Automatic instance segmentation of individual vertebrae from 3D CT is essential for various applications in orthopedics, neurology, and oncology. In case model-based segmentation (MBS) shall be used to generate a mesh-based representation of the spine, a good initialization of MBS is crucial to avoid wrong vertebra labels due to the similar appearance of adjacent vertebrae. Here, we propose to use deep learning (DL) for MBS initialization and for robustly guiding MBS during segmentation to generate 24 instance segmentations for each and every vertebra. We propose a four-step approach: In step 1, we apply a first single-class U-Net to coarsely segment the spine. In step 2, we sample image patches along the coarse segmentation of step 1 and apply a second multi-class U-net to generate a fine segmentation including individual labeling of some key vertebrae and vertebra body landmarks. In step 3, we detect and label landmark coordinates from the classes estimated in step 2. In step 4, we initialize all MBS vertebrae models using the landmarks from step 3 and adapt the model to the joint vertebrae probability map from step 2. We validated our method on segmentation results from 147 patient images. We computed surface distances between segmentation and ground truth meshes and achieved root mean squared distances of RMSDist = 0.90 mm over all cases and vertebrae.
Spinal fusion is a common procedure to stabilize the spinal column by fixating parts of the spine. In such procedures,
metal screws are inserted through the patients back into a vertebra, and the screws of adjacent vertebrae are connected by
metal rods to generate a fixed bridge. In these procedures, 3D image guidance for intervention planning and outcome
control is required. Here, for anatomical guidance, an automated approach for vertebra segmentation from C-arm CT
images of the spine is introduced and evaluated.
As a prerequisite, 3D C-arm CT images are acquired covering the vertebrae of interest. An automatic model-based
segmentation approach is applied to delineate the outline of the vertebrae of interest. The segmentation approach is based
on 24 partial models of the cervical, thoracic and lumbar vertebrae which aggregate information about (i) the basic shape
itself, (ii) trained features for image based adaptation, and (iii) potential shape variations. Since the volume data sets
generated by the C-arm system are limited to a certain region of the spine the target vertebra and hence initial model
position is assigned interactively.
The approach was trained and tested on 21 human cadaver scans. A 3-fold cross validation to ground truth annotations
yields overall mean segmentation errors of 0.5 mm for T1 to 1.1 mm for C6. The results are promising and show
potential to support the clinician in pedicle screw path and rod planning to allow accurate and reproducible insertions.
Pleural thickenings are caused by asbestos exposure and may evolve into malignant pleural mesothelioma. The detection
of pleural thickenings is today mostly done by a visual inspection of CT data, which is time-consuming and underlies the
physician's subjective judgment. We propose a new detection algorithm within our computer-assisted diagnosis (CAD)
system to automatically detect pleural thickenings within CT data. First, pleura contours are identified by thresholding
and contour relaxation with a probabilistic model. Subsequently, the approach to automatically detect pleural thickenings
is proposed as a two-step procedure. Step one; since pleural thickenings appear as fine-scale occurrences on the rather
large-scale pleura contour, a surface-based smoothing algorithm is developed. Pleural thickenings are initially detected
as the difference between the original contours and the resulting "healthy" model of the pleura. Step two; as pleural
thickenings can expand into the surrounding thoracic tissue, a subsequent tissue-specific segmentation for the initially
detected pleural thickenings is performed in order to separate pleural thickenings from the surrounding thoracic tissue.
For this purpose, a probabilistic Hounsfield model for pleural thickenings as a mixture of Gaussian distributions has been
constructed. The parameters were estimated by applying the Expectation-Maximization (EM) algorithm. A model fitting
technique in combination with the application of a Gibbs-Markov random field (GMRF) model then allows the tissuespecific
segmentation of pleural thickenings with high precision. With these methods, a new approach is presented in
order to assure a precise and reproducible detection of pleural mesothelioma in its early stage.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.