Liver Segmentation Using a Statistical Shape Model Based on Learning Local Objective Functions

In this paper, we present an indexing structure of data-driven cuboid patterns to speed up the process of liver detection and segmentation from computed tomography (CT) scans using the cube-based generalized Hough transform (CGHT). Most existing approaches to automatic liver segmentation from CT scans use a statistical shape model (SSM) integrated with a searching algorithm to recover the deformation. However, establishing the correspondences among landmark points of training shapes for the construction of the average shape of SSM remains as a challenge due to the high variation of liver shapes in CT scans. The proposed method is a fully automatic segmentation method that combines four steps. Firstly, a test CT volume is partitioned into multiple non-overlapped sub-volumes with each of them consisting of variable numbers of consecutive slices. Secondly, we locate the cube-based liver shapes in all sub-volumes via Hough voting and dynamic programming. Thirdly, we construct the basic 3D model through a level-set framework for liver shape segmentation. Finally, to introduce neighbors statistical analysis into the above model, we deform the 3D liver shape to overcome disturbances caused by noise and inhomogeneity. The MICCAI 2007 liver segmentation challenge datasets are used to verify the effectiveness of the proposed method. Experimental results demonstrate the good performance of the proposed method in terms of segmentation accuracy and execution speed.

Poster 139: Utilization of 3D Statistical Shape Modeling of Anatomic Variation Across a Cohort of Patella Instability Patients

Patient-specific biomechanical simulations of joints require accurate reconstruction of bony anatomy from medical image data. The articular geometries of the joints may influence their biomechanics. Statistical shape models (SSMs) have become ubiquitous in the literature and aim to capture the natural variation of biological objects. They work by learning the variation from training examples to define the space of valid biological shapes. However, the kinematic information descriptive of the anato-physiological relationship of two interacting objects is not generally encoded in the SSM. Here, we propose a framework for developing combined statistical shape and kinematics models (SSKMs) as Gaussian process morphable models to analyse the shape and kinematics relationship. We demonstrate the framework on a three-dimensional (3D) image data set consisting of ten right-handed cadaveric shoulder joints acquired using computed tomography. Additionally, we simulate specific bone motions to encode kinematics in the combined model. Our SSKM built from shoulder data (matching scapulae and humeri) correctly depicts a correlation between the shape and kinematics as hypothesized. We furthermore demonstrate the ability to marginalize from the SSKM to obtain shape-only variation and kinematics-only variation. Future work aims to use the SSKM framework to understand the relationships between kinematics and shape for various joints as well as to develop patient-specific computational models to evaluate joint biomechanics.

The segmentation of organs in CT volumes is a prerequisite for diagnosis and treatment planning. In this paper, we focus on liver segmentation from contrast-enhanced abdominal CT volumes, a challenging task due to intensity overlapping, blurred edges, large variability in liver shape, and complex background with cluttered features. The algorithm integrates multidiscriminative cues (i.e., prior domain information, intensity model, and regional characteristics of liver in a graph-cut image segmentation framework). The paper proposes a swarm intelligence inspired edge-adaptive weight function for regulating the energy minimization of the traditional graph-cut model. The model is validated both qualitatively (by clinicians and radiologists) and quantitatively on publically available computed tomography (CT) datasets (MICCAI 2007 liver segmentation challenge, 3D-IRCAD). Quantitative evaluation of segmentation results is performed using liver volume calculations and a mean score of 80.8% and 82.5% on MICCAI and IRCAD dataset, respectively, is obtained. The experimental result illustrates the efficiency and effectiveness of the proposed method.

