Explore the vast range of titles available.

Statistical shape models have been widely employed in cardiac image segmentation. In practice, however, the construction of the models is faced with several challenges, in particular the need for a sufficiently large training database and a detailed delineation of the training images. Moreover, for pathologies that induce severe shape remodeling such as for pulmonary hypertension (PH), a statistical model is rarely capable of encoding the significant and complex variability of the class. This work presents a new approach for the segmentation of abnormal hearts by reusing statistical shape models built from normal population. To this end, a normalization of the pathological image data is first performed towards the space of the normal shape model, which is then used to guide the segmentation process. Subsequently, the model recovered in the space of normal anatomies is propagated back to the pathological images space. Detailed validation with PH image data shows that the method is both accurate and consistent in its segmentation of highly remodeled hearts.

PurposePropose a fully automatic 3D segmentation framework to segment liver on challenging cases that contain the low contrast of adjacent organs and the presence of pathologies from abdominal CT images.MethodsFirst, all of the atlases are weighted in the selected training datasets by calculating the similarities between the atlases and the test image to dynamically generate a subject-specific probabilistic atlas for the test image. The most likely liver region of the test image is further determined based on the generated atlas. A rough segmentation is obtained by a maximum a posteriori classification of probability map, and the final liver segmentation is produced by a shape–intensity prior level set in the most likely liver region. Our method is evaluated and demonstrated on 25 test CT datasets from our partner site, and its results are compared with two state-of-the-art liver segmentation methods. Moreover, our performance results on 10 MICCAI test datasets are submitted to the organizers for comparison with the other automatic algorithms.ResultsUsing the 25 test CT datasets, average symmetric surface distance is 1.09±0.34 mm (range 0.62–2.12 mm), root mean square symmetric surface distance error is 1.72±0.46 mm (range 0.97–3.01 mm), and maximum symmetric surface distance error is 18.04±3.51 mm (range 12.73–26.67 mm) by our method. Our method on 10 MICCAI test data sets ranks 10th in all the 47 automatic algorithms on the site as of July 2015. Quantitative results, as well as qualitative comparisons of segmentations, indicate that our method is a promising tool to improve the efficiency of both techniques.ConclusionThe applicability of the proposed method to some challenging clinical problems and the segmentation of the liver are demonstrated with good results on both quantitative and qualitative experimentations. This study suggests that the proposed framework can be good enough to replace the time-consuming and tedious slice-by-slice manual segmentation approach.

Despite the large demand for dental restoration each year, the design of crown restorations is mainly performed via manual software operation, which is tedious and subjective. Moreover, the current design process lacks biomechanics optimization, leading to localized stress concentration and reduced working life. To tackle these challenges, we develop a fully automated algorithm for crown restoration based on deformable model fitting and biomechanical optimization. From a library of dental oral scans, a conditional shape model (CSM) is constructed to represent the inter-teeth shape correlation. By matching the CSM to the patient’s oral scan, the optimal crown shape is estimated to coincide with the surrounding teeth. Next, the crown is seamlessly integrated into the finish line of preparation via a surface warping step. Finally, porous internal supporting structures of the crown are generated to avoid excessive localized stresses. This algorithm is validated on clinical oral scan data and achieved less than 2 mm mean surface distance as compared to the manual designs of experienced human operators. The mechanical simulation was conducted to prove that the internal supporting structures lead to uniform stress distribution all over the model.

PurposeThis paper aims to propose a framework for optimizing the pose in the assembly process of the non-ideal parts considering the manufacturing deviations and contact deformations. Furthermore, the accuracy of the method would be verified by comparing it with the other conventional methods for calculating the optimal assembly pose.Design/methodology/approachFirst, the surface morphology of the parts with manufacturing deviations would be modeled to obtain the skin model shapes that can characterize the specific geometric features of the part. The model can provide the basis for the subsequent contact deformation analysis. Second, the simulated non-nominal components are discretized into point cloud data, and the spatial position of the feature points is corrected. Furthermore, the evaluation index to measure the assembly quality has been established, which integrates the contact deformations and the spatial relationship of the non-nominal parts’ key feature points. Third, the improved particle swarm optimization (PSO) algorithm combined with the finite element method is applied to the process of solving the optimal pose of the assembly, and further deformation calculations are conducted based on interference detection. Finally, the feasibility of the optimal pose prediction method is verified by a case.FindingsThe proposed method has been well suited to solve the problem of the assembly process for the non-ideal parts with complex geometric deviations. It can obtain the reasonable assembly optimal pose considering the constraints of the surface morphological features and contact deformations. This paper has verified the effectiveness of the method with an example of the shaft-hole assembly.Research limitations/implicationsThe method proposed in this paper has been well suited to the problem of the assembly process for the non-ideal parts with complex geometric deviations. It can obtain the reasonable assembly optimal pose considering the constraints of the surface morphological features and contact deformations. This paper has verified the method with an example of the shaft-hole assembly.Originality/valueThe different surface morphology influenced by manufacturing deviations will lead to the various contact behaviors of the mating surfaces. The assembly problem for the components with complex geometry is usually accompanied by deformation due to the loading during the contact process, which may further affect the accuracy of the assembly. Traditional approaches often use worst-case methods such as tolerance offsets to analyze and optimize the assembly pose. In this paper, it is able to characterize the specific parts in detail by introducing the skin model shapes represented with the point cloud data. The dynamic changes in the parts' contact during the fitting process are also considered. Using the PSO method that takes into account the contact deformations improve the accuracy by 60.7% over the original method that uses geometric alignment alone. Moreover, it can optimize the range control of the contact to the maximum extent to prevent excessive deformations.

