) y la variabilidad de las mediciones mediante análisis de Bland-Altman. Resultados: Se incluyeron 1.493 casos, se excluyeron 7 por falla en técnica de la radiografía, 922 de sexo femenino (61.8%), mediana de edad cronológica 9.96 años y 11.12 años para los varones (p 0,001). La correlación entre la edad ósea manual GP y la edad ósea automatizada BE entre los lectores varió entre 0,91 y 0,93. El análisis de Bland-Altman indicó una diferencia promedio entre la edad ósea manual y la edad ósea BE de 0,19 años (IC 0,13 a 0,25). En el análisis/re-análisis de 100 casos al azar mediante BoneXpert, la correlación fue de 1,0. Conclusión: El análisis automatizado mediante BoneXpert permite una evaluación estandarizada, de baja variabilidad, y alta concordancia.

Abstract: Objective: To determine the degree of correlation in the radiological bone age assessment using the Greulich and Pyle method versus automated assessment through BoneXpert® software between 2013 and 2016. Material and Method: Correlation study of diagnostic techniques of 1500 carpal X-rays to assess bone age in patients under 16 years of age from Clínica Alemana de Santiago. X-rays with bone age assessment using the Atlas of Greulich and Pyle (GP) by 1 out of 7 pediatric radiologists, were analyzed using the BoneXpert (BE) software for automated bone age assessment. 100 cases were taken at random for analysis/re-analysis using the BoneXpert method to determine its accuracy. The level of correlation of the measurements was analyzed using the correlation coefficient (Pearson's r) and the variability of the measurements using the Bland-Altman analysis. Results: 1493 cases were assessed, seven were excluded due to failure in the X-ray technique, 922 females (61.8%), with a median chronological age of 9.96 years and 11.12 years for males (p 0.001). The correlation between manual bone age (GP) and automated bone age using BoneXpert method among radiologists ran ged from 0.91 to 0.93. The Bland-Altman analysis indicated an average difference between manual bone age and bone age using the BoneXpert method of 0.19 years (CI 0.13 to 0.25). In the analysis/ re-analysis of 100 random cases using the BoneXpert software, the correlation was 1.00 (100% accu racy). Conclusion: The automated analysis using BoneXpert allows for standardized, low-variability, and high-concordance assessment.

Advanced bone age as an indicator facilitates the diagnosis of precocious puberty / Idade óssea avançada como um indicador de facilitação do diagnóstico de puberdade precoce

Abstract Objective: Diagnosis of central precocious puberty has always been challenging in clinical practice. As an important method in the diagnosis of central precocious puberty, luteinizing hormone-releasing hormone stimulation test is complex and time-consuming. In many cases, clinical traits are inconsistent with luteinizing hormone-releasing hormone stimulation test results, therefore not reliable for diagnosis. In this study, the authors intended to find an indicator that predicts the results of the luteinizing hormone-releasing hormone stimulation test among subjects with early pubertal signs. Methods: Cases of 382 girls with early breast development before 8 years old and luteinizing hormone-releasing hormone stimulation test before 9 years old were included and underwent follow-up tests. Patients with peak luteinizing hormone level ≥5 IU/L were considered positive in the luteinizing hormone-releasing hormone stimulation test. Anthropometric data, body mass index, bone age evaluation, blood hormones levels of luteinizing hormone, estradiol, follicle-stimulating hormone, and uterine and ovarian volumes were analyzed. Results: Subjects with positive results in the initial test demonstrated early bone maturation, accelerated growth, and elevated basal blood luteinizing hormone, estradiol, and follicle-stimulating hormone levels, when compared with subjects with negative results in the initial test. Subjects with positive results in the follow-up test presented a more advanced bone age and more accelerated linear growth, when compared with subjects with negative results in the follow-up test. Conclusions: According to the statistical analysis, advanced bone age is the most effective predictor of the result of luteinizing hormone-releasing hormone stimulation test.

