Deep learning-based automated bone age estimation for Saudi patients on hand radiograph images: a retrospective study.
Bone age assessment
Convolutional neural network
Deep learning
Left-hand radiographs
Pediatric medicine
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
01 Aug 2024
01 Aug 2024
Historique:
received:
26
03
2024
accepted:
24
07
2024
medline:
2
8
2024
pubmed:
2
8
2024
entrez:
1
8
2024
Statut:
epublish
Résumé
In pediatric medicine, precise estimation of bone age is essential for skeletal maturity evaluation, growth disorder diagnosis, and therapeutic intervention planning. Conventional techniques for determining bone age depend on radiologists' subjective judgments, which may lead to non-negligible differences in the estimated bone age. This study proposes a deep learning-based model utilizing a fully connected convolutional neural network(CNN) to predict bone age from left-hand radiographs. The data set used in this study, consisting of 473 patients, was retrospectively retrieved from the PACS (Picture Achieving and Communication System) of a single institution. We developed a fully connected CNN consisting of four convolutional blocks, three fully connected layers, and a single neuron as output. The model was trained and validated on 80% of the data using the mean-squared error as a cost function to minimize the difference between the predicted and reference bone age values through the Adam optimization algorithm. Data augmentation was applied to the training and validation sets yielded in doubling the data samples. The performance of the trained model was evaluated on a test data set (20%) using various metrics including, the mean absolute error (MAE), median absolute error (MedAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The code of the developed model for predicting the bone age in this study is available publicly on GitHub at https://github.com/afiosman/deep-learning-based-bone-age-estimation . Experimental results demonstrate the sound capabilities of our model in predicting the bone age on the left-hand radiographs as in the majority of the cases, the predicted bone ages and reference bone ages are nearly close to each other with a calculated MAE of 2.3 [1.9, 2.7; 0.95 confidence level] years, MedAE of 2.1 years, RMAE of 3.0 [1.5, 4.5; 0.95 confidence level] years, and MAPE of 0.29 (29%) on the test data set. These findings highlight the usability of estimating the bone age from left-hand radiographs, helping radiologists to verify their own results considering the margin of error on the model. The performance of our proposed model could be improved with additional refining and validation.
Identifiants
pubmed: 39090563
doi: 10.1186/s12880-024-01378-2
pii: 10.1186/s12880-024-01378-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
199Informations de copyright
© 2024. The Author(s).
Références
Tanner JM, Whitehouse RH, Cameron N, Marshall WA, Healy MJ, Goldstein H. Assessment of skeletal maturity and prediction of adult height (TW2 method). London: Academic; 1983.
Greulich WW, Pyle SI. Radiograph atlas of skeletal development of the hand and wrist. 2nd ed. California: Stanford University Press; 1959.
Ozdemir C, Gedik MA, Kaya Y. Age estimation from left-hand radiographs with deep learning methods. Traitement Du Signal. 2021;38(6):1565–74. https://doi.org/10.18280/ts.380601 .
doi: 10.18280/ts.380601
Mehta C, Ayeesha B, Sotakanal A, Nirmala SR, Desai SD, Suryanarayana KV, Ganguly AD, Shetty V. Deep Learning Framework for Automatic Bone Age Assessment. In Proceedings of the 2021 43rd Annual Inte’lConf of the IEEE Engineering in Med &Biol Society (EMBC) Virtual 2021;3093–3096.
Iglovikov VI, Rakhlin A, Kalinin AA, Shvets AA et al. Paediatric Bone Age Assessment Using Deep Convolutional Neural Networks. In: Stoyanov Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. DLMIA ML-CDS 2018. 2018. Lecture Notes in Computer Science, vol 11045. Springer, Cham, 2018. https://doi.org/10.1007/978-3-030-00889-5_34 .
Castillo JC, Tong Y, Zhao J, Zhu F. (2018). RSNA bone-age detection using transfer learning and attention mapping. 2018. http://noiselab.ucsd.edu/ECE228_2018/Reports/Report6.pdf .
Nabilah A, Sigit R, Fariza A, Madyono M. Human bone age estimation of carpal bone X-Ray using residual network with batch normalization classification. Int J Inf Visualization. 2023;7(1):105–14.
doi: 10.30630/joiv.7.1.1024
Liu Y, Zhang C, Cheng J, Chen X, Wang ZJ. A multi-scale data fusion framework for bone age assessment with convolutional neural networks. ComputBiol Med. 2019;108:161–73. https://doi.org/10.1016/j.compbiomed.2019.03.015 .
doi: 10.1016/j.compbiomed.2019.03.015
Mutasa S, Chang PD, Ruzal-Shapiro C, Ayyala R. MABAL: a Novel Deep-Learning Architecture for machine-assisted bone age labeling. J Digit Imaging. 2018;31:513–9.
doi: 10.1007/s10278-018-0053-3
pubmed: 29404850
pmcid: 6113150
Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP. Performance of adeep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology. 2018;287(1):313–22. https://doi.org/10.1148/radiol.2017170236 .
doi: 10.1148/radiol.2017170236
pubmed: 29095675
Hao P, Chokuwa S, Xie X, Wu F, Wu J, Bai C. Skeletal bone age assessments for young children based on regression convolutional neural networks. Math Biosci Eng. 2019;16(6):6454–66. https://doi.org/10.3934/mbe.2019323 .
doi: 10.3934/mbe.2019323
pubmed: 31698572
Pan I, Baird GL, Mutasa S, Merck D, Ruzal-Shapiro C, Swenson DW, Ayyala RS. Rethinking Greulich and Pyle: a Deep Learning Approach to Pediatric Bone Age Assessment Using Pediatric Trauma Hand Radiographs. RadiolArtifIntell. 2020;2(4):e190198. https://doi.org/10.1148/ryai.2020190198 .
doi: 10.1148/ryai.2020190198
Spampinato C, Palazzo S, Giordano D, Aldinucci M, Leonardi R. Deep learning for automated skeletal bone age assessment in X-ray images. Med Image Anal. 2017;36:41–51. https://doi.org/10.1016/j.media.2016.10.010 .
doi: 10.1016/j.media.2016.10.010
pubmed: 27816861
Bui TD, Lee J-J, Shin J. Incorporated region detection and classification using deep convolutional networks for bone age assessment. ArtifIntell Med. 2019;97:1–8.
Xu X, Xu H, Li Z. Automated Bone Age Assessment: a New Three-Stage Assessment Method from Coarse to Fine. Healthcare. 2022;10:2170.
doi: 10.3390/healthcare10112170
pubmed: 36360511
pmcid: 9690777
Lee H, Tajmir S, Lee J, Zissen M, Yeshiwas BA, Alkasab TK, Choy G, Do S. Fully automated deep learning system for bone age assessment. J Digit Imaging. 2017;30(4):427–41. https://doi.org/10.1007/s10278-017-9955-8 .
doi: 10.1007/s10278-017-9955-8
pubmed: 28275919
pmcid: 5537090
Salamon J, Bello JP. Deep convolutional neural networks and data augmentation for environmental sound classification. 2016; arXiv:1608.04363. Available at https://arxiv.org/abs/1608.04363 .
Nair V, Hinton GE. Rectified linear units improve restricted Boltzmann machines. Proc. 27th IntConf Mach Learn. 2010;807–814.
Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. 2015; arXiv:1502.03167v3. https://arxiv.org/abs/1502.03167v3 .
Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15:1929–58.