A lightweight convolutional neural network for myositis classification from muscle ultrasound images_Journal of Biomedical Engineering

Authors：

TAN Hao ¹ ,  LANG Xun ¹ , WANG Tao ¹ , HE Bingbing ¹ , LI Zhiyao ² , LU Yu ¹ , ZHANG Yufeng ¹

1. School of Information Science and Engineering, Yunnan University, Kunming 650504, P. R. China;
2. Third Affiliated Hospital of Kunming Medical University, Kunming 650118, P. R. China;

Corresponding author：

LANG Xun, Email: langxun@ynu.edu.cn

Keywords：

Idiopathic inflammatory myopathies; Attention mechanisms; Lightweight neural networks; Ultrasound images

DOI：

10.7507/1001-5515.202301023

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Existing classification methods for myositis ultrasound images have problems of poor classification performance or high computational cost. Motivated by this difficulty, a lightweight neural network based on a soft threshold attention mechanism is proposed to cater for a better IIMs classification. The proposed network was constructed by alternately using depthwise separable convolution (DSC) and conventional convolution (CConv). Moreover, a soft threshold attention mechanism was leveraged to enhance the extraction capabilities of key features. Compared with the current dual-branch feature fusion myositis classification network with the highest classification accuracy, the classification accuracy of the network proposed in this paper increased by 5.9%, reaching 96.1%, and its computational complexity was only 0.25% of the existing method. The obtained results support that the proposed method can provide physicians with more accurate classification results at a lower computational cost, thereby greatly assisting them in their clinical diagnosis.

Citation： TAN Hao, LANG Xun, WANG Tao, HE Bingbing, LI Zhiyao, LU Yu, ZHANG Yufeng. A lightweight convolutional neural network for myositis classification from muscle ultrasound images. Journal of Biomedical Engineering, 2024, 41(5): 895-902. doi: 10.7507/1001-5515.202301023 Copy

1.	Schulze M, Kötter I, Ernemann U, et al. MRI findings in inflammatory muscle diseases and their noninflammatory mimics. Am J Roentgenol, 2009, 192(6): 1708-1716.
2.	Dalakas M C. Polymyositis, dermatomyositis, and inclusion-body myositis. New Engl J Med, 1991, 325(21): 1487-1498.
3.	Amato A A, Barohn R J. Idiopathic inflammatory myopathies. Neurol Clin, 1997, 15(3): 615-648.
4.	Lang X, He B, Zhang Y, et al. Adaptive clutter filtering for ultrafast Doppler imaging of blood flow using fast multivariate empirical mode decomposition// 2021 IEEE International Ultrasonics Symposium (IUS). Xi'an: IEEE, 2021: 1-4.
5.	Botar-Jid C, Dudea S M, Damian L, et al. The role of gray-scale ultrasound in assessment of myositis. Ultraschall Med, 2008, 29: PP_9_9.
6.	Noto Y I, Shiga K, Tsuji Y, et al. Contrasting echogenicity in flexor digitorum profundus–flexor carpi ulnaris: A diagnostic ultrasound pattern in sporadic inclusion body myositis. Muscle Nerve, 2014, 49(5): 745-748.
7.	He B, Lei J, Lang X, et al. Ultra-fast ultrasound blood flow velocimetry for carotid artery with deep learning. Artif Intell Med, 2023, 144: 102664.
8.	蒋林芮, 曾妮, 苗青山, 等. 荧光共振能量转移聚合物胶束及其作为药物载体的研究进展. 生物医学工程学杂志, 2022, 39(5): 1022-1032.
9.	Nodera H, Sogawa K, Takamatsu N, et al. Texture analysis of sonographic muscle images can distinguish myopathic conditions. J Med Invest, 2019, 66(3.4): 237-247.
10.	Burlina P, Billings S, Joshi N, et al. Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods. PLoS One, 2017, 12(8): e0184059.
11.	Uçar E. Classification of myositis from muscle ultrasound images using deep learning. Biomed Signal Proces, 2022, 71: 103277.
12.	Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. Mobilenets, 2017, 10: 151.
13.	Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift// International Conference on Machine Learning. Lille: PMLR, 2015: 448-456.
14.	Lin M, Chen Q, Yan S. Network in network. arXiv preprint arXiv: 2013, 1312.4400.
15.	Hu J, Shen L, Sun G. Squeeze-and-excitation networks// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE 2018: 7132-7141.
16.	Wang H, Zhu Y, Green B, et al. Axial-DeepLab: Stand-alone axial-attention for panoptic segmentation// European Conference on Computer Vision (ECCV). Glasgow: Springer, 2020: 108-126.
17.	Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module// Proceedings of the European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 3-19.
18.	Hou Q, Zhang L, Cheng M M, et al. Strip pooling: Rethinking spatial pooling for scene parsing// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington: IEEE, 2020: 4003-4012.
19.	Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Virtual: IEEE, 2021: 13713-13722.
20.	Lang X, ur Rehman N, Zhang Y, et al. Median ensemble empirical mode decomposition. Signal Process, 2020, 176: 107686.
21.	Lang X, Zhang Y, Xie L, et al. Detrending and denoising of industrial oscillation data. IEEE T Ind Inform, 2022, 19(4): 5809-5820.
22.	Zhao M, Zhong S, Fu X, et al. Deep residual shrinkage networks for fault diagnosis. IEEE T Ind Inform, 2019, 16(7): 4681-4690.
23.	Rose M R, enMC iBM Working Group. 188th ENMC International Workshop: inclusion body myositis, 2–4 December 2011, Naarden, The Netherlands. Neuromuscular Disord, 2013, 23(12): 1044-1055.
24.	Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization// Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice: IEEE 2017: 618-626.