Resumo Objetivo: O diagnóstico da puberdade precoce central sempre foi complicado na prática clínica. Como um importante método no diagnóstico de puberdade precoce central, o teste de estimulação do hormônio liberador do hormônio luteinizante é complexo e demorado. Em muitos casos, as características clínicas são incompatíveis com os resultados do teste de estimulação do hormônio liberador do hormônio luteinizante e, assim, não são confiáveis para o diagnóstico. Neste estudo, visamos constatar um indicador que previsse os resultados do teste de estimulação do hormônio liberador do hormônio luteinizante entre indivíduos com sinais puberais precoces. Métodos: Foram incluídos casos de 382 meninas com desenvolvimento precoce das mamas antes dos 8 anos de idade e teste de estimulação do hormônio liberador do hormônio luteinizanteantes dos 9 anos e elas foram submetidas a testes de acompanhamento. Os resultados das pacientes com nível máximo de hormônio luteinizante ≥ 5 IU/L foram consideradas positivos no teste de estimulação do hormônio liberador do hormônio luteinizante. Foi feita uma análise dos dados antropométricos, do índice de massa corporal, da avaliação da idade óssea, dos níveis sanguíneos de hormônio luteinizante, volumes uterinos e ovarianos de estradiol (E2) e do hormônio folículo-estimulante. Resultados: Os indivíduos com resultado positive no teste inicial demonstraram maturação precoce do osso, crescimento acelerado e níveis sanguíneos elevados de hormônio luteinizante, estradiol e hormônio folículo-estimulante, em comparação aos indivíduos com resultados negativos no teste inicial. Os indivíduos com resultados positivos no teste de acompanhamento apresentaram um maior avanço na idade óssea e crescimento linear mais acelerado, em comparação aos indivíduos com resultados negativos no teste de acompanhamento. Conclusões: De acordo com a análise estatística, a idade óssea avançada é o indicador mais efetivo do resultado do teste de estimulação do hormônio liberador do hormônio luteinizante.

Applying Deep Learning in Medical Images: The Case of Bone Age Estimation / 대한의료정보학회지

OBJECTIVES: A diagnostic need often arises to estimate bone age from X-ray images of the hand of a subject during the growth period. Together with measured physical height, such information may be used as indicators for the height growth prognosis of the subject. We present a way to apply the deep learning technique to medical image analysis using hand bone age estimation as an example. METHODS: Age estimation was formulated as a regression problem with hand X-ray images as input and estimated age as output. A set of hand X-ray images was used to form a training set with which a regression model was trained. An image preprocessing procedure is described which reduces image variations across data instances that are unrelated to age-wise variation. The use of Caffe, a deep learning tool is demonstrated. A rather simple deep learning network was adopted and trained for tutorial purpose. RESULTS: A test set distinct from the training set was formed to assess the validity of the approach. The measured mean absolute difference value was 18.9 months, and the concordance correlation coefficient was 0.78. CONCLUSIONS: It is shown that the proposed deep learning-based neural network can be used to estimate a subject's age from hand X-ray images, which eliminates the need for tedious atlas look-ups in clinical environments and should improve the time and cost efficiency of the estimation process.

Maturation of cervical vertebrae and chronological age in children and adolescents

In maxillary orthopedics and related areas, it is essential to determine patient growth peak in order to provide timely diagnosis and treatments. This requires the use of biological indicators that enable children and adolescents to be assigned to maturation stages. The aim of this study was to determine the correlation between cervical vertebrae maturation stages and chronological age in children and adolescents. In this study were evaluated 93 lateral cranium radiographs of 6to 17yearold patients who visited the Postgraduate Maxillary Orthopedics Clinic at the School of Dentistry at Universidad del Zulia. Two examiners made independent assessments of cervical vertebrae maturation stage using the method described by Baccetti et al. For each stage, descriptive statistics for chronological age were evaluated, classified according to sex. In addition, parametric and nonparametric tests were performed in which p <0.05 was considered significant. Mean age of the children and adolescents studied was 9.6 years, with standard deviation 2.5 years. The correlation coefficient (r=0.771) certified a high positive correlation between bone maturation and chronological age. This correlation coefficient was highly positive for girls (r=0.858) and moderately positive for boys (r=0.688). The model obtained explains 59.4 % of the variation between bone maturation and chronological age, evidencing an average age increase of three years when maturation stage increases by approximately 1 year. The results suggest that although the degree of covariance between chronological age and matu ration stages was highly positive in this study, chronological age does not allow bone maturation to be determined precisely, since it may be influenced by genetic and/or environmental factors (AU)

