Reliability of the Greulich and Pyle method for chronological age estimation and age majority prediction in a Spanish sample

Alcina, M.; Lucea, Alina; Salicrú, Miquel; Turbón, Daniel

doi:10.1007/s00414-017-1760-x

Cited by 10 publications

(13 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In short, previous deep learning-based BAA systems all employ the GP method. Thus, they suffer from the lack of measurement repeatability and the systematic errors that are inherent to the GP method [27]. In contrast, this study presents a TW3-based, complete end-to-end BAA system using deep neural networks.…”

Section: Related Workmentioning

confidence: 99%

TW3-Based Fully Automated Bone Age Assessment System Using Deep Neural Networks

et al. 2019

View full text Add to dashboard Cite

Deep learning technology has rapidly evolved in recent years. Bone age assessment (BAA) is a typical object detection and classification problem that would benefit from deep learning. Convolutional neural networks (CNNs) and their variants are hence increasingly used for automating BAA, and they have shown promising results. In this paper, we propose a complete end-to-end BAA system to automate the entire process of the Tanner-Whitehouse 3 method, starting from localization of the epiphysis-metaphysis growth regions within 13 different bones and ending with estimation of the corresponding BA. Specific modifications to the CNNs and other stages are proposed to improve results. In addition, an annotated database of 3300 X-ray images is built to train and evaluate the system. The experimental results show that the average top-1 and top-2 prediction accuracies for skeletal bone maturity levels for 13 regions of interest are 79.6% and 97.2%, respectively. The mean absolute error and root mean squared error in age prediction are 0.46 years and 0.62 years, respectively, and accuracy within one year of the ground truth of 97.6% is achieved. The proposed system is shown to outperform a commercially available Greulich-Pyle-based system, demonstrating the potential for practical clinical use. INDEX TERMS Bone age assessment, deep learning, GP, TW3.

show abstract

Section: Related Workmentioning

confidence: 99%

TW3-Based Fully Automated Bone Age Assessment System Using Deep Neural Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Therefore, it will be a waste of money and time. There are many reported methods that used bones for age estimation and they are subdivided into three main categories: image processing [29][30][31], by comparing with bone age atlas [32][33][34], and statistical regression analysis [35][36][37][38]. As being compared with the atlas, as the name proposes, X-ray image of the subjects are being made comparison with an atlas which contains a set of radiographs of identified gender and age.…”

Section: Results and Analysismentioning

confidence: 99%

Random forest age estimation model based on length of left hand bone for Asian population

Darmawan¹,

Abidin²,

Kasim³

et al. 2020

IJECE

View full text Add to dashboard Cite

In forensic anthropology, age estimation is used to ease the process of identifying the age of a living being or the body of a deceased person. Nonetheless, the specialty of the estimation models is solely suitable to a specific people. Commonly, the models are inter and intra-observer variability as the qualitative set of data is being used which results the estimation of age to rely on forensic experts. This study proposes an age estimation model by using length of bone in left hand of Asian subjects range from newborn up to 18-year-old. One soft computing model, which is Random Forest (RF) is used to develop the estimation model and the results are compared with Artificial Neural Network (ANN) and Support Vector Machine (SVM), developed in the previous case studies. The performance measurement used in this study and the previous case study are R-square and Mean Square Error (MSE) value. Based on the results produced, the RF model shows comparable results with the ANN and SVM model. For male subjects, the performance of the RF model is better than ANN, however less ideal than SVM model. As for female subjects, the RF model overperfoms both ANN and SVM model. Overall, the RF model is the most suitable model in estimating age for female subjects compared to ANN and SVM model, however for male subjects, RF model is the second best model compared to the both models. Yet, the application of this model is restricted only to experimental purpose or forensic practice.

show abstract

“…The intraobserver result appeared in the same direction. Comparing with chronological age, this study found differences approximately half a year for girls and 4 months for boys (Alcina et al, 2015).…”

Section: Observer Dependencementioning

confidence: 54%

“…Furthermore, using the same method, but different observers may generate different results (Hackman, 2012) Alcina and colleague studied the application of Greulich and Pyle method in Spanish population and also analyzed inter-observer and intra-observer error (Alcina et al, 2015). It was found that, although not clinically significant, inter-observer mean difference was less than a month but the deviation might be up to 6 months.…”

Section: Observer Dependencementioning

confidence: 99%

See 1 more Smart Citation

Age Estimation Methods Using Hand and Wrist Radiographs in a Group of Thai

Benjavongkulchai

View full text Add to dashboard Cite

Introduction: Age estimation takes part in a variety of situations, such as growth observation, immigrant registration, legal penalty judgment and body identification. Chronological age usually corresponds with stages of skeletal and dental development. Age estimation by using hand and wrist radiography is the first method of choice for many cases because it is uncomplicated, inexpensive and non-invasive. However, the validity of the result is still questionable mainly because of the influence of ethnic differences. Objectives: The primary aim of this study was to evaluate the accuracy and reliability of the commonly used age estimation methods on Thai population. The secondary aims were to compare the results between different methods and to find any possible relationship on Thai population. Materials and methods: Hand and wrist radiographs from the Department of Radiology, Faculty of Dentistry, Chulalongkorn University were collected. The radiographs were taken between 2011 – 2016 and the patients must not have history of diseases that affect skeletal development. ‘Greulich and Pyle’, ‘Tanner and Whitehouse (TW3-RUS)’, and ‘Fishman’ method were applied for each radiograph. The results from each method and the chronological age were compared using Friedman’s rank test (p<0.05) followed by a Wilcoxon signed ranks test with Bonferroni correction. Results and Discussion: The estimated ages from the three methods were significantly different from the chronological age (p<0.002), except for ‘Tanner and Whitehouse’ in male which showed no significant difference. Overall, the results from each method tended to be overestimated although the tendency of underestimation was found particularly in younger groups. The presence of discordance supported the influence of ethnical factor and secular change on skeletal maturation rate. Conclusions: Tanner and Whitehouse TW3-RUS method was more accurate in predicting the age of contemporary Thais; however, a further adaptation of the method to reduce the discrepancies in late teenagers is recommended.

show abstract

Reliability of the Greulich and Pyle method for chronological age estimation and age majority prediction in a Spanish sample

Cited by 10 publications

References 54 publications

TW3-Based Fully Automated Bone Age Assessment System Using Deep Neural Networks

TW3-Based Fully Automated Bone Age Assessment System Using Deep Neural Networks

Random forest age estimation model based on length of left hand bone for Asian population

Age Estimation Methods Using Hand and Wrist Radiographs in a Group of Thai

Contact Info

Product

Resources

About