Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
Source abstract
Abstract
Scoliosis is a widespread medical condition where the spine becomes severely deformed and bends over time. It mostly affects young adults and may have a permanent impact on them. A periodic assessment, using a suitable modality, is necessary for its early detection. Conventionally, the usually employed modalities include X-ray and MRI, which employ ionising radiation and are expensive. Hence, a non-radiating 3D ultrasound imaging technique has been developed as a safe and economic alternative. However, ultrasound produces low-contrast images that are full of speckle noise, and skilled intervention is necessary for their processing. Given the prevalent occurrence of scoliosis and the limitations of scalability of human expert interventions, an automatic, fast, and low-computation assessment technique is being developed for mass scoliosis diagnosis. In this paper, a novel hybridized light-weight convolutional neural network architecture is presented for automatic lateral bony feature identification, which can help to develop a fully-fledged automatic scoliosis detection system. The proposed architecture, Light-convolution Dense Selection U-Net (LDS U-Net), can accurately segment ultrasound spine lateral bony features, from noisy images, thanks to its capabilities of smartly selecting only the useful information and extracting rich deep layer features from the input image. The proposed model is tested using a dataset of 109 spine ultrasound images. The segmentation result of the proposed network is compared with basic U-Net, Attention U-Net, and MultiResUNet using various popular segmentation indices. The results show that LDS U-Net provides a better segmentation performance compared to the other models. Additionally, LDS U-Net requires a smaller number of parameters and less memory, making it suitable for a large-batch screening process of scoliosis without a high computational requirement.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Imaging and Analysis · Scoliosis diagnosis and treatment · Ultrasound Imaging and Elastography
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Biomedical Engineering, University of Technology, Sydney, NSW 2007, Australia
College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong, China
Department of Biomedical Engineering, Hong Kong Polytechnic University, Hong Kong, China
Funding
Hong Kong Research Grant Council
References (67)
Show source-provided references
1. Scoliosis imaging: What radiologists should know10.1148/rg.307105061 ↗
2. Zheng, Y.-P., Lee, T.T.Y., Lai, K.K.L., Yip, B.H.K., Zhou, G.Q., Jiang, W.W., Cheung, J.C.W., Wong, M.S., Ng, B.K.W., and Cheng, J.C.Y. (2016). A reliability and validity study for Scolioscan: A radiation-free scoliosis assessment system using 3D ultrasound imaging. Scoliosis Spinal Disord., 11.10.1186/s13013-016-0074-y ↗
3. Scoliosis on pulmonary function
4. Left ventricular mechanics assessed by 2-dimensional speckle tracking echocardiography in children and adolescents with idiopathic scoliosis10.1097/BSD.0000000000000219 ↗
5. Liu, D., Yang, Y., Yu, X., Yang, J., Xuan, X., Yang, J., and Huang, Z. (2020). Effects of specific exercise therapy on adolescent patients with idiopathic scoliosis: A prospective controlled cohort study. Spine, 45.10.1097/BRS.0000000000003451 ↗
6. Outline for the study of scoliosis
7. Reducing the lifetime risk of cancer from spinal radiographs among people with adolescent idiopathic scoliosis10.1097/00007632-199607010-00011 ↗
8. McKenna, C., Wade, R., Faria, R., Yang, H., Stirk, L., Gummerson, N., Sculpher, M., and Woolacott, N. (2012). EOS 2D/3D X-ray imaging system: A systematic review and economic evaluation. Health Technol. Assess. Winch. Engl., 16.10.3310/hta16140 ↗
9. Rehm, J., Germann, T., Akbar, M., Pepke, W., Kauczor, H.U., Weber, M.A., and Spira, D. (2017). 3D-modeling of the spine using EOS imaging system: Inter-reader reproducibility and reliability. PLoS ONE, 12.10.1371/journal.pone.0171258 ↗
10. Quasi-automatic early detection of progressive idiopathic scoliosis from biplanar radiography: A preliminary validation10.1007/s00586-019-05998-z ↗
11. Spinal curvature measurement by tracked ultrasound snapshots10.1016/j.ultrasmedbio.2013.09.021 ↗
12. Ultrasound measurement of vertebral rotation in idiopathic scoliosis10.1302/0301-620X.71B2.2647754 ↗
13. Development of a portable 3D ultrasound imaging system for musculoskeletal tissues10.1016/j.ultras.2004.05.003 ↗
14. 3-D measurement of body tissues based on ultrasound images with 3-D spatial information10.1016/j.ultrasmedbio.2005.08.004 ↗
15. Zhou, G.-Q., and Zheng, Y.-P. (2015, January 21–24). Assessment of scoliosis using 3-D ultrasound volume projection imaging with automatic spine curvature detection. Proceedings of the 2015 IEEE International Ultrasonics Symposium (IUS), Taipei, Taiwan.10.1109/ULTSYM.2015.0485 ↗
16. Ultrasound volume projection imaging for assessment of scoliosis10.1109/TMI.2015.2390233 ↗
17. Zhou, G.-Q., Jiang, W.-W., Lai, K.-L., Lam, T.-P., Cheng, J.C.-Y., and Zheng, Y.-P. (April, January 31). Semi-automatic Measurement of Scoliotic Angle Using a Freehand 3-D Ultrasound System Scolioscan. Proceedings of the XIV Mediterranean Conference on Medical and Biological Engineering and Computing, Paphos, Cyprus.
18. Automatic measurement of spine curvature on 3-D ultrasound volume projection image with phase features10.1109/TMI.2017.2674681 ↗
19. An adaptive weighted median filter for speckle suppression in medical ultrasonic images10.1109/31.16577 ↗
20. 3D ultrasound imaging provides reliable angle measurement with validity comparable to X-ray in patients with adolescent idiopathic scoliosis
21. Vedula, S., Senouf, O., Bronstein, A.M., Michailovich, O.V., and Zibulevsky, M. (2017). Towards CT-quality ultrasound imaging using deep learning. arXiv.
22. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2013). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, Proceedings of the 26th Annual Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, 3–6 December 2012, Curran Associates, Inc.
23. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
24. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
25. Zeiler, M.D., and Fergus, R. (2014). Visualizing and understanding convolutional networks. Computer Vision—ECCV 2014, Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland, 6–12 September 2014, Springer.10.1007/978-3-319-10590-1_53 ↗
26. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015, Springer.10.1007/978-3-319-24574-4_28 ↗
27. Long, J., Shelhamer, E., and Darrell, T. (2015, January 18–23). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2015.7298965 ↗
28. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
29. Hu, R., Dollár, P., He, K., and Darrell, T. (2017, January 22–29). Girshick RLearning to Segment Every Thing. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/CVPR.2018.00445 ↗
30. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
31. Li, J., Wu, Y., Zhao, J., Guan, L., Ye, C., and Yang, T. (2017, January 14–19). Pedestrian detection with dilated convolution, region proposal network and boosted decision trees. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AL, USA.10.1109/IJCNN.2017.7966367 ↗
32. Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM10.1109/LGRS.2018.2795531 ↗
33. Deep learning and its application to medical image segmentation
34. Two-stage ultrasound image segmentation using U-Net and test time augmentation10.1007/s11548-020-02158-3 ↗
35. Automatic segmentation of human placenta images with U-Net10.1109/ACCESS.2019.2958133 ↗
36. Thomson, B.R., Nijkamp, J., Ivashchenko, O., van der Heijden, F., Smit, J.N., Kok, N.F., Kuhlmann, K.F., Ruers, T.J., and Fusaglia, M. (2019). Hepatic vessel segmentation using a reduced filter 3D U-Net in ultrasound imaging. arXiv.
37. Dual-task ultrasound spine transverse vertebrae segmentation network with contour regularization10.1016/j.compmedimag.2021.101896 ↗
38. Banerjee, S., Ling, S.H., Lyu, J., Su, S., and Zheng, Y.-P. (2020, January 20–24). Automatic Segmentation of 3D Ultrasound Spine Curvature Using Convolutional Neural Network. Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada.10.1109/EMBC44109.2020.9175673 ↗
39. Huang, Z., Wang, L.W., Leung, F.H., Banerjee, S., Yang, D., Lee, T., Lyu, J., Ling, S.H., and Zheng, Y.P. (2020). Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise. arXiv.10.1109/SMC42975.2020.9283335 ↗
40. Ravishankar, H., Venkataramani, R., Thiruvenkadam, S., Sudhakar, P., and Vaidya, V. (2017). Learning and incorporating shape models for semantic segmentation. Medical Image Computing and Computer Assisted Intervention—MICCAI 2017, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Quebec City, QC, Canada, 11–13 September 2017, Springer.10.1007/978-3-319-66182-7_24 ↗
41. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation10.1016/j.neunet.2019.08.025 ↗
42. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016). Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv.10.1609/aaai.v31i1.11231 ↗
43. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.
44. Fully Dense UNet for 2-D Sparse Photoacoustic Tomography Artifact Removal10.1109/JBHI.2019.2912935 ↗
45. Deep convolutional neural network for inverse problems in imaging10.1109/TIP.2017.2713099 ↗
46. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
47. Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv.
48. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
49. Predicting parameters in deep learning
50. Sifre, L., and Mallat, P.S. (2014). Rigid-Motion Scattering For Image Classification Author. [Ph.D. Thesis, Ecole Polytechnique].
51. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
52. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
53. Guo, J., Li, Y., Lin, W., Chen, Y., and Li, J. (2018). Network decoupling: From regular to depthwise separable convolutions. arXiv.
54. Kaiser, L., Gomez, A.N., and Chollet, F. (2017). Depthwise separable convolutions for neural machine translation. arXiv.
55. Stacked fully convolutional networks with multi-channel learning: Application to medical image segmentation10.1007/s00371-017-1379-4 ↗
56. Pleiss, G., Chen, D., Huang, G., Li, T., van der Maaten, L., and Weinberger, K.Q. (2017). Memory-efficient implementation of densenets. arXiv.
57. DRINet for medical image segmentation10.1109/TMI.2018.2835303 ↗
58. Liu, S., and Huang, D. (2018, January 8–14). Receptive field block net for accurate and fast object detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01252-6_24 ↗
59. Chollet, F. (2021, October 26). Keras. Available online: https://www.scirp.org/(S(351jmbntvnsjt1aadkposzje))/reference/ReferencesPapers.aspx?ReferenceID=1887532.
60. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2–4). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16), Savannah, GA, USA.
61. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
62. The distribution of the flora in the alpine zone10.1111/j.1469-8137.1912.tb05611.x ↗
63. Measures of the amount of ecologic association between species10.2307/1932409 ↗
64. Maximum F1-score discriminative training criterion for automatic mispronunciation detection10.1109/TASLP.2015.2409733 ↗
65. A hybrid multilayer filtering approach for thyroid nodule segmentation on ultrasound images10.1002/jum.14731 ↗
66. Gadosey, P.K., Li, Y., Agyekum, E.A., Zhang, T., Liu, Z., Yamak, P.T., and Essaf, F. (2020). Sd-unet: Stripping down u-net for segmentation of biomedical images on platforms with low computational budgets. Diagnostics, 10.10.3390/diagnostics10020110 ↗
67. Attention gated networks: Learning to leverage salient regions in medical images10.1016/j.media.2019.01.012 ↗