Spine MRI image segmentation method based on ASPP and U-Net network

Biao Cai; Qing Xu; Cheng Yang; Yi Lu; Cheng Ge; Zhichao Wang; Kai Liu; Xubin Qiu; Shan Chang; Biao Cai; Qing Xu; Cheng Yang; Yi Lu; Cheng Ge; Zhichao Wang; Kai Liu; Xubin Qiu; Shan Chang

doi:10.3934/mbe.2023713

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 9: 15999-16014. doi: 10.3934/mbe.2023713

Previous Article Next Article

Research article

Spine MRI image segmentation method based on ASPP and U-Net network

1.
Institute of Bioinformatics and Pharmaceutical Engineering, Jiangsu University of Technology, Changzhou 213001, China
2.
The Third Affiliated Hospital of Soochow University, Changzhou 213000, China
3.
Key Laboratory of Marine Drugs, Chinese Ministry of Education, School of Medicine and Pharmacy, Ocean University of China, Qingdao 266003, China

Academic Editor: Yang Kuang

Received: 18 May 2023 Revised: 09 July 2023 Accepted: 25 July 2023 Published: 04 August 2023

The spine is one of the most important structures in the human body, serving to support the body, organs, protect nerves, etc. Medical image segmentation for the spine can help doctors in their clinical practice for rapid decision making, surgery planning, skeletal health diagnosis, etc. The current difficulty is mainly the poor segmentation accuracy of skeletal Magnetic Resonance Imaging (MRI) images. To address the problem, we propose a spine MRI image segmentation method, Atrous Spatial Pyramid Pooling (ASPP)-U-shaped network (UNet), which combines an ASPP structure with a U-Net network. This approach improved the network feature extraction by introducing an ASPP structure into the U-Net network down-sampling structure. The medical image segmentation models are trained and tested on publicly available datasets and obtained the Dice coefficient and Mean Intersection over Union coefficients with 0.866 and 0.755, respectively. The experimental results show that ASPP-UNet has higher accuracy for spine MRI image segmentation compared with other mainstream networks.
- ASPP,
- U-Net,
- spine,
- segmentation,
- DeepLabV3
Citation: Biao Cai, Qing Xu, Cheng Yang, Yi Lu, Cheng Ge, Zhichao Wang, Kai Liu, Xubin Qiu, Shan Chang. Spine MRI image segmentation method based on ASPP and U-Net network[J]. Mathematical Biosciences and Engineering, 2023, 20(9): 15999-16014. doi: 10.3934/mbe.2023713

Related Papers:

Abstract

The spine is one of the most important structures in the human body, serving to support the body, organs, protect nerves, etc. Medical image segmentation for the spine can help doctors in their clinical practice for rapid decision making, surgery planning, skeletal health diagnosis, etc. The current difficulty is mainly the poor segmentation accuracy of skeletal Magnetic Resonance Imaging (MRI) images. To address the problem, we propose a spine MRI image segmentation method, Atrous Spatial Pyramid Pooling (ASPP)-U-shaped network (UNet), which combines an ASPP structure with a U-Net network. This approach improved the network feature extraction by introducing an ASPP structure into the U-Net network down-sampling structure. The medical image segmentation models are trained and tested on publicly available datasets and obtained the Dice coefficient and Mean Intersection over Union coefficients with 0.866 and 0.755, respectively. The experimental results show that ASPP-UNet has higher accuracy for spine MRI image segmentation compared with other mainstream networks.