En ortopedia maxilar y áreas afines resulta esencial determinar el pico de crecimiento de los pacientes para establecer diagnósticos y tratamientos oportunos para lo cual es necesario utilizar indicadores biológicos, que permiten ubicar a los niños y adolescentes en estadios de maduración. El objetivo de este estudio fue determinar la correlación de los estadios de maduración de las vértebras cervicales según la edad cronológica en niños y adolescentes. Se evaluaron 93 imágenes de radiografías lateral de cráneo, de pacientes entre 6 y 17 años de edad que asistieron a la clínica del Posgrado de Ortopedia Maxilar de la Facultad de Odontología de La Universidad del Zulia, dos examinadores estimaron de forma independiente el estadio de maduración de las vértebras cervicales, utilizando el método descrito por Baccetti et al. y para cada estadio se evaluaron los estadísticos descriptivos de la edad cronológica categorizando según sexo, además se realizaron pruebas paramétricas y no paramétricas donde un p <0,05 fue considerado como significativo. La edad media de los niños y adolescentes estudiados resultó de 9,6 años y una desviación típica de 2,5 años. El coeficiente de correlación (r=0,771) certificó una correlación positiva alta entre maduración ósea y edad cronológica, igual producto se obtuvo en el caso de las niños y adolescentes del sexo femenino (r=0,858), mientras los del sexo masculino obtuvieron una correlación positiva moderada (r= 0,688). El modelo obtenido explica el 59,4 % de la variación entre maduración ósea y edad cronológica, lo cual evidencia el aumento de la edad promedio en tres años, cuando el estadio de maduración aumenta 1 año aproximadamente. Los resultados registrados sugieren que, aunque el grado de covarianza entre edad cronológica y estadios de maduración en esta investigación fue positiva alta, la edad cronológica no permite determinar con exactitud la maduración ósea, pudiendo estar influenciada por factores genéticos y/o ambientales (AU)

Comparação entre métodos de avaliação de altura final em adolescentes com baixa estura variante do normal / Comparison of methods for final height assessment in adolescents with a normal variant short stature

INTRODUCTION: Patients with low stature normal variant growth have peculiar evolutionary patterns making it difficult to precisely define when final stature will be reached, since prediction methods are based on parameters of difficult quantification, such as bone age. OBJECTIVE: To assess the agreement between two methods for prediction of final height based on family target range regarding the final height reached by adolescents with a diagnosis of normal variant short stature. METHODS: Thirty-three subjects were evaluated using height of parents for the calculation of family target range and Bayley-Pinneau and Tanner-Whitehouse methods for prediction of final height. Spearman correlation coefficient was calculated to correlate final height with the mean of the family target range, and the St. Laurent concordance coefficient was used to assess concordance between final stature and predictive methods. RESULTS: 87.9% (29/33) subjects kept short stature at the end of growth and 90.9% (30/33) had a final height within family target range. A very strong positive correlation (Cs = 0.77; p < 0.01) was observed between parental mean and final height. Bayley-Pinneau method showed a 0.47 concordance coefficient with final height (95% CI: 0.34; 0.57), and Tanner-Whitehouse 3 method showed a concordance coefficient of 0.58 (95% CI: 0.41; 0.75. CONCLUSION: The strong positive correlation observed demonstrates the significant influence of parental height on final height. Neither method showed good concordance when used as a predictor of final height, with height values being overestimated.

