Skip to content
2000
  1. Home
  2. Volume 20, Issue 1
  3. Article
  • E-ISSN:
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background:

Intervertebral disc degeneration (IVD) is now the most prevalent disease in the world; thus, precise intervertebral disc segmentation is essential for the assessment and diagnosis of spinal diseases. Multi-modal magnetic resonance (MR) imaging is more multi-dimensional and thorough than unimodal imaging. However, manual segmentation of multi-modal MRI not only imposes a huge burden on physicians but also has a high error rate.

Objective:

In this study, we propose a new method that can efficiently and accurately segment intervertebral discs from multi-modal MR spine images, providing a reproducible usage scheme for the diagnosis of spinal disorders.

Methods:

We suggest a network structure called MLP-Res-Unet that reduces the amount of computational load and the number of parameters while maintaining performance. Our contribution is two-fold. First, a medical image segmentation network that fuses residual blocks and a multilayer perceptron (MLP) is proposed. Secondly, we design a new deep supervised method and pass the features extracted from the encoder to the decoder through the residual path to achieve a new full-scale residual connection.

Results:

We evaluate the network on the MICCAI-2018 IVD dataset and obtain Dice similarity coefficient equal to 94.77 (%) and Jaccard coefficient equal to 84.74 (%), while we reduce the amount of parameters by a factor of 3.9 and computation by a factor of 2.4 compared to the IVD-Net.

Conclusion:

Experiments show that MLP-Res-Unet improves segmentation performance and creates a simpler model structure while reducing the number of parameters and computation.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmim/10.2174/1573405620666230417082855
2023-05-24
2025-01-10

  • From This Site

    /content/journals/cmim/10.2174/1573405620666230417082855
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmim/20/1/e170423215841.html?itemId=/content/journals/cmim/10.2174/1573405620666230417082855&mimeType=html&fmt=ahah