We present a fully-automatic statistical 3D shape modeling approach and apply it to a large dataset of 3D images, the Headspace dataset, thus generating the first public shape-and-texture 3D morphable model (3DMM) of the full human head. Our approach is the first to employ a template that adapts to the dataset subject before dense morphing. This is fully automatic and achieved using 2D facial landmarking, projection to 3D shape, and mesh editing. In dense template morphing, we improve on the well-known Coherent Point Drift algorithm, by incorporating iterative data-sampling and alignment. Our evaluations demonstrate that our method has better performance in correspondence accuracy and modeling ability when compared with other competing algorithms. We propose a texture map refinement scheme to build high quality texture maps and texture model. We present several applications that include the first clinical use of craniofacial 3DMMs in the assessment of different types of surgical intervention applied to a craniosynostosis patient group.

This article discusses a general framework for smoothing parameter estimation for models with regular likelihoods constructed in terms of unknown smooth functions of covariates. Gaussian random effects and parametric terms may also be present. By construction the method is numerically stable and convergent, and enables smoothing parameter uncertainty to be quantified. The latter enables us to fix a well known problem with AIC for such models, thereby improving the range of model selection tools available. The smooth functions are represented by reduced rank spline like smoothers, with associated quadratic penalties measuring function smoothness. Model estimation is by penalized likelihood maximization, where the smoothing parameters controlling the extent of penalization are estimated by Laplace approximate marginal likelihood. The methods cover, for example, generalized additive models for nonexponential family responses (e.g., beta, ordered categorical, scaled t distribution, negative binomial and Tweedie distributions), generalized additive models for location scale and shape (e.g., two stage zero inflation models, and Gaussian location-scale models), Cox proportional hazards models and multivariate additive models. The framework reduces the implementation of new model classes to the coding of some standard derivatives of the log-likelihood. Supplementary materials for this article are available online.

Most digital models of the equine distal limb that are available in the community are static and/or subject specific; hence, they have limited applications in veterinary research. In this paper, we present an articulatable model of the entire equine distal limb based on statistical shape modeling. The model describes the inter-subject variability in bone geometry while maintaining proper jointspace distances to support model articulation toward different poses. Shape variation modes are explained in terms of common biometrics in order to ease model interpretation from a veterinary point of view. The model is publicly available through a graphical user interface ( https://github.com/jvhoutte/equisim ) in order to facilitate future digitalization in veterinary research, such as computer-aided designs, three-dimensional printing of bone implants, bone fracture risk assessment through finite element methods, and data registration and segmentation problems for clinical practices.

Time series of hydrogen fluoride (HF) total columns have been derived from ground‐based Fourier transform infrared (FTIR) solar spectra recorded between March 1984 and December 2009 at the International Scientific Station of the Jungfraujoch (Swiss Alps, 46.5°N, 8.0°E, 3580 m asl) with two high‐resolution spectrometers (one homemade and one Bruker 120‐HR). Solar spectra have been inverted with the PROFFIT 9.5 algorithm, using the optimal estimation method. An intercomparison of HF total columns retrieved with PROFFIT and SFIT‐2–the other reference algorithm in the FTIR community–is performed for the first time. The effect of a Galatry line shape model on HF retrieved total columns and vertical profiles, on the residuals of the fits and on the error budget is also quantified. Information content analysis indicates that in addition to HF total vertical abundance, three independent stratospheric HF partial columns can be derived from our Bruker spectra. A complete error budget has been established and indicates that the main source of systematic error is linked to HF spectroscopy and that the random error affecting our HF total columns does not exceed 2.5%. Ground‐based middle and upper stratospheric HF amounts have been compared to satellite data collected by the HALOE or ACE‐FTS instruments. Comparisons of our FTIR HF total and partial columns with runs performed by two three‐dimensional numerical models (SLIMCAT and KASIMA) are also included. Finally, FTIR and model HF total and partial columns time series have been analyzed to derive the main characteristics of their seasonal cycles.

Active shape model (ASM) is an image searching method based on statistical model, which is widely used to extract features. The classical ASM model includes the shape model and the local profile model. The main merit of ASM model is using statistics to contribute model of specific target image, by introducing prior knowledge on awaiting extraction target object, limiting the searching result in the variable range. These characteristics make it suitable for any similar object's feature. Experimental results show that the algorithm can extract facial features rapidly and have higher accuracy. Index Terms-Active Shape Model; Locate Object's Feature; Shape Model; Local Profile Model; Prior Knowledge

PurposeFacet joint injections of analgesic agents are widely used to treat patients with lower back pain. The current standard-of-care for guiding the injection is fluoroscopy, which exposes the patient and physician to significant radiation. As an alternative, several ultrasound guidance systems have been proposed, but have not become the standard-of-care, mainly because of the difficulty in image interpretation by the anesthesiologist unfamiliar with the complex spinal sonography.MethodsWe introduce an ultrasound-based navigation system that allows for live 2D ultrasound images augmented with a patient-specific statistical model of the spine and relating this information to the position of the tracked injection needle. The model registration accuracy is assessed on ultrasound data obtained from nine subjects who had prior CT images as the gold standard for the statistical model. The clinical validity of our method is evaluated on four subjects (of an ongoing in vivo study) which underwent facet joint injections.ResultsThe statistical model could be registered to the bone structures in the ultrasound volume with an average RMS accuracy of 2.3±0.4 mm. The shape of the individual vertebrae could be estimated from the US volume with an average RMS surface distance error of 1.5±0.4 mm. The facet joints could be identified by the statistical model with an average accuracy of 5.1±1.5 mm.ConclusionsThe results of this initial feasibility assessment suggest that this ultrasound-based system is capable of providing information sufficient to guide facet joint injections. Further clinical studies are warranted.