Automatically Extract Vertebra and Compute the Cobb Angle based on Spine’s Features and Adaptive ASMs in Posteroanterior Radiographs

Nowadays, clinical diagnoses are more and more supported by medical equipment, but doctors still need a lot of time and effort to diagnosis. The construction of a system that can diagnose automatically will help doctors a lot when the doctor must handle many medical records. Many diseases need to be diagnosed by radiographs and they can be diagnosed automatically, especially bone diseases. The purpose of this paper is to introduce a new method to measure the curve of the spine in the X-ray images. We split this subject into two problems. The first problem is to extract the spine from the X-ray image. We use the threshold to remove redundant information from the images. Then an automatic mask is created to save the position of the spine and smooth the boundary of the spine. Based on the spine extracted from the previous steps, the Active Shape Model (ASM) which is designed from the characteristics of the vertebrae, is used to extract each vertebra from the spine. Finally, we measure the Cobb angle which is formed by vertebrae. The solution of two problems is implemented on X-ray images which have high quality, the results are more than 80% an area of the spine is extracted, and the Cobb angle is measured correctly, the accuracy of our method will decrease if the quality of the image is low.

@article{Bao2019,
  title     = {Automatically Extract Vertebra and Compute the Cobb Angle based on Spine’s Features and Adaptive ASMs in Posteroanterior Radiographs},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {10},
  number    = {12},
  year      = {2019},
  publisher = {The Science and Information Organization},
  author    = {Pham The Bao},
  doi       = {10.14569/IJACSA.2019.0101209},
  url       = {https://doi.org/10.14569/IJACSA.2019.0101209}
}