Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 60, Issue 10, 1010024(2023)

X-Ray Spine Corner Localization using an Embedded Attention Mechanism-Based Model

Yao Chen, Wenjun Yu*, and Yongbin Gao
Author Affiliations
  • School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (6)
    References (23)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Architecture of modified VFLD. (a) Basic network structure of VFLD; (b) architecture of rotational attention mechanism

    Fig. 1. Architecture of modified VFLD. (a) Basic network structure of VFLD; (b) architecture of rotational attention mechanism

    Download full size
    Schematic diagram of vector loss module

    Fig. 2. Schematic diagram of vector loss module

    Download full size
    Design sketch of data enhancement

    Fig. 3. Design sketch of data enhancement

    Download full size
    Identification result diagrams

    Fig. 4. Identification result diagrams

    Download full size
    Recognition result images of cervical vertebra

    Fig. 5. Recognition result images of cervical vertebra

    Download full size
    Ablation experiment

    Fig. 6. Ablation experiment

    Download full size

    • Table 1. Comparison indicators of model before and after improvement

      View table

      Table 1. Comparison indicators of model before and after improvement

      MethodSMAPE /%SMAPEPT /%SMAPEMT /%SMAPETL /%Edec /pixelFPSWeight /MB
      Original network10.816.2618.0423.4250.1111.4097
      Proposed network9.315.7515.1822.3548.7511.3498.5

    • Table 2. Result comparison of MICCAI 2019 spine challenge dataset

      View table

      Table 2. Result comparison of MICCAI 2019 spine challenge dataset

      MethodSMAPESMAPEPTSMAPEMTSMAPETL
      Original method10.816.2618.0423.42
      Seg4Reg‎［18］22.25
      Regression method‎［19］23.4316.3830.2735.61
      ACAD‎［20］25.69
      Segmentation method‎［21］16.489.7125.9733.01
      SCG-Net‎［22］22.17
      AAKD‎［23］22.16
      Proposed method9.315.7515.1822.35

    • Table 3. Comparison experiment before and after improvement of cervical vertebrae dataset

      View table

      Table 3. Comparison experiment before and after improvement of cervical vertebrae dataset

      MethodSMAPE /%Edec /pixelFPSWeight /MB

      method

      Original

      		8.4416.4114.697
      Proposed method6.2115.2114.698.5M

    • Table 4. Ablation experiment

      View table

      Table 4. Ablation experiment

      MethodSMAPE /%
      Original network10.81
      Original network + rotational attention module9.42
      Original network + rotational Attention module +vector loss module9.31
    Tools

    Get Citation

    Copy Citation Text

    Yao Chen, Wenjun Yu, Yongbin Gao. X-Ray Spine Corner Localization using an Embedded Attention Mechanism-Based Model[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1010024

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Mar. 1, 2022

    Accepted: May. 10, 2022

    Published Online: May. 17, 2023

    The Author Email: Yu Wenjun (yuwenjun@sues.edu.cn)

    DOI:10.3788/LOP220851

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology