Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Lumbar disc herniation (LDH) is a common clinical condition causing lower back and leg pain. Accurate segmentation of the lumbar discs is crucial for assessing and diagnosing LDH. Magnetic resonance imaging (MRI) can reveal the condition of articular cartilage. However, manual segmentation of MRI images is burdensome for physicians and needs to be more efficient.

Objective

In this study, we propose a method that combines UNet and superpixel segmentation to address the problem of loss of detailed information in the feature extraction phase, leading to poor segmentation results at object edges. The aim is to provide a reproducible solution for diagnosing patients with lumbar disc herniation.

Methods

We suggest using the network structure of UNet. Firstly, dense blocks are inserted into the UNet network, and training is performed using the Swish activation function. The Dense-UNet model extracts semantic features from the images and obtains rough semantic segmentation results. Then, an adaptive-scale superpixel segmentation algorithm is applied to segment the input images into superpixel images. Finally, high-level abstract semantic features are fused with the detailed information of the superpixels to obtain edge-optimized semantic segmentation results.

Results

Evaluation of a private dataset of multifidus muscles in magnetic resonance images demonstrates that compared to other segmentation algorithms, this algorithm exhibits better semantic segmentation performance in detailed areas such as object edges. Compared to UNet, it achieves a 9.5% improvement in the Dice Similarity Coefficient (DSC) and an 11.3% improvement in the Jaccard Index (JAC).

Conclusion

The experimental results indicate that this algorithm improves segmentation performance while reducing computational complexity.

© 2024 Xu et al.
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/cmir/10.2174/0115734056280128240201081830
2024-01-01
2025-07-07

  • From This Site

    /content/journals/cmir/10.2174/0115734056280128240201081830
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. Akçal MehmetA. Severe lumbar intervertebral disc degeneration is associated with modic changes and fatty infiltration in the paraspinal muscles at all lumbar levels, except for L1- L2: A crosssectional analysis of 50 sympto-matic women and 50 agematched symptomatic men.World Neurosurg.2019122e1069e107710.1016/j.wneu.2018.10.22930415054
     [Google Scholar]
  2. CooleyJ.R. WalkerB.F. M ArdakaniE. KjaerP. JensenT.S. HebertJ.J. Relationships between paraspinal muscle morphology and neurocompressive conditions of the lumbar spine: A systematic review with meta-analysis.BMC Musculoskelet. Disord.201819135110.1186/s12891‑018‑2266‑530261870
     [Google Scholar]
  3. ZhangX. [New concept of the development of modern medicine: Make full use of the internet, large data, and artificial intelligence].Zhongguo Fei Ai Za Zhi201821314114229587927
     [Google Scholar]
  4. HiltonGE. SalakhutdinovR. Reducing the dimensionality of data with neural networks.Science20063135786504507
     [Google Scholar]
  5. JonathanL. Fully convolutional networks for semantic segmentation.IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Boston, MA, USA, 07-12 June, 2015.
     [Google Scholar]
  6. Al-KafriA.S. SudirmanS. HussainA. Al-JumeilyD. NataliaF. MeidiaH. AfrilianaN. Al-RashdanW. BashtawiM. Al-JumailyM. Boundary delineation of MRI images for lumbar spinal stenosis detection through semantic segmentation using deep neural net-works.IEEE Access20197434874350110.1109/ACCESS.2019.2908002
     [Google Scholar]
  7. RonnebergerO. FischerP. BroxT. U-Net: Convolutional networks for biomedical image segmentation.Medical Image Computing and Computer-Assisted Intervention.Springer2015
     [Google Scholar]
  8. MilletariF. NavabN. AhmadiS.A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation.Fourth International Conference on 3D Vision (3DV).Stanford, CA, USA, 25-28 Oct, 2016 565-571.
     [Google Scholar]
  9. ZhouZ.W. SiddiqueeM.M.P. UNet++: A nested U-net architecture for medical image segmentation.Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Springer2018
     [Google Scholar]
  10. TangH. PeiX. HuangS. LiX. LiuC. Automatic lumbar spinal CT image segmentation with a dual densely connected U-Net.IEEE Access20208892288923810.1109/ACCESS.2020.2993867
     [Google Scholar]
  11. XuQ. MaZ. HeN. DuanW. DCSAU-Net: A deeper and more compact split-attention U-Net for medical image segmentation.Comput. Biol. Med.202315410662610.1016/j.compbiomed.2023.10662636736096
     [Google Scholar]
  12. GuZ W CE-Net: Context encoder network for 2D medical image segmentation.IEEE Transac. Med. Imag.2019381022812292
     [Google Scholar]
  13. HeK.M. ZhangX.Y. RenS.Q. Deep residual learning for image recognition.IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Las Vegas, NV, USA, 27-30 June, 2016 270-778.
     [Google Scholar]
  14. CaiY.T. MA-Unet: An improved version of Unet based on multi-scale and attention mechanism for medical image segmentation.Third International Conference on Electronics and Communication; Network and Computer Technology (ECNCT),Bellingham: SPIE, 2022; 12167: 205-211.
     [Google Scholar]
  15. SuR. ZhangD. LiuJ. ChengC. MSU-Net: Multi-scale U-Net for 2D medical image segmentation.Front. Genet.20211263993010.3389/fgene.2021.63993033679900
     [Google Scholar]
  16. SinhaA. DolzJ. Multi-scale self-guided attention for medical image segmentation.IEEE J. Biomed. Health Inform.202125112113010.1109/JBHI.2020.298692632305947
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056280128240201081830
Loading
Magnetic Resonance Images Segmentation of Multifidus based on Dense-unet and Superpixel
Curr. Med. Imaging 20, e15734056280128 (2024); https://doi.org/10.2174/0115734056280128240201081830
/content/journals/cmir/10.2174/0115734056280128240201081830
/content/journals/cmir/10.2174/0115734056280128240201081830
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Deep learning; Densely connected networks; Lumbar disc herniation; Medical image segmentation; MRI; Segmentation of superpixels

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