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

Abstract

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.

Automatic segmentation of the spine by means of a probabilistic atlas with a special focus on ribs suppression. Preliminary results

“…In the case of the spine clear reference points are available because of the presence of the vertebral canal, the space in vertebrae through which the spinal cord passes. Vertebral canal can be segmented in a fully automatic way [18] and their central points at each slice constitute a curve in 3D, from now on, the 'guiding curve', shown in Fig. 1 (a.1).…”

“…1(c). To generate initial contours it uses seed points detected automatically in the spinal canal using the method proposed by Díaz-Parra et al [18].…”

Research on Spinal Canal Generation Method based on Vertebral Foramina Inpainting of Spinal CT Images by using BEGAN

“…The automatic detection of vertebral foramina in CT images is still a problem. Although predecessors have done a lot of work on the vertebral foramen segmentation of the spinal CT image [6][7][8][9][10][11][12], it is still difficult to develop an easy-to-use, robust, accurate, and efficient algorithm [7,13].…”

“…However, these methods are not efficient for the segmentation of CT images. Therefore, Díaz-Parra et al [9] proposed a Gradient Vector Flow algorithm to automatically segment the spinal canal in CT images and evaluate three patients using the Dice coefficient, with accuracy rates of 79.50%, 83.77%, and 81.88%, respectively. Cheng et al [10] proposed a learning-based method to extract the centerline of the spine and the centerline of the spinal canal.…”