Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach (Preprint)

BACKGROUND Bone age assessment (BAA) is used in numerous pediatric clinical settings as well as in legal settings when entities need an estimate of chronological age (CA) when valid documents are lacking. The latter case presents itself as critical as the law is harsher for adults and granted rights along with imputability changes drastically if the individual is a minor. Traditional BAA methods have drawbacks such as exposure of minors to radiation, they do not consider factors that might affect the bone age, and they mostly focus on a single region. Given the critical scenarios in which BAA can affect the lives of young individuals, it is important to focus on the drawbacks of the traditional methods and investigate the potential of estimating CA through BAA. OBJECTIVE This study aims to investigate CA estimation through BAA in young individuals aged 14-21 years with machine learning methods, addressing the drawbacks of research using magnetic resonance imaging (MRI), assessment of multiple regions of interest, and other factors that may affect the bone age. METHODS MRI examinations of the radius, distal tibia, proximal tibia, distal femur, and calcaneus were performed on 465 men and 473 women (aged 14-21 years). Measures of weight and height were taken from the subjects, and a questionnaire was given for additional information (self-assessed Tanner Scale, physical activity level, parents' origin, and type of residence during upbringing). Two pediatric radiologists independently assessed the MRI images to evaluate their stage of bone development (blinded to age, gender, and each other). All the gathered information was used in training machine learning models for CA estimation and minor versus adult classification (threshold of 18 years). Different machine learning methods were investigated. RESULTS The minor versus adult classification produced accuracies of 0.90 and 0.84 for male and female subjects, respectively, with high recalls for the classification of minors. The CA estimation for the 8 age groups (aged 14-21 years) achieved mean absolute errors of 0.95 years and 1.24 years for male and female subjects, respectively. However, for the latter, a lower error occurred only for the ages of 14 and 15 years. CONCLUSIONS This study investigates CA estimation through BAA using machine learning methods in 2 ways: minor versus adult classification and CA estimation in 8 age groups (aged 14-21 years), while addressing the drawbacks in the research on BAA. The first achieved good results; however, for the second case, the BAA was not precise enough for the classification.

Download Full-text

Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach

JMIR Medical Informatics ◽

10.2196/18846 ◽

2020 ◽

Vol 8 (9) ◽

pp. e18846

Author(s):

Ana Luiza Dallora ◽

Ola Kvist ◽

Johan Sanmartin Berglund ◽

Sandra Diaz Ruiz ◽

Martin Boldt ◽

...

Keyword(s):

Machine Learning ◽

Age Groups ◽

Bone Age ◽

Chronological Age ◽

Learning Methods ◽

Age Assessment ◽

Male And Female ◽

Machine Learning Methods ◽

Bone Age Assessment ◽

Female Subjects

Background Bone age assessment (BAA) is used in numerous pediatric clinical settings as well as in legal settings when entities need an estimate of chronological age (CA) when valid documents are lacking. The latter case presents itself as critical as the law is harsher for adults and granted rights along with imputability changes drastically if the individual is a minor. Traditional BAA methods have drawbacks such as exposure of minors to radiation, they do not consider factors that might affect the bone age, and they mostly focus on a single region. Given the critical scenarios in which BAA can affect the lives of young individuals, it is important to focus on the drawbacks of the traditional methods and investigate the potential of estimating CA through BAA. Objective This study aims to investigate CA estimation through BAA in young individuals aged 14-21 years with machine learning methods, addressing the drawbacks of research using magnetic resonance imaging (MRI), assessment of multiple regions of interest, and other factors that may affect the bone age. Methods MRI examinations of the radius, distal tibia, proximal tibia, distal femur, and calcaneus were performed on 465 men and 473 women (aged 14-21 years). Measures of weight and height were taken from the subjects, and a questionnaire was given for additional information (self-assessed Tanner Scale, physical activity level, parents' origin, and type of residence during upbringing). Two pediatric radiologists independently assessed the MRI images to evaluate their stage of bone development (blinded to age, gender, and each other). All the gathered information was used in training machine learning models for CA estimation and minor versus adult classification (threshold of 18 years). Different machine learning methods were investigated. Results The minor versus adult classification produced accuracies of 0.90 and 0.84 for male and female subjects, respectively, with high recalls for the classification of minors. The CA estimation for the 8 age groups (aged 14-21 years) achieved mean absolute errors of 0.95 years and 1.24 years for male and female subjects, respectively. However, for the latter, a lower error occurred only for the ages of 14 and 15 years. Conclusions This study investigates CA estimation through BAA using machine learning methods in 2 ways: minor versus adult classification and CA estimation in 8 age groups (aged 14-21 years), while addressing the drawbacks in the research on BAA. The first achieved good results; however, for the second case, the BAA was not precise enough for the classification.

