Classification of Distal Growth Plate Ossification States of the Radius Bone Using a Dedicated Ultrasound Device and Machine Learning Techniques for Bone Age Assessments

X-ray imaging, based on ionizing radiation, can be used to determine bone age by examining distal growth plate fusion in the ulna and radius bones. Legal age determination approaches based on ultrasound signals exist but are unsuitable to reliably determine bone age. We present a low-cost, mobile sy...

Full description

Bibliographic Details
Main Authors: Brausch, L. (Author), Dirksen, R. (Author), Hewener, H. (Author), Risser, C. (Author), Rohrer, T. (Author), Schwab, M. (Author), Stolz, C. (Author), Tretbar, S. (Author)
Format: Article
Language:English
Published: MDPI 2022
Subjects:
Online Access:View Fulltext in Publisher
LEADER 02250nam a2200265Ia 4500
001 0.3390-app12073361
008 220421s2022 CNT 000 0 und d
020 |a 20763417 (ISSN) 
245 1 0 |a Classification of Distal Growth Plate Ossification States of the Radius Bone Using a Dedicated Ultrasound Device and Machine Learning Techniques for Bone Age Assessments 
260 0 |b MDPI  |c 2022 
856 |z View Fulltext in Publisher  |u https://doi.org/10.3390/app12073361 
520 3 |a X-ray imaging, based on ionizing radiation, can be used to determine bone age by examining distal growth plate fusion in the ulna and radius bones. Legal age determination approaches based on ultrasound signals exist but are unsuitable to reliably determine bone age. We present a low-cost, mobile system that uses one-dimensional ultrasound radio frequency signals to obtain a robust binary classifier enabling the determination of bone age from data of girls and women aged 9 to 24 years. These data were acquired as part of a clinical study conducted with 148 subjects. Our system detects the presence or absence of the epiphyseal plate by moving ultrasound array transducers along the forearm, measuring reflection and transmission signals. Even though classical digital signal processing methods did not achieve a robust classifier, we achieved an F1 score of approximately 87% for binary classification of completed bone growth with machine learning approaches, such as the gradient boosting machine method CatBoost. We demonstrate that our ultrasound system can classify the fusion of the distal growth plate of the radius bone and the completion of bone growth with high accuracy. We propose a non-ionizing alternative to established X-ray imaging methods for this purpose. © 2022 by the authors. Licensee MDPI, Basel, Switzerland. 
650 0 4 |a bone age 
650 0 4 |a growth plate fusion 
650 0 4 |a machine learning 
650 0 4 |a mobile ultrasound 
700 1 0 |a Brausch, L.  |e author 
700 1 0 |a Dirksen, R.  |e author 
700 1 0 |a Hewener, H.  |e author 
700 1 0 |a Risser, C.  |e author 
700 1 0 |a Rohrer, T.  |e author 
700 1 0 |a Schwab, M.  |e author 
700 1 0 |a Stolz, C.  |e author 
700 1 0 |a Tretbar, S.  |e author 
773 |t Applied Sciences (Switzerland)