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

<b>Background:</b> 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaowei Liu, Rulan Wang, Wenting Jiang, Zhaohua Lu, Ningning Chen, Hongfei Wang
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Tomography
Subjects:
Online Access:https://www.mdpi.com/2379-139X/10/12/139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036756600061952
author Xiaowei Liu
Rulan Wang
Wenting Jiang
Zhaohua Lu
Ningning Chen
Hongfei Wang
author_facet Xiaowei Liu
Rulan Wang
Wenting Jiang
Zhaohua Lu
Ningning Chen
Hongfei Wang
author_sort Xiaowei Liu
collection DOAJ
description <b>Background:</b> 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. <b>Methods</b>: 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. <b>Results:</b> 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. <b>Findings:</b> 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.
format Article
id doaj-art-35d9a2b6b0ca4d75b503e3de110fc0b6
institution DOAJ
issn 2379-1381
2379-139X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Tomography
spelling doaj-art-35d9a2b6b0ca4d75b503e3de110fc0b62025-08-20T02:57:04ZengMDPI AGTomography2379-13812379-139X2024-11-0110121915192910.3390/tomography10120139Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning MethodXiaowei Liu0Rulan Wang1Wenting Jiang2Zhaohua Lu3Ningning Chen4Hongfei Wang5School of Computing and Artificial Intelligence, Shandong University of Finance and Economics, Jinan 250000, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaDepartment of Diagnostic Radiology, The University of Hong Kong, Hong Kong 999077School of Computing and Artificial Intelligence, Shandong University of Finance and Economics, Jinan 250000, ChinaDepartment of Orthopedic Surgery, The Seventh Affiliated Hospital, Sun Yat-Sen University, Shenzhen 518000, ChinaDepartment of Orthopaedics and Traumatology, The University of Hong Kong, Hong Kong 999077<b>Background:</b> 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. <b>Methods</b>: 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. <b>Results:</b> 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. <b>Findings:</b> 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.https://www.mdpi.com/2379-139X/10/12/139bone agehand-wrist X-rayscoliosisdeep learningclassificationsegmentation
spellingShingle Xiaowei Liu
Rulan Wang
Wenting Jiang
Zhaohua Lu
Ningning Chen
Hongfei Wang
Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method
Tomography
bone age
hand-wrist X-ray
scoliosis
deep learning
classification
segmentation
title Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method
title_full Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method
title_fullStr Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method
title_full_unstemmed Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method
title_short Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method
title_sort automated distal radius and ulna skeletal maturity grading from hand radiographs with an attention multi task learning method
topic bone age
hand-wrist X-ray
scoliosis
deep learning
classification
segmentation
url https://www.mdpi.com/2379-139X/10/12/139
work_keys_str_mv AT xiaoweiliu automateddistalradiusandulnaskeletalmaturitygradingfromhandradiographswithanattentionmultitasklearningmethod
AT rulanwang automateddistalradiusandulnaskeletalmaturitygradingfromhandradiographswithanattentionmultitasklearningmethod
AT wentingjiang automateddistalradiusandulnaskeletalmaturitygradingfromhandradiographswithanattentionmultitasklearningmethod
AT zhaohualu automateddistalradiusandulnaskeletalmaturitygradingfromhandradiographswithanattentionmultitasklearningmethod
AT ningningchen automateddistalradiusandulnaskeletalmaturitygradingfromhandradiographswithanattentionmultitasklearningmethod
AT hongfeiwang automateddistalradiusandulnaskeletalmaturitygradingfromhandradiographswithanattentionmultitasklearningmethod