The temporal bone is a part of the lateral skull surface that contains organs responsible for hearing and balance. Mastering surgery of the temporal bone is challenging because of this complex and microscopic three-dimensional (3D) anatomy. Virtual reality (VR) surgical simulators have proven to be effective for surgical training. In this paper a fully automated method is proposed for segmenting multiple temporal-bone structures based on micro computed tomography (micro-CT) images for a realistic virtual environment. An automated segmentation pipeline is proposed based on a three-dimensional, fully convolutional neural network. The proposed balanced subsampling strategy creates balanced learning among the labels of multiple anatomical structures and reduces the class imbalance. The accuracy and speed of the proposed algorithm outperforms current manual and semi-automated segmentation techniques. The average Dice similarity scores for all temporal-bone structures was 88%. The proposed algorithm was validated on low-resolution CTs scanned by other centers with different scanner parameters than the ones used to create the algorithm. The presented fully automated segmentation algorithm creates 3D models of multiple structures of temporal-bone anatomy from micro- CT images with sufficient accuracy to be used in VR surgical training simulators.
Cochlear implant surgery is a hearing restoration procedure for patients with profound hearing loss. In this surgery, an
electrode is inserted into the cochlea to stimulate the auditory nerve and restore the patient’s hearing. Clinical computed
tomography (CT) images are used for planning and evaluation of electrode placement, but their low resolution limits the
visualization of internal cochlear structures. Therefore, high resolution micro-CT images are used to develop atlas-based
segmentation methods to extract these nonvisible anatomical features in clinical CT images. Accurate registration of the
high and low resolution CT images is a prerequisite for reliable atlas-based segmentation. In this study, we evaluate and
compare different non-rigid B-spline registration parameters using micro-CT and clinical CT images of five cadaveric
human cochleae. The varying registration parameters are cost function (normalized correlation (NC), mutual information
and mean square error), interpolation method (linear, windowed-sinc and B-spline) and sampling percentage (1%, 10%
and 100%). We compare the registration results visually and quantitatively using the Dice similarity coefficient (DSC),
Hausdorff distance (HD) and absolute percentage error in cochlear volume. Using MI or MSE cost functions and linear or
windowed-sinc interpolation resulted in visually undesirable deformation of internal cochlear structures. Quantitatively,
the transforms using 100% sampling percentage yielded the highest DSC and smallest HD (0.828±0.021 and 0.25±0.09mm
respectively). Therefore, B-spline registration with cost function: NC, interpolation: B-spline and sampling percentage:
moments 100% can be the foundation of developing an optimized atlas-based segmentation algorithm of intracochlear
structures in clinical CT images.
Ultrasound (US) guided prostate brachytherapy is a minimally invasive form of cancer treatment during which a needle is used to insert radioactive seeds into the prostate at pre-planned positions. Interaction with the needle can cause the prostate to deform and this can lead to inaccuracy in seed placement. Virtual reality (VR) simulation could provide a way for surgical residents to practice compensating for these deformations. To facilitate such a tool, we have developed a hybrid deformable model that combines ChainMail distance constraints with mass-spring physics to provide realistic, yet customizable deformations. Displacements generated by the model were used to warp a baseline US image to simulate an acquired US sequence. The algorithm was evaluated using a gelatin phantom with a Young's modulus approximately equal to that of the prostate (60 kPa). A 2D US movie was acquired while the phantom underwent needle insertion and inter-frame displacements were calculated using normalized cross correlation. The hybrid model was used to simulate the same needle insertion and the two sets of displacements were compared on a frame-by-frame basis. The average perpixel displacement error was 0.210 mm. A simulation rate of 100 frames per second was achieved using a 1000 element triangular mesh while warping a 300x400 pixel US image on an AMD Athlon 1.1 Ghz computer with 1 GB of RAM and an ATI Radeon 9800 Pro graphics card. These results show that this new deformable model can provide an accurate solution to the problem of simulating real-time prostate brachytherapy.
We evaluated three algorithms for prostate boundary segmentation from 3D ultrasound images. In the parallel segmentation method, the 3D image was sliced into parallel, contiguous 2D images, whereas in the rotational method, the image was sliced in a rotational manner. Using either method, four points were selected on a central slice and used to initiate a 2D deformable model. The segmented contour was propagated to adjacent slices until the entire prostate was segmented. In the volume-based method, the 3D image was segmented directly without slicing it. Each segmentation algorithm was applied to four 3D images, and the results were compared to manual segmentation. Average volume errors of -8.58%, -1.95% and -5.01% were estimated for the parallel, rotational and volume-based methods, respectively. Approximately 20% of the slices required editing in the parallel method, whereas 13% required editing in the rotational method. Although only one surface segmented using the volume-based method needed editing, manual editing was difficult in 3D. Segmentation times, including editing, ranged from 42 to 82 seconds for the parallel method, from 27 to 52 seconds for the rotational method, and up to 55 seconds for the volume-based method. Based on these results, we recommend the rotational segmentation method.
A semi-automatic method for segmenting carotid lumen and plaque from three-dimensional vascular ultrasound (US) images has been developed. We examine its ability to distinguish changes in carotid vessel and plaque surface morphology, such as those caused by plaque ulceration. Two stenosed vessel phantoms were imaged using a 3D US imaging system. The phantoms were identical except for the inclusion of a hemispherical cut in the side of one of the vessels, in order to simulate the development of an ulceration. Ultrasound images of the phantoms were segmented using our algorithm, then the resulting surfaces were registered to one another using a rigid-body iterative closest point (ICP) algorithm. The volume of ulceration was determined by finding the difference between the two segmented surfaces in a region of interest surrounding the ulceration. Since the true volume of the ulceration was known a priori, an optimization strategy was used to tune the deformable model to better segment the ulceration. Analysis of ulceration volume as a function of the deformable model's parameters show that 1) large ulcerations are easily identified in our test case, and 2) the model is well behaved with respect to its parameters, suggesting that an automatic strategy for volumetric optimization is feasible.
KEYWORDS: Image segmentation, 3D image processing, 3D modeling, Arteries, Ultrasonography, 3D acquisition, 3D metrology, Image processing, Image acquisition, Imaging systems
In this paper, we report on a semi-automatic approach to segmentation of carotid arteries from 3D ultrasound (US) images. Our method uses a deformable model which first is rapidly inflated to approximately find the boundary of the artery, then is further deformed using image-based forces to better localize the boundary. An operator is required to initialize the model by selecting a position in the 3D US image, which is within the carotid vessel. Since the choice of position is user-defined, and therefore arbitrary, there is an inherent variability in the position and shape of the final segmented boundary. We have assessed the performance of our segmentation method by examining the local variability in boundary shape as the initial selected position is varied in a freehand 3D US image of a human carotid bifurcation. Our results indicate that high variability in boundary position occurs in regions where either the segmented boundary is highly curved, or the 3D US image has poorly defined vessel edges.
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.