References

  1. BalaguéF. TroussierB. SalminenJ.J. Non-specific low back pain in children and adolescents: Risk factors.Eur. Spine J.19998642943810.1007/s00586005020110664299
     [Google Scholar]
  2. ZhouT. RuanS. CanuS. A review: Deep learning for medical image segmentation using multi-modality fusion.Array2019100004
     [Google Scholar]
  3. TaoR. LiuW. ZhengG. Spine-transformers: Vertebra labeling and segmentation in arbitrary field-of-view spine CTs via 3D transformers.Med. Image Anal.20227510225810.1016/j.media.2021.10225834670147
     [Google Scholar]
  4. RonnebergerO. FischerP. BroxT. U-net: Convolutional networks for biomedical image segmentation.Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015.20159351234241
     [Google Scholar]
  5. KimS. BaeW. MasudaK. ChungC. HwangD. Fine-Grain segmentation of the intervertebral discs from MR spine images using deep convolutional neural networks: BSU-Net.Appl. Sci.201889165610.3390/app809165630637135
     [Google Scholar]
  6. ZhangY. YuanL. WangY. ZhangJ. SAU-Net: Efficient 3D Spine MRI segmentation using inter-slice attention.Medical Imaging with Deep Learning2020903913
     [Google Scholar]
  7. ChengY.K. LinC.L. HuangY.C. ChenJ.C. LanT.P. LianZ.Y. ChuangC.H. Automatic segmentation of specific intervertebral discs through a two-stage multiresunet model.J. Clin. Med.20211020476010.3390/jcm1020476034682885
     [Google Scholar]
  8. ChengP. YangY. YuH. HeY. Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net.Sci. Rep.20211112215610.1038/s41598‑021‑01296‑134772972
     [Google Scholar]
  9. ValanarasuJ.M.J. PatelV.M. Unext: Mlp-based rapid medical image segmentation network.Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference2022134352333
     [Google Scholar]
  10. DolzJ. DesrosiersC. Ben AyedI. IVD-Net: Intervertebral Disc Localization and Segmentation in MRI with a Multi-modal UNet.Computational Methods and Clinical Applications for Spine Imaging: 5th International Workshop and Challenge, CSI 2018, Held in Conjunction with MICCAI 2018201811397130143
     [Google Scholar]
  11. SrivastavaA. JhaD. ChandaS. PalU. JohansenH. JohansenD. RieglerM. AliS. HalvorsenP. Msrf-net: A multi-scale residual fusion network for biomedical image segmentation.IEEE J. Biomed. Health Inform.20222652252226310.1109/JBHI.2021.313802434941539
     [Google Scholar]
  12. ZhangJ. XieY. WangY. XiaY. Inter-slice context residual learning for 3D medical image segmentation.IEEE Trans. Med. Imaging202140266167210.1109/TMI.2020.303499533125324
     [Google Scholar]
  13. MubasharM. AliH. GrönlundC. AzmatS. R2U++: A multiscale recurrent residual U-Net with dense skip connections for medical image segmentation.Neural Comput. Appl.20223420177231773910.1007/s00521‑022‑07419‑735694048
     [Google Scholar]
  14. TranS.T. NguyenM.H. DangH.P. NguyenT.T. Automatic polyp segmentation using modified recurrent residual Unet network.IEEE Access202210659516596110.1109/ACCESS.2022.3184773
     [Google Scholar]
  15. ChengJ. TianS. YuL. GaoC. KangX. MaX. WuW. LiuS. LuH. ResGANet: Residual group attention network for medical image classification and segmentation.Med. Image Anal.20227610231310.1016/j.media.2021.10231334911012
     [Google Scholar]
  16. PunnN.S. AgarwalS. RCA-IUnet: A residual cross-spatial attention-guided inception U-Net model for tumor segmentation in breast ultrasound imaging.Mach. Vis. Appl.20223322710.1007/s00138‑022‑01280‑3
     [Google Scholar]
  17. WangZ. ZouY. LiuP.X. Hybrid dilation and attention residual U-Net for medical image segmentation.Comput. Biol. Med.202113410444910.1016/j.compbiomed.2021.104449
     [Google Scholar]
  18. DutandeP. BaidU. TalbarS. Deep residual separable convolutional neural network for lung tumor segmentation.Comput. Biol. Med.202214110516110.1016/j.compbiomed.2021.10516134999468
     [Google Scholar]
  19. LvJ. HuY. FuQ. CM-MLP: Cascade multi-scale mlp with axial context relation encoder for edge segmentation of medical image.2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)20221100110710.1109/BIBM55620.2022.9995348
     [Google Scholar]
  20. LianD. YuZ. SunX. GaoS. As-mlp: An axial shifted mlp architecture for vision.arXiv201708391
     [Google Scholar]
  21. JiaY. PanX. MS-DC-UNeXt: An MLP-based Multi-Scale Feature Learning Framework For X-ray Images.arXiv2022221012361
     [Google Scholar]
  22. YanJ. WangX. CaiJ. QinQ. YangH. WangQ. ChengY. GanT. JiangH. DengJ. ChenB. Medical image segmentation model based on triple gate MultiLayer perceptron.Sci. Rep.2022121610310.1038/s41598‑022‑09452‑x35413958
     [Google Scholar]
  23. AnL. WangL. LiY. HEA-Net: Attention and MLP hybrid encoder architecture for medical image segmentation.Sensors20222218702410.3390/s2218702436146373
     [Google Scholar]
  24. GuoJ. TangY. HanK. Hire-mlp: vision mlp via hierarchical rearrangement.Proceedings of the IEEE/CVF conference on computer vision and pattern recognition2022New OrleansLA, USA826836
     [Google Scholar]
  25. TolstikhinI.O. HoulsbyN. KolesnikovA. MLP-Mixer: An all-MLP Architecture for Vision.Adv. Neural Inf. Process. Syst.2021342426124272
     [Google Scholar]
  26. ZhouZ. SiddiqueeM.M.R. TajbakhshN. LiangJ. UNet++: Redesigning skip connections to exploit multiscale features in image segmentation.IEEE Trans. Med. Imaging20203961856186710.1109/TMI.2019.295960931841402
     [Google Scholar]
  27. CaoH. WangY. ChenJ. Swin-Unet: Unet-like pure transformer for medical image segmentation.Computer vision - ECCV 2022 workshops. KarlinslyL MichaeliT NishinoK Springer, Cham202313803
     [Google Scholar]
  28. LiC. LiuT. ChenZ. SPA-RESUNET: Strip pooling attention resunet for multi-class segmentation of vertebrae and intervertebral discs.In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI).202215
     [Google Scholar]
  29. WangH. ZhuY. GreenB. AdamH. YuilleA. ChenL.C. Axial-deeplab: Stand-alone axial-attention for panoptic segmentation.In: UK, Glasgow, Computer Vision–ECCV 2020: 16th European Conference2020108126
     [Google Scholar]
  30. ŠušteršičT. RankovićV. MilovanovicV. KovačevićV. RasulićL. FilipovićN. A deep learning model for automatic detection and classification of disc herniation in magnetic resonance images.IEEE J. Biomed. Health Inform.202226126036604610.1109/JBHI.2022.320958536155472
     [Google Scholar]
  31. LiaskosM. SavelonasM.A. AsvestasP.A. LykissasM.G. MatsopoulosG.K. Bimodal CT/MRI-based segmentation method for intervertebral disc boundary extraction.Information202011944810.3390/info11090448
     [Google Scholar]
  32. HuangH. LinL. TongR. Unet 3+: A full-scale connected unet for medical image segmentation.ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)202010551059
     [Google Scholar]
/content/journals/cmim/10.2174/1573405620666230417082855
Loading
MLP-Res-Unet: MLPs and Residual Blocks-based U-shaped Network Intervertebral Disc Segmentation of Multi-modal MR Spine Images
20, e170423215841 (2024); https://doi.org/10.2174/1573405620666230417082855
/content/journals/cmim/10.2174/1573405620666230417082855
/content/journals/cmim/10.2174/1573405620666230417082855
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Deep learning; Intervertebral disc segmentation; Medical image segmentation; MR spine images; MRI; Multi-modal imaging

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test