1. Schulze M, Kötter I, Ernemann U, et al. MRI findings in inflammatory muscle diseases and their noninflammatory mimics. Am J Roentgenol, 2009, 192(6): 1708-1716.
2. Dalakas M C. Polymyositis, dermatomyositis, and inclusion-body myositis. New Engl J Med, 1991, 325(21): 1487-1498.
3. Amato A A, Barohn R J. Idiopathic inflammatory myopathies. Neurol Clin, 1997, 15(3): 615-648.
4. Lang X, He B, Zhang Y, et al. Adaptive clutter filtering for ultrafast Doppler imaging of blood flow using fast multivariate empirical mode decomposition// 2021 IEEE International Ultrasonics Symposium (IUS). Xi'an: IEEE, 2021: 1-4.
5. Botar-Jid C, Dudea S M, Damian L, et al. The role of gray-scale ultrasound in assessment of myositis. Ultraschall Med, 2008, 29: PP_9_9.
6. Noto Y I, Shiga K, Tsuji Y, et al. Contrasting echogenicity in flexor digitorum profundus–flexor carpi ulnaris: A diagnostic ultrasound pattern in sporadic inclusion body myositis. Muscle Nerve, 2014, 49(5): 745-748.
7. He B, Lei J, Lang X, et al. Ultra-fast ultrasound blood flow velocimetry for carotid artery with deep learning. Artif Intell Med, 2023, 144: 102664.
8. 蒋林芮, 曾妮, 苗青山, 等. 荧光共振能量转移聚合物胶束及其作为药物载体的研究进展. 生物医学工程学杂志, 2022, 39(5): 1022-1032.
9. Nodera H, Sogawa K, Takamatsu N, et al. Texture analysis of sonographic muscle images can distinguish myopathic conditions. J Med Invest, 2019, 66(3.4): 237-247.
10. Burlina P, Billings S, Joshi N, et al. Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods. PLoS One, 2017, 12(8): e0184059.
11. Uçar E. Classification of myositis from muscle ultrasound images using deep learning. Biomed Signal Proces, 2022, 71: 103277.
12. Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. Mobilenets, 2017, 10: 151.
13. Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift// International Conference on Machine Learning. Lille: PMLR, 2015: 448-456.
14. Lin M, Chen Q, Yan S. Network in network. arXiv preprint arXiv: 2013, 1312.4400.
15. Hu J, Shen L, Sun G. Squeeze-and-excitation networks// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE 2018: 7132-7141.
16. Wang H, Zhu Y, Green B, et al. Axial-DeepLab: Stand-alone axial-attention for panoptic segmentation// European Conference on Computer Vision (ECCV). Glasgow: Springer, 2020: 108-126.
17. Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module// Proceedings of the European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 3-19.
18. Hou Q, Zhang L, Cheng M M, et al. Strip pooling: Rethinking spatial pooling for scene parsing// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington: IEEE, 2020: 4003-4012.
19. Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Virtual: IEEE, 2021: 13713-13722.
20. Lang X, ur Rehman N, Zhang Y, et al. Median ensemble empirical mode decomposition. Signal Process, 2020, 176: 107686.
21. Lang X, Zhang Y, Xie L, et al. Detrending and denoising of industrial oscillation data. IEEE T Ind Inform, 2022, 19(4): 5809-5820.
22. Zhao M, Zhong S, Fu X, et al. Deep residual shrinkage networks for fault diagnosis. IEEE T Ind Inform, 2019, 16(7): 4681-4690.
23. Rose M R, enMC iBM Working Group. 188th ENMC International Workshop: inclusion body myositis, 2–4 December 2011, Naarden, The Netherlands. Neuromuscular Disord, 2013, 23(12): 1044-1055.
24. Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization// Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice: IEEE 2017: 618-626.

Journal of Biomedical Engineering

A lightweight convolutional neural network for myositis classification from muscle ultrasound images

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content