INTRODUÇÃO: Pacientes com baixa estatura variante normal do crescimento têm padrões evolutivos peculiares dificultando definir com precisão quando a estatura final será atingida, visto que os métodos de previsão baseiam-se em parâmetros de difícil quantificação, como a idade óssea. OBJETIVO: Avaliar a concordância entre dois métodos de previsão da estatura final e do canal familiar com a altura final atingida (padrão ouro) por adolescentes com diagnóstico de variantes normais da baixa estatura atendidos em ambulatório de avaliação de problemas de crescimento. MÉTODO: Foram avaliados 33 sujeitos utilizando-se as estaturas dos pais para o cálculo do canal familiar e da média parental e os métodos Bayley-Pinneau e Tanner- Whitehouse 3 para as previsões de estatura final. Também foram calculados o coeficiente de correlação de Spearman para correlacionar a estatura final com a média do canal familiar, e o coeficiente de concordância de St. Laurent para avaliar a concordância entre a estatura final e os métodos de previsão. RESULTADOS: 87,9% (29/33) permaneceram com Baixa Estatura ao término do crescimento e 90,9% (30/33) apresentaram estatura final dentro do canal familiar. Observou-se correlação positiva muito forte (Cs = 0,77; p < 0,01) entre a média parental e a altura final. O método de Bayley-Pinneau apresentou coeficiente de concordância com a altura final de 0,47 (IC 95%: 0,34; 0,57), o de TW3, 0,58 (IC 95%: 0,41; 0,75). CONCLUSÃO: A correlação positiva forte demonstra a influência significativa da altura dos pais na estatura final. Nenhum dos dois métodos apresentou boa concordância ao serem utilizados como preditores de estatura final, pois os valores das alturas foram superestimados principalmente pelo método de Bayley-Pinneau.

Prospective study on effect of body composition increase on bone age development in children aged 3 to 10 years / 中华实用儿科临床杂志

Objective To verify the influence of body composition content and different distribution on bone age development,and establish a healthy lifestyle that benefits bone age development. Methods The prospective cohort study was conducted in the children aged 3 to 10 years at the outpatient and the body component analysis and bone age evaluation were tested during January 1st ,2014 to August 31th ,2015 at the Department of Child Health Care,Wuhan Children′s Hospital(Wuhan Maternal and Child Healthcare Hospital),Tongji Medical College,Huazhong University of Science & Technology,and they were followed up for 1 year. During the follow - up of body weight,height,body compo-sition and bone age,the effect of different body composition distribution and the increase rate on bone age development was investigated. Results Total 341 children were selected,of whom 166 cases were male,175 cases were female,and their mean age were 3. 3 - 10. 8 years. The annual growth rate of bone age ranged from 0. 62 to 1. 37 years in different age groups. Adipose tissue was the fastest growing composition(2. 60 kg/ year),followed by lean body tissue(2. 47 kg/ year),while the slowest growing composition was bone mineral(0. 14 kg/ year). The prospective factors for fast bone age growth were the content of lean body tissue(β = 14. 13),skeletal muscle(β = 12. 79),bone minerals(β = 6. 26), salts(β = 5. 91)and lean body tissue of four limbs(1. 74≤β≤20. 79),longer circumferences of chest(β = 2. 02),ab-domen(β = 1. 37),and left arms(β = 1. 36),more fat thickness of abdomen(β = 13. 10),right and left arms(β = 9. 47, 6. 07)(all P < 0. 01). On the other hand,the obstructive factors of fast bone age growth were higher content of total body water(β = - 5. 99),extracellular fluid(β = - 1. 60),trunk lean body tissue(β = - 7. 67),and longer circum-ferences of right and left thighs(β = - 1. 81,- 1. 77),and high fat thickness of left thighs(β = - 7. 99)(all P <0. 05). Conclusions A healthier lifestyle can defer bone development effectively,such as long - term aerobic exercise,less weight - bearing movement of the limbs (especially in upper limbs),and more water intake,which may result in a taller ultimate height.