References

[1]	D. Lee, S. H. Tak, Fear of falling and related factors in older adults with spinal diseases, J. Gerontol. Nurs., 47 (2021), 29–35. https://doi.org/10.3928/00989134-20210624-05 doi: 10.3928/00989134-20210624-05
[2]	F. C. Kohler, P. Schenk, M. Bechstedt-Schimske, B. W. Ullrich, F. Klauke, G. O. Hofmann, et. al., Open versus minimally invasive fixation of thoracic and lumbar spine fractures in patients with ankylosing spinal diseases, Eur. J. Trauma Emerg. Surg., 48 (2021), 2297–2307. https://doi.org/10.1007/s00068-021-01756-3 doi: 10.1007/s00068-021-01756-3
[3]	F. R. V. Tol, A. L. Versteeg, H. M. Verkooijen, F. C. Öner, J. J. Verlaan, Time to surgical treatment for metastatic spinal disease: Identification of delay intervals, Global Spine J., 13 (2021). https://doi.org/10.1177/2192568221994787 doi: 10.1177/2192568221994787
[4]	W. Jung, S. S. Shim, K. Kim, CT findings of acute radiation-induced pneumonitis in breast cancer, Br. J. Radiol., 94 (2021). https://doi.org/10.1259/bjr.20200997 doi: 10.1259/bjr.20200997
[5]	S. Amiri, M. Akbarabadi, F. Abdolali, A. Nikoofar, A. J. Esfahani, S. Cheraghi, Radiomics analysis on CT images for prediction of radiation-induced kidney damage by machine learning models, Comput. Biol. Med., 133 (2021), 104409. https://doi.org/10.1016/j.compbiomed.2021.104409 doi: 10.1016/j.compbiomed.2021.104409
[6]	H. Zhang, Z. Tang, Y. Xie, X. Gao, Q. Chen, A watershed segmentation algorithm based on an optimal marker for bubble size measurement, Measurement, 138 (2019), 182–193. https://doi.org/10.1016/j.measurement.2019.02.005 doi: 10.1016/j.measurement.2019.02.005
[7]	A. Kornilov, I. Safonov, I. Yakimchuk, A review of watershed implementations for segmentation of volumetric images, J. Imaging, 8 (2022), 127. https://doi.org/10.3390/jimaging8050127 doi: 10.3390/jimaging8050127
[8]	A. Kucharski, A. Fabijańska, CNN-watershed: A watershed transform with predicted markers for corneal endothelium image segmentation, Biomed. Signal Process., 68 (2021), 102805. https://doi.org/10.1016/j.bspc.2021.102805 doi: 10.1016/j.bspc.2021.102805
[9]	O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention, 9351 (2015), 234–241.
[10]	J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015), 3431–3440. https://doi.org/10.1109/CVPR.2015.7298965
[11]	J. Zhang, C. Li, S. Kosov, M. Grzegorzek, K. Shirahama, T. Jiang, et. al., LCU-Net: A novel low-cost U-Net for environmental microorganism image segmentation, Pattern Recognit., 115 (2021), 107885. https://doi.org/10.1016/j.patcog.2021.107885 doi: 10.1016/j.patcog.2021.107885
[12]	Z. Liu, Y. Cao, Y. Wang, W. Wang, Computer vision-based concrete crack detection using U-net fully convolutional networks, Autom. Constr., 104 (2019), 129–139. https://doi.org/10.1016/j.autcon.2019.04.005 doi: 10.1016/j.autcon.2019.04.005
[13]	J. Zhou, Y. Lu, S. Tao, X. Cheng, C. Huang, E-Res U-Net: An improved U-Net model for segmentation of muscle images, Expert Syst. Appl., 185 (2021), 115625. https://doi.org/10.1016/j.eswa.2021.115625 doi: 10.1016/j.eswa.2021.115625
[14]	X. Dong, Y. Lei, T. Wang, M. Thomas, L. Tang, W. J. Curran, et. al., Automatic multiorgan segmentation in thorax CT images using U-net-GAN, Med. Phys., 46 (2019), 2157–2168. https://doi.org/10.1002/mp.13458 doi: 10.1002/mp.13458
[15]	G. Tong, Y. Li, H. Chen, Q. Zhang, H. Jiang, Improved U-NET network for pulmonary nodules segmentation, Optik, 174 (2018), 460–469. https://doi.org/10.1016/j.ijleo.2018.08.086 doi: 10.1016/j.ijleo.2018.08.086
