Fully automatic spinal canal segmentation for radiation therapy using a Gradient Vector Flow-based method on computed tomography images: A preliminary study

Nowadays, radiotherapy is one of the key techniques for localized cancer treatment. Accurate identification of target volume (TV) and organs at risk (OAR) is a crucial step to therapy success. Spinal cord is one of the most radiosensitive OAR and its localization tends to be an observer-dependent and time-consuming task. Hence, numerous studies have aimed to carry out the contouring automatically. In CT images, there is a lack of contrast between soft tissues, making more challenge the delineation. That is the reason why the majority of researches have focused on spinal canal segmentation rather than spinal cord. In this work, we propose a fully automated method for spinal canal segmentation using a Gradient Vector Flow-based (GVF) algorithm. An experienced radiologist performed the manual segmentation, generating the ground truth. The method was evaluated on three different patients using the Dice coefficient, obtaining the following results: 79.50%, 83.77%, and 81.88%, respectively. Outcome reveals that more research has to be performed to improve the accuracy of the method.

[1]  Zhongxing Liao,et al.  A deformable-model approach to semi-automatic segmentation of CT images demonstrated by application to the spinal canal. , 2004, Medical physics.

[2]  C J Moore,et al.  Automated delineation of radiotherapy volumes: are we going in the right direction? , 2013, The British journal of radiology.

[3]  Stelios Zimeras,et al.  An Accurate 3D Segmentation Method of the Spinal Canal Applied to CT Data , 2002, Bildverarbeitung für die Medizin.

[4]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[5]  Steven Bedrick,et al.  Development of a Software for Quantitative Evaluation Radiotherapy Target and Organ-at-Risk Segmentation Comparison , 2014, Journal of Digital Imaging.

[6]  Estanislao Arana,et al.  A fully automated method for spinal canal detection in computed tomography images , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Johannes A Langendijk,et al.  Delineation guidelines for organs at risk involved in radiation-induced salivary dysfunction and xerostomia. , 2009, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[8]  Rangaraj M. Rangayyan,et al.  Method for the automatic detection and segmentation of the spinal canal in computed tomographic images , 2006, J. Electronic Imaging.

[9]  Michael Egmont-Petersen,et al.  A knowledge-based approach to automatic detection of the spinal cord in CT images , 2002, IEEE Transactions on Medical Imaging.

[10]  László G. Nyúl,et al.  Method for Automatically Segmenting the Spinal Cord and Canal from 3D CT Images , 2005, CAIP.

[11]  C. Njeh,et al.  Tumor delineation: The weakest link in the search for accuracy in radiotherapy , 2008, Journal of medical physics.

[12]  David A. Jaffray,et al.  Radiation Therapy for Cancer , 2015 .

[13]  A. Taylor,et al.  Intensity-modulated radiotherapy—what is it? , 2004, Cancer imaging : the official publication of the International Cancer Imaging Society.

[14]  Ronald M. Summers,et al.  Detection of Vertebral Body Fractures Based on Cortical Shell Unwrapping , 2012, MICCAI.

[15]  E. R. van den Heuvel,et al.  3D Variation in delineation of head and neck organs at risk , 2012, Radiation oncology.

[16]  Junaed Sattar.  Snakes , Shapes and Gradient Vector Flow , 2022 .

[17]  E H KIM,et al.  [Radiation therapy for cancer]. , 1963, Taehan Uihak Hyophoe chi. The Journal of the Korean Medical Association.

[18]  Jing Jia,et al.  Automatic Segmentation of the Body and the Spinal Canal in CT Images Based on A Priori Information , 2011, 2011 5th International Conference on Bioinformatics and Biomedical Engineering.