Age assessment from unlabeled hand bone X-ray images based on Xception

Minghao Liang; Hang Lu

doi:10.47297/wspbdsWSP2752-630506.20240404

PDF
Export
Share
Collection
Album

Age assessment from unlabeled hand bone X-ray images based on Xception

Volume 4, Issue 4

Views: 0 Downloads: 0

Age assessment from unlabeled hand bone X-ray images based on Xception
Age assessment from unlabeled hand bone X-ray images based on Xception
Data Science and Big Data Technology, Guangdong Medical University, Dongguan, 523000, China
Vol. 4, Issue 4, Pages: 36-43(2024)
Published： 25 December 2024 ，
DOI：10.47297/wspbdsWSP2752-630506.20240404
Accepted：

Scan QR Code

MINGHAO LIANG & HANG LU. (2024). Age assessment from unlabeled hand bone X-ray images based on Xception. Biomedical Data Science, 4(4), 36-43..
DOI：

MINGHAO LIANG & HANG LU. (2024). Age assessment from unlabeled hand bone X-ray images based on Xception. Biomedical Data Science, 4(4), 36-43.. DOI： 10.47297/wspbdsWSP2752-630506.20240404.

摘要

Abstract

Bone age assessment (BAA) through hand X-rays plays a vital role in diagnosing endocrine disorders in adolescents and assessing children's growth and development. Traditionally

clinical BAA has been a subjective estimation

with its accuracy largely depending on the expertise of pediatric specialists. Recently

several deep learning techniques have been introduced to automate bone age estimation

demonstrating encouraging outcomes. However

these approaches often lack the ability to utilize discriminative information adequately due to the absence of manual annotations for key bone regions

which are critical indicators of skeletal maturity

potentially limiting their practical effectiveness. In this research

we introduce a deep learning-based BAA approach that eliminates the need for manual region annotations. The proposed model leverages the Xception deep convolutional neural network

enhanced with the CBAM attention module

to estimate bone age from unlabeled hand X-ray images. Experiments conducted on the RSNA public dataset indicate that our method achieves a mean absolute error (MAE) of 7.93 months.

关键词

Keywords

Bone Age Assessment (BAA)Deep LearningCBAM Attention ModuleXception NetworkRSNA

references

Prokop-Piotrkowska, Monika, et al. "Traditional and new methods of bone age assessment-an overview." Journal of Clinical Research in Pediatric Endocrinology 13.3 (2021): 251.

Cavallo, Federica, et al. "Evaluation of bone age in children: a mini-review." Frontiers in Pediatrics9 (2021): 580314.

Wang, Qingju. Bone growth in pubertal girls: cross-sectional and longitudinal investigation of the association of sex hormones, physical activity, body composition, and muscle strength with bone mass and geometry. No. 110. University of Jyväskylä, 2005.

Hochberg, Zeʼev. Endocrine control of skeletal maturation: annotation to bone age readings. Karger Medical and Scientific Publishers, 2002.

Ren, Xuhua, et al. "Regression convolutional neural network for automated pediatric bone age assessment from hand radiograph." IEEE journal of biomedical and health informatics 23.5 (2018): 2030-2038.

Larson, David B., et al. "Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs." Radiology 287.1 (2018): 313-322.

Pan, Xiaoying, et al. "Fully Automated Bone Age Assessment on Large‐Scale Hand X‐Ray Dataset." International journal of biomedical imaging2020.1 (2020): 8460493.

Iglovikov, Vladimir, and Alexey Shvets. "Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation." arXiv preprint arXiv:1801.05746 (2018).

Escobar, María, et al. "Hand pose estimation for pediatric bone age assessment." Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part VI 22. Springer International Publishing, 2019.

Son, Sung Joon, et al. "TW3-based fully automated bone age assessment system using deep neural networks." IEEE Access7 (2019): 33346-33358.

Li, Zhangyong, et al. "Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction." Frontiers in Artificial Intelligence6 (2023): 1142895.

He, Bishi, et al. "Multi-Branch Attention Learning for Bone Age Assessment with Ambiguous Label." Sensors 23.10 (2023): 4834.

Chollet, François. "Xception: Deep learning with depthwise separable convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

Woo, Sanghyun, et al. "Cbam: Convolutional block attention module." Proceedings of the European conference on computer vision (ECCV). 2018.

Alert me when the article has been cited

Submit

No data

Related Author

No data

Related Institution

No data

⁰