ECAAF-CenterNet: Efficient Channel Attention and Adaptive Fusion for Cephalometric Landmark Detection

Feng Xu; Guangping Zhuo; Guanghua Zhang; Xiuping  Wu

doi:10.54097/rpdnd942

Authors

Feng Xu
Guangping Zhuo
Guanghua Zhang
Xiuping Wu

DOI:

https://doi.org/10.54097/rpdnd942

Keywords:

Lateral Cranial X-ray, Channel Attention, Adaptive Feature Fusion, Deep Learning

Abstract

In response to the challenges of complex local structures and significant differences in scale distribution in key point detection of lateral cranial films, this paper proposes an automatic key point detection method for lateral cranial films based on the improved CenterNet, ECAAF-CenterNet. Based on the CenterNet anchor-free detection framework, DLA34 is selected as the backbone network. Combined with the characteristics of dense distribution of key points and obvious scale differences in head images, the network structure is improved from the two aspects of feature enhancement and feature fusion. Introduce the Efficient Channel Attention Mechanism (ECA) in the backbone residual module to enhance the network's expression ability for key channel features. Meanwhile, in the multi-scale feature fusion stage, an adaptive weighted cross-scale feature fusion mechanism AF is designed to perform dynamic weighted fusion on features at different levels. Through experimental verification on the private dataset of 1603 lateral cranial films, the MRE reached 1.54mm, and the SDR could reach 94.51% at the 4.0mm threshold, which was superior to the baseline model.

Downloads

Download data is not yet available.

References

[1] Wang C W, Huang C T, Lee J H, et al. A benchmark for comparison of dental radiography analysis algorithms[J]. Medical image analysis, 2016, 31: 63-76. DOI: https://doi.org/10.1016/j.media.2016.02.004

[2] Hlongwa P. Cephalometric analysis: manual tracing of a lateral cephalogram[J]. South African Dental Journal, 2019, 74(6): 318-322. DOI: https://doi.org/10.17159/2519-0105/2019/v74no6a6

[3] Hwang H W, Moon J H, Kim M G, et al. Evaluation of automated cephalometric analysis based on the latest deep learning method[J]. The Angle Orthodontist, 2021, 91(3): 329-335. DOI: https://doi.org/10.2319/021220-100.1

[4] Nishimoto S, Sotsuka Y, Kawai K, et al. Personal computer-based cephalometric landmark detection with deep learning, using cephalograms on the internet[J]. Journal of Craniofacial Surgery, 2019, 30(1): 91-95. DOI: https://doi.org/10.1097/SCS.0000000000004901

[5] Hwang H W, Park J H, Moon J H, et al. Automated identification of cephalometric landmarks: Part 2-Might it be better than human? [J]. The Angle Orthodontist, 2020, 90(1): 69-76. DOI: https://doi.org/10.2319/022019-129.1

[6] Yu F, Wang D, Shelhamer E, et al. Deep layer aggregation [C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 2403-2412. DOI: https://doi.org/10.1109/CVPR.2018.00255

[7] Zeng M, Yan Z, Liu S, et al. Cascaded convolutional networks for automatic cephalometric landmark detection[J]. Medical Image Analysis, 2021, 68: 101904. DOI: https://doi.org/10.1016/j.media.2020.101904

[8] Lee J H, Yu H J, Kim M, et al. Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks[J]. BMC oral health, 2020, 20(1): 270. DOI: https://doi.org/10.1186/s12903-020-01256-7

[9] Ibragimov B, Likar B, Pernus F, et al. Computerized cephalometry by game theory with shape-and appearance-based landmark refinement [C]//Proceedings of International Symposium on Biomedical imaging (ISBI). 2015.

[10] Lindner C, Bromiley P A, Ionita M C, et al. Robust and accurate shape model matching using random forest regression-voting[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 37(9): 1862-1874. DOI: https://doi.org/10.1109/TPAMI.2014.2382106

[11] Urschler M, Ebner T, Štern D. Integrating geometric configuration and appearance information into a unified framework for anatomical landmark localization[J]. Medical image analysis, 2018, 43: 23-36. DOI: https://doi.org/10.1016/j.media.2017.09.003

[12] Arık S Ö, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks[J]. Journal of Medical Imaging, 2017, 4(1): 014501-014501. DOI: https://doi.org/10.1117/1.JMI.4.1.014501

[13] Payer C, Štern D, Bischof H, et al. Integrating spatial configuration into heatmap regression based CNNs for landmark localization[J]. Medical image analysis, 2019, 54: 207-219. DOI: https://doi.org/10.1016/j.media.2019.03.007

[14] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical image computing and computer-assisted intervention. Cham: Springer international publishing, 2015: 234-241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28

[15] ZHOU XY, WANG DQ, KRÄHENBÜHL P. Objects as Points [EB/OL]. (2019-04-25) [2026-01-15]. arXiv:1904. 07850. https: // doi.org/10.48550/arXiv.1904.07850.

[16] Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks [C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 11534-11542. DOI: https://doi.org/10.1109/CVPR42600.2020.01155

[17] Kunz F, Stellzig-Eisenhauer A, Zeman F, et al. Künstliche Intelligenz in der Kieferorthopädie: Evaluierung einer vollständig automatisierten Fernröntgenseitenanalyse unter Anwendung eines individualisierten „convolutional neural network “[J]. Journal of Orofacial Orthopedics/Fortschritte der Kieferorthopädie, 2020, 81: 52-68. DOI: https://doi.org/10.1007/s00056-019-00203-8