IntroductionVideo urodynamic studies (VUDS) use fluoroscopic imaging to visualize the bladder and multichannel urodynamics to assess its function. Qualitative assessment of bladder shape is used to identify abnormal features (e.g., diverticula) that correspond with pathophysiology; however, this assessment is limited in its ability to predict bladder function. Therefore, we developed a novel quantitative approach to assess bladder shape obtained from fluoroscopic VUDS images utilizing statistical shape modeling. This method was compared to existing binary and continuous shape quantification methods and used to identify relationships between bladder shape and measures of bladder physiology categorized as related to sensation, incontinence, or emptying.MethodsThis was a retrospective, cross-sectional study of 49 participants. Bladder walls were segmented from fluoroscopic images at rest with the bladder filled to approximately 300 mL. Bladder shape was evaluated in three ways: 1) binary categorization as typical or atypical based on clinical assessment, 2) quantification of height-to-width ratios, and 3) quantification by statistical shape modeling. Independent t-tests and correlations were used to assess associations between the three shape evaluation methods and to define relationships between shape and physiologic measures: 3 volumetric measures describing sensation, 2 dichotomous variables addressing incontinence, and 1 volumetric measure representing emptying.ResultsThe statistical shape model generated 5 modes of variation. Mode 1 corresponded with height-to-width ratio (r=0.920, p<0.001), modes 2 and 3 with diagonal height-to-width ratio (r=0.66 and -0.585, p<0.001 and <0.001), and mode 3 with binary shape categorization (p<0.001). In terms of function, those with atypical bladder shape had impaired emptying (p=0.010), modes 4 and 5 were significantly associated with measures of bladder sensation, mode 3 with urodynamic stress urinary incontinence, and mode 3 with emptying in those able to void (r=0.368, p=0.021). The relationship between mode 3 and emptying across all patients is best fitted by a quadratic function (p<0.001).DiscussionOur results demonstrate that binary shape categorization and bladder shape quantified by statistical shape modeling correspond with measures of bladder physiology. This foundational study establishes statistical shape modeling as a robust bladder shape quantification method that can be used to relate bladder shape with physiology.

Clinical relevance of augmented statistical shape model of the scapula in the glenoid region

This paper describes a new method of non-rigid registration using the combined power of elastic and statistical shape models. The transformations are constrained to be consistent with a physical model of elasticity to maintain smoothness and continuity. A Bayesian formulation, based on this model, on an intensity similarity measure, and on statistical shape information embedded in corresponding boundary points, is employed to find a more accurate and robust non-rigid registration. A dense set of forces arises from the intensity similarity measure to accommodate complex anatomical details. A sparse set of forces constrains consistency with statistical shape models derived from a training set. A number of experiments were performed on both synthetic and real medical images of the brain and heart to evaluate the approach. It is shown that statistical boundary shape information significantly augments and improves elastic model based non-rigid registration.KeywordsControl PointBoundary PointElastic ModelSynthetic ImageShape InformationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

To develop a patient-specific 3 D reconstruction of a femur modeled using the statistical shape model (SSM) and X-ray images, it is assumed that the target shape is not outside the range of variations allowed by the SSM built from a training dataset. We propose the shape-partitioned statistical shape model (SPSSM) to cover significant variations in the target shape. This model can divide a shape into several segments of anatomical interest. We break up the eigenvector matrix into the corresponding representative matrices for the SPSSM by preserving the relevant rows of the original matrix without segmenting the shape and building an independent SSM for each segment. To quantify the reconstruction error of the proposed method, we generated two groups of deformation models of the femur which cannot be easily represented by the conventional SSM. One group of femurs had an anteversion angle deformation, and the other group of femurs had two different scales of the femoral head. Each experiment was performed using the leave-one-out method for twelve femurs. When the femoral head was rotated by 30°, the average reconstruction error of the conventional SSM was 5.34 mm, which was reduced to 3.82 mm for the proposed SPSSM. When the femoral head size was decreased by 20%, the average reconstruction error of the SSM was 4.70 mm, which was reduced to 3.56 mm for the SPSSM. When the femoral head size was increased by 20%, the average reconstruction error of the SSM was 4.28 mm, which was reduced to 3.10 mm for the SPSSM. The experimental results for the two groups of deformation models showed that the proposed SPSSM outperformed the conventional SSM.