[16]	N. Siddique, S. Paheding, C. P. Elkin, V. Devabhaktuni, U-net and its variants for medical image segmentation: A review of theory and applications, IEEE Access, 9 (2021), 82031–82057. https://doi.org/10.1109/ACCESS.2021.3086020 doi: 10.1109/ACCESS.2021.3086020
[17]	G. Du, X. Cao, J. Liang, X. Chen, Y. Zhan, Medical image segmentation based on u-net: A review, J. Imaging Sci. Technol., 64 (2020), 1–12. https://doi.org/10.2352/J.ImagingSci.Technol.2020.64.2.020508 doi: 10.2352/J.ImagingSci.Technol.2020.64.2.020508
[18]	H. El-Hariri, L. A. S. M. Neto, P. Cimflova, F. Bala, R. Golan, A. Sojoudi, et. al., Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with Acute Ischemic Stroke, Comput. Biol. Med., 141 (2022), 105033. https://doi.org/10.1016/j.compbiomed.2021.105033 doi: 10.1016/j.compbiomed.2021.105033
[19]	V. Badrinarayanan, A. Kendall, R. Cipolla, Segnet: A deep convolutional encoder-decoder architecture for image segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 39 (2017), 2481–2495. https://doi.org/10.1109/TPAMI.2016.2644615 doi: 10.1109/TPAMI.2016.2644615
[20]	L. Chen, G. Papandreou, I. Kokkinos, K. Murphy, A. L. Yuille, Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE Trans. Pattern Anal. Mach. Intell., 40 (2017), 834–848. https://doi.org/10.1109/TPAMI.2017.2699184 doi: 10.1109/TPAMI.2017.2699184
[21]	S. Pang, C. Pang, L. Zhao, Y. Chen, Z. Su, Y. Zhou, et. al., SpineParseNet: Spine parsing for volumetric MR image by a two-stage segmentation framework with semantic image representation, IEEE Trans. Med. Imaging, 40 (2020), 262–273. https://doi.org/10.1109/TMI.2020.3025087 doi: 10.1109/TMI.2020.3025087
[22]	S. Pang, C. Pang, Z. Su, L. Lin, L. Zhao, Y. Chen, et. al., DGMSNet: Spine segmentation for MR image by a detection-guided mixed-supervised segmentation network, Med. Image Anal., 75 (2022), 102261. https://doi.org/10.1016/j.media.2021.102261 doi: 10.1016/j.media.2021.102261
[23]	R. Liu, F. Tao, X. Liu, J. Na, H. Leng, J. Wu, et. al., RAANet: A residual ASPP with attention framework for semantic segmentation of high-resolution remote sensing images, Remote Sens., 14 (2022), 3109. https://doi.org/10.3390/rs14133109 doi: 10.3390/rs14133109
[24]	T. Lei, R. Wang, Y. Zhang, Y. Wan, C. Liu, A. K. Nandi, DefED-Net: Deformable encoder-decoder network for liver and liver tumor segmentation, IEEE Trans. Radiat. Plasma Med. Sci., 6 (2021), 68–78. https://doi.org/10.1109/TRPMS.2021.3059780 doi: 10.1109/TRPMS.2021.3059780
[25]	Y. Weng, T. Zhou, Y. Li, X. Qiu, Nas-unet: Neural architecture search for medical image segmentation, IEEE Access, 7 (2019), 44247–44257. https://doi.org/10.1109/ACCESS.2019.2908991 doi: 10.1109/ACCESS.2019.2908991
[26]	Z. Luo, Y. Zhang, L. Zhou, B. Zhang, J. Luo, H. Wu, Micro-vessel image segmentation based on the AD-UNet model, IEEE Access, 7 (2019), 143402–143411. https://doi.org/10.1109/ACCESS.2019.2945556 doi: 10.1109/ACCESS.2019.2945556
[27]	P. Ahmad, H. Jin, R. Alroobaea, S. Qamar, R. Zheng, F. Alnajjar, et. al., MH UNet: A multi-scale hierarchical based architecture for medical image segmentation, IEEE Access, 9 (2021), 148384–148408. https://doi.org/10.1109/ACCESS.2021.3122543 doi: 10.1109/ACCESS.2021.3122543
[28]	X. Li, H. Chen, X. Qi, Q. Dou, C. Fu, P. Heng, H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes, IEEE Trans. Med. Imaging, 37 (2018), 2663–2674. https://doi.org/10.1109/TMI.2018.2845918 doi: 10.1109/TMI.2018.2845918

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)