ARF-NET:Method of spinal segmentation in deformed spine radiographs

Deformed spine radiograph spine segmentation can help doctors to analyze the disease site faster, which is a necessary part of the current development of competent healthcare. For scoliosis diagnosis, this paper designs an Attention-guided ResNet with an FPN-like Upsampling model(ARF-Net) for segmen...

Full description

Saved in:
Bibliographic Details
Published in2023 11th International Conference on Information Systems and Computing Technology (ISCTech) pp. 154 - 157
Main Authors Lin, XiaTian, Liu, Yingli, Shen, Tao, Gao, Ming
Format Conference Proceeding
LanguageEnglish
Published IEEE 30.07.2023
Subjects
attention mechanism
Computers
Diagnostic radiography
Diseases
Image Segmentation
Information systems
Medical services
residual network
Residual neural networks
Scoliosis
Spinal X-ray
Online AccessGet full text
DOI10.1109/ISCTech60480.2023.00035

Cover

More Information
Summary:Deformed spine radiograph spine segmentation can help doctors to analyze the disease site faster, which is a necessary part of the current development of competent healthcare. For scoliosis diagnosis, this paper designs an Attention-guided ResNet with an FPN-like Upsampling model(ARF-Net) for segmenting the cone part of the spine radiograph map. In this paper, ResNet50 is used as the backbone to propose the feature map. Then the Global-Coordinate Attention (GCA) attention mechanism is added to obtain the X-axis, Y-axis, and global features. Finally, through the SIMAMUP module, the feature map is upsampled to introduce more detailed information to prevent cone segmentation errors and to improve the cone segmentation capability. The final experimental findings demonstrate that the model described in this study has greater segmentation precision in the SpineWebl6 public dataset, with the Jaccard and Dice coefficients reaching 87.70% and 93.45%, respectively.
DOI:10.1109/ISCTech60480.2023.00035