A fully automated level-set based segmentation method of thoracic and lumbar vertebral bodies in Computed Tomography images

Abstract

Spine is a structure commonly involved in several diseases. Identification and segmentation of the vertebral structures are of relevance to many medical applications related to the spine such as diagnosis, therapy or surgical intervention. However, the development of automatic and reliable methods are an unmet need. This work presents a fully automatic segmentation method of thoracic and lumbar vertebral bodies from Computed Tomography images. The procedure can be divided into four main stages: firstly, seed points were detected in the spinal canal in order to generate initial contours in the segmentation process, automating the whole process. Secondly, a processing step is performed to improve image quality. Third step was to carry out the segmentation using the Selective Binary Gaussian Filtering Regularized Level Set method and, finally, two morphological operations were applied in order to refine the segmentation result. The method was tested in clinical data coming from 10 trauma patients. To evaluate the result the average value of the DICE coefficient was calculated, obtaining a 90.86 ± 1.87% in the whole spine (thoracic and lumbar regions), a 86.08 ± 1.73% in the thoracic region and a 95,61 ±2,25% in the lumbar region. The results are highly competitive when compared to the results obtained in previous methods, especially for the lumbar region.

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

“…To perform a initial segmentation of the spine a fully automated method for vertebrae segmentation was used [19]. This method permits the segmentation of cervical, thoracic and lumbar vertebrae in CT images using a region-based active contour.…”

Automatic segmentation of vertebral contours from CT images using fuzzy corners

“…To overcome the inherent drawbacks of thresholding, an adaptive 3D region growing method is devised in [12]. A fully automated method of segmentation for delineating the thoracic and lumbar vertebrae is given in [13]. While it calls for seed placement in the canal, a level-set is allowed to evolve followed by a voxel-based delineation.…”

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

“…However, the availability of this kind of data is not always possible, therefore, other methods that do not require any form of prior knowledge are used, too. Some of them are approximations based on thresholding, watershed, and direct graph methods, or level set methods . Level‐set methods are particularly appropriate for dealing with different features such as cavities or convoluted areas.…”

“…However, many of these works either do not segment all thoracic and lumbar vertebrae, or they are not completely automatic, or have been only tested in healthy cases . The presence of the ribs is one of the problems for which different methods show less accuracy in the segmentation of the thoracic region . This is mainly due to the difficulty of discriminating between these structures and the vertebrae.…”

“…However, by using only atlas‐based segmentation methods it is difficult to capture the fine details or localize areas with high cavities in complex images, mainly due to the anatomical variability. Therefore, in this study two different methods have been combined; firstly, an initial segmentation of each vertebra is performed using a level‐set based segmentation method . Secondly, a probabilistic atlas of the spine has been developed, including the last cervical vertebra and the entire thoracic and lumbar regions, generating a probability map that it is deformed to be adapted to each patient.…”