Automatic spinal cord segmentation as organ at risk in planning CT using adaptive template matching and U-Net

  • João Diniz IFMA
  • Jonnison Ferrreira UFMA
  • Pedro Diniz IFMA
  • Bruno Serejo IFMA
  • Neilson Ribeiro IFMA
  • Osias Santos IFMA
  • Aristófanes Silva UFMA
  • Anselmo Paiva UFMA

Resumo


Radiotherapy is one of the major option used in cancer management. The treatment involves several steps, one of which is the construction of a computed tomography (CT) model of the patient so that the target tissues and organs at risk (OARs) surrounding that target can be evaluated. With the CT, the responsible physician delimits the OARs slice by slice, as the spinal cord that comprises almost all the tomography becomes more tiring to be segmented and thus susceptible to errors. Thus, this paper presents a method of spinal cord segmentation in planning CT for radiotherapy. The result achieved an accuracy of 99.18%, specificity of 99.30%, sensitivity of 92.64%, and dice index of 80.83%, without any segmentation refinement.

Referências

Banik, S., Rangayyan, R. M., and Boag, G. S. (2010). Automatic segmentation of the ribs, the vertebral column, and the spinal canal in pediatric computed tomographic images. Journal of digital imaging, 23(3):301–322.

Chen, M., Carass, A., Oh, J., Nair, G., Pham, D. L., Reich, D. S., and Prince, J. L. (2013). Automatic magnetic resonance spinal cord segmentation with topology constraints for variable fields of view. Neuroimage, 83:1051–1062.

De Leener, B., Cohen-Adad, J., and Kadoury, S. (2015). Automatic segmentation of the spinal cord and spinal canal coupled with vertebral labeling. IEEE transactions on medical imaging, 34(8):1705–1718.

Diniz, J. O. B., Diniz, P. H. B., Valente, T. L. A., Silva, A. C., and Paiva, A. C. (2019). Spinal cord detection in planning ct for radiotherapy through adaptive template matching, imslic and convolutional neural networks. Computer methods and programs in biomedicine, 170(3):53–67

Evans, E. and Staffurth, J. (2018). Principles of cancer treatment by radiotherapy. Surgery-Oxford International Edition, 36(3):111–116.

Fu, G., Lu, H., Tan, J. K., Kim, H., Zhu, X., and Lu, J. (2018). Segmentation of spinal canal region in ct images using 3d region growing technique. In 2018 International Conference on Information and Communication Technology Robotics (ICT-ROBOT), pages 1–4. IEEE.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.

Tsang, Y. M. and Hoskin, P. (2017). The impact of bladder preparation protocols on post treatment toxicity in radiotherapy for localised prostate cancer patients. Technical Innovations and Patient Support in Radiation Oncology, 3:37–40.
Publicado
26/12/2019
Como Citar

Selecione um Formato
DINIZ, João; FERRREIRA, Jonnison; DINIZ, Pedro; SEREJO, Bruno; RIBEIRO, Neilson; SANTOS, Osias; SILVA, Aristófanes; PAIVA, Anselmo. Automatic spinal cord segmentation as organ at risk in planning CT using adaptive template matching and U-Net. In: ESCOLA REGIONAL DE COMPUTAÇÃO APLICADA À SAÚDE (ERCAS), 7. , 2019, Teresina. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . p. 151-156.