Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Nov 28;10(12):1915-1929.
doi: 10.3390/tomography10120139.

Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method

Xiaowei Liu  1 , Rulan Wang  2 , Wenting Jiang  3 , Zhaohua Lu  1 , Ningning Chen  4   5 , Hongfei Wang  6
Affiliations

Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method

Xiaowei Liu et al. Tomography. .

Abstract

Background: Assessment of skeletal maturity is a common clinical practice to investigate adolescent growth and endocrine disorders. The distal radius and ulna (DRU) maturity classification is a practical and easy-to-use scheme that was designed for adolescent idiopathic scoliosis clinical management and presents high sensitivity in predicting the growth peak and cessation among adolescents. However, time-consuming and error-prone manual assessment limits DRU in clinical application. Methods: In this study, we propose a multi-task learning framework with an attention mechanism for the joint segmentation and classification of the distal radius and ulna in hand X-ray images. The proposed framework consists of two sub-networks: an encoder-decoder structure with attention gates for segmentation and a slight convolutional network for classification. Results: With a transfer learning strategy, the proposed framework improved DRU segmentation and classification over the single task learning counterparts and previously reported methods, achieving an accuracy of 94.3% and 90.8% for radius and ulna maturity grading. Findings: Our automatic DRU assessment platform covers the whole process of growth acceleration and cessation during puberty. Upon incorporation into advanced scoliosis progression prognostic tools, clinical decision making will be potentially improved in the conservative and operative management of scoliosis patients.

Keywords: bone age; classification; deep learning; hand-wrist X-ray; scoliosis; segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Data inclusion and exclusion flowchart.
Figure 2
Figure 2
DRU object detection from hand X-rays and crops extraction.
Figure 3
Figure 3
Represented radiographs, segmentation labels, and data size of different ulna and radius maturity stages.
Figure 4
Figure 4
Schematic of the implemented additive attention gate.
Figure 5
Figure 5
Proposed multi-task learning framework with attention mechanism for DRU maturity classification and segmentation.
Figure 6
Figure 6
(A) Confusion matrix for radius stage grading for proposed method. (B) Confusion matrix for ulna stage grading for proposed method.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Molinari L., Gasser T., Largo R. A comparison of skeletal maturity and growth. Ann. Hum. Biol. 2013;40:333–340. doi: 10.3109/03014460.2012.756122. - DOI - PubMed
    1. Augusto A.C.L., Goes P.C.K., Flores D.V., Costa M.A.F., Takahashi M.S., Rodrigues A.C.O., Padula L.C., Gasparetto T.D., Nogueira-Barbosa M.H., Aihara A.Y. Imaging review of normal and abnormal skeletal maturation. Radiographics. 2022;42:861–879. doi: 10.1148/rg.210088. - DOI - PubMed
    1. Johnson M.A., Flynn J.M., Anari J.B., Gohel S., Cahill P.J., Winell J.J., Baldwin K.D. Risk of scoliosis progression in nonoperatively treated adolescent idiopathic scoliosis based on skeletal maturity. J. Pediatr. Orthop. 2021;41:543–548. doi: 10.1097/BPO.0000000000001929. - DOI - PubMed
    1. Spadoni G.L., Cianfarani S. Bone age assessment in the workup of children with endocrine disorders. Horm. Res. Paediatr. 2010;73:2–5. doi: 10.1159/000271910. - DOI - PubMed
    1. Staal H.M., Goud A.L., van der Woude H.J., Witlox M.A., Ham S.J., Robben S.G., Dremmen M.H., van Rhijn L.W. Skeletal maturity of children with multiple osteochondromas: Is diminished stature due to a systemic influence? J. Child. Orthop. 2015;9:397–402. doi: 10.1007/s11832-015-0680-x. - DOI - PMC - PubMed

Publication types

LinkOut - more resources