Download Full-text

A Novel Approach for Bone Age Assessment using Deep Learning

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit21731 ◽

2021 ◽

pp. 67-75

Author(s):

Nishan B. Poojary ◽

Prathamesh G. Pokhare ◽

Pratik P. Poojary ◽

Charmi D. Raghavani ◽

Dr. Jayashree Khanapuri

Keyword(s):

Transfer Learning ◽

Age Groups ◽

Bone Age ◽

Absolute Error ◽

Assessment Model ◽

Age Assessment ◽

Male And Female ◽

Novel Approach ◽

Proposed Model ◽

Bone Age Assessment

In this paper, we propose a detailed approach to create a Bone age assessment model. Bone age assessment is a common medical practice in the assessment of child development, who are less than 18 years of age. In this proposed model, the Xception architecture is being used for transfer learning. Using feature extraction and transfer learning, the pre-trained convolutional neural network were custom trained. The dataset used for training the model is obtained from the Kaggle RNSA Bone Age dataset containing 12811 male and female bone images of different age groups. Finally, we were able to attain a mean absolute error (MAE) of 8.175 months in male and female patients, which aligns with our initial goal of achieving MAE in under a year.

Download Full-text

Deep Learning and Classic Machine Learning Approach for Automatic Bone Age Assessment

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) ◽

10.1109/acirs.2019.8935965 ◽

2019 ◽

Cited By ~ 1

Author(s):

Ari Wibisono ◽

Mei Silviana Saputri ◽

Petrus Mursanto ◽

Joachim Rachmad ◽

Alberto ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Bone Age ◽

Learning Approach ◽

Age Assessment ◽

Machine Learning Approach ◽

Bone Age Assessment

Download Full-text

Bone Age Assessment for Lower Age Groups Using Triplet Network in Small Dataset of Hand X-Rays

Intelligent Human Computer Interaction - Lecture Notes in Computer Science ◽

10.1007/978-3-030-68449-5_15 ◽

2021 ◽

pp. 142-153

Author(s):

Shipra Madan ◽

Tapan Gandhi ◽

Santanu Chaudhury

Keyword(s):

Age Groups ◽

Bone Age ◽

X Rays ◽

Age Assessment ◽

Bone Age Assessment ◽

Small Dataset

Download Full-text

Evaluation and development of a bone age assessment method in patients with Down syndrome

Revista da ABENO ◽

10.30979/rev.abeno.v10i2.19 ◽

2013 ◽

Vol 10 (2) ◽

pp. 41-45

Author(s):

Michelle BM BM ◽

Mari Eli LM ◽

Fernando VR ◽

Simone MRG ◽

Déborah H

Keyword(s):

Down Syndrome ◽

Bone Age ◽

Assessment Method ◽

Control Group ◽

Age Assessment ◽

Male And Female ◽

Vertebral Bone ◽

Significant Difference ◽

Bone Age Assessment ◽

Female Control

The objective of this paper was to evaluate the applicability of the method developed by Caldas to measure the vertebral bone age of Brazilians suffering from Down syndrome. A database comprised of 57 case records of individuals with this syndrome, both male and female, with ages ranging between 5 and 18 years, was used for this purpose. These records had lateral cephalometric radiographs and radiographs of hand and wrist, all of which had been obtained on the same date. There were 48 other records of individuals who did not suffer from Down syndrome. The Tanner and Whitehouse (TW3) method was used to perform the hand and wrist radiographs for obtaining bone age. The Caldas method was employed on the lateral cephalometric radiographs in order to obtain the vertebral bone age. From the information acquired on bone age, vertebral bone age and chronological age, it could be concluded that there is a statistically significant difference between the three ages for both the male and the female control group and for the female Down syndrome group. Therefore, this method was employed only on male Down syndrome individuals. Based on the results, a formula was developed to obtain the bone age for Down syndrome individuals.

Download Full-text