Bone Age Assessment Method Based on Improved ResNet
DOI:
https://doi.org/10.62051/ijcsit.v5n3.06Keywords:
Bone age assessment, Improved residual network, Lightweight and efficient attention module, RUS-CHNAbstract
To extract the features of hand X-ray images in more detail, a bone age assessment method based on an improved residual network is proposed. Based on the RUS-CHN method, a lightweight and efficient attention module is combined with the residual network to improve the accuracy of extracting fine-grained features. Experimental results show that on the dataset provided by a certain tertiary hospital in Xi'an, the average absolute errors (MAE) for males and females are 0.4228 years and 0.4341 years respectively. Within a 1-year error range, the accuracy rates for males and females reach 94.6% and 93.7% respectively, significantly improving the accuracy of bone age assessment.
Downloads
References
[1] Shen Jiyun Evaluation method of adolescent bone age based on NTS deep neural network [j]. digital technology and applications, 2022, 40 (12): 123-128
[2] Li Rui, zhangshijie, Huang Aoyun, et al Evaluation of wrist bone age in adolescents based on deep learning [j]. computer technology and development, 2020, 30 (1): 124-128+134
[3] Wang Lin Design and implementation of bone age calculation and height prediction system based on data model [d]. Hangzhou: Zhejiang University of technology, 2019
[4] BIAN Z, ZHANG R. Bone Age Assessment Method Based on Deep Convolutional Neural Network [C]//2018 8th International Conference on Electronics Information and Emergency Communication (ICEIEC).Beijing: IEEE, 2018: 194-197.
[5] GARN S M. Radiographic Atlas of Skeletal Development of the Hand and Wrist [J]. American Journal of Human Genetics, 1959, 11(3):282-283.
[6] BAYER L M. Radiographic Atlas of Skeletal Development of the Hand and Wrist [J]. California Medicine, 1959, 91(1):53.
[7] MALINA R M, BEUNEN G P. Assessment of Skeletal Maturity and Prediction of Adult Height (TW3 Method) [J]. American Journal of Human Biology, 2002, 14(6):788-789.
[8] Tangzhihao, liulijun, fengxupeng, et al Residual network bone age assessment combined with efficient channel attention module [j]. optoelectronics · laser, 2021, 32 (3): 331-338
[9] Zhanmengjun, zhangshijie, Chen Hu, et al Research progress in automated assessment of bone age [j]. Journal of forensic medicine, 2020, 36 (2): 249-255
[10] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet Classification with Deep Convolutional Neural Networks [C]//Advances in Neural Information Processing Systems 25 (NIPS 2012). CURRAN ASSOCIATION INC., 2012:1-9.
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet Classification with Deep Convolutional Neural Networks [J]. Communications of the ACM, 2017, 60(6):84-90.
[12] Hutinghong, huozhong, liutaiang, et al Automatic assessment of left wrist bone age of Uygur adolescents based on deep learning [j]. Journal of forensic medicine, 2018, 34 (1): 27-32
[13] Zhanmengjun, zhangshijie, Liuli, et al Automatic assessment of left wrist joint bone age of Han adolescents in Sichuan Based on deep learning [j]. Chinese Journal of forensic medicine, 2019, 34 (5): 427-432
[14] Zhangshijie, Li Rui, zhanmengjun, etc Research on bone age evaluation based on deep learning region fusion [j]. modern computer, 2020 (9): 54-59+68
[15] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas: IEEE, 2016:770-778.
[16] Pang Sisi, Huang Chengcheng Research on image classification based on convolutional neural network [j]. modern computer, 2019 (23): 40-44
[17] ZHANG Q L, YANG Y B. SA-NetP: Shuffle Attention for Deep Convolutional Neural Networks [C]//ICASSP 2021— 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto: IEEE, 2021:2235 2239.
[18] Gu Jing, Ma Ruiqi, zhuhengan Evaluation method of X-ray image bone age based on convolutional neural network [j]. Chinese Journal of medical physics, 2022, 39 (3): 305-310.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Computer Science and Information Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