Statistical shape modeling (SSM) is an essential tool for analyzing variations in anatomical morphology. In a typical SSM pipeline, 3D anatomical images, gone through segmentation and rigid registration, are represented using lower-dimensional shape features, on which statistical analysis can be performed. Various methods for constructing compact shape representations have been proposed, but they involve laborious and costly steps. We propose Image2SSM, a novel deep-learning-based approach for SSM that leverages image-segmentation pairs to learn a radial-basis-function (RBF)-based representation of shapes directly from images. This RBF-based shape representation offers a rich self-supervised signal for the network to estimate a continuous, yet compact representation of the underlying surface that can adapt to complex geometries in a data-driven manner. Image2SSM can characterize populations of biological structures of interest by constructing statistical landmark-based shape models of ensembles of anatomical shapes while requiring minimal parameter tuning and no user assistance. Once trained, Image2SSM can be used to infer low-dimensional shape representations from new unsegmented images, paving the way toward scalable approaches for SSM, especially when dealing with large cohorts. Experiments on synthetic and real datasets show the efficacy of the proposed method compared to the state-of-art correspondence-based method for SSM.

Posture normalisation of 3D body scans

Accurate Humeral Version Angle Prediction From Limited Anatomical Data Using Statistical Shape Models.

In this article, we propose a unified statistical framework for image segmentation with shape prior information. The approach combines an explicitely parameterized point-based probabilistic statistical shape model (SSM) with a segmentation contour which is implicitly represented by the zero level set of a higher dimensional surface. These two aspects are unified in a Maximum a Posteriori (MAP) estimation where the level set is evolved to converge towards the boundary of the organ to be segmented based on the image information while taking into account the prior given by the SSM information. The optimization of the energy functional obtained by the MAP formulation leads to an alternate update of the level set and an update of the fitting of the SSM. We then adapt the probabilistic SSM for multi-shape modeling and extend the approach to multiple-structure segmentation by introducing a level set function for each structure. During segmentation, the evolution of the different level set functions is coupled by the multi-shape SSM. First experimental evaluations indicate that our method is well suited for the segmentation of topologically complex, non spheric and multiple-structure shapes. We demonstrate the effectiveness of the method by experiments on kidney segmentation as well as on hip joint segmentation in CT images.

BackgroundComplex bilateral midface fractures necessitate a surgically challenging procedure to preserve or restore the occlusion and the sensitive eye area. In this case control study, we aim to show the potential of a statistical shape model (SSM) for measuring the quality of the midface reconstruction, compared to the estimated preoperative situation.MethodsAn individualized SSM was postoperatively registered on 19 reconstructed complex bilateral midface fractures. Using this SSM, the distances from the simulated preoperative situation to the postoperative positions of the fracture segments were calculated. The fracture lines for Le Fort II, Le Fort III, and NOE fractures were chosen as reference points for the distance measurements.ResultsThe SSM could be registered on all 19 complex bilateral midface fractures. All analyzed fractures showed a dorsal impaction (negative values) of the midface. Le Fort II fractures showed deviation values of –0.98 ± 4.6 mm, Le Fort III fractures showed values of –3.68 ± 3.6 mm, NOE type 2 fractures showed values of –0.25 ± 4.6 mm, and NOE type 1 fractures showed values of –0.25 ± 4.6 mm.ConclusionsThe SSM can be used to measure the quality of the achieved reduction of complex bilateral midface fractures based on the estimated preoperative situation.Trial registrationDRKS00009719.

Active Shape Models (ASM) have been widely used in the literature for the extraction of the tibial and the femoral bones from MRI. These methods use Statistical Shape Models (SSM) to drive the deformation and make the segmentation more robust. One crucial step for building such SSM is the shape correspondence (SC). Several methods have been described in the literature. The goal of this paper is to compare two SC methods, the Iterative Median Closest Point-Gaussian Mixture Model (IMCP- GMM) and the Minimum Description Length (MDL) approaches for the creation of a SSM, and to assess the impact of these SC methods on the accuracy of the femur segmentation in MRI. 28 MRI of the knee have been used. The validation has been performed by using the leave-one-out cross-validation technique. An ASMMDL and an ASMIMCP-GMMM has been built with the SSMs computed respectively with the MDL and IMCP-GMM methods. The computation time for building both SSMs has been also measured. For 90% of data, the error is inferior to 1.78 mm and 1.85 mm for respectively the ASMIMCP-GMM and the ASMMDL methods. The computation time for building the SSMs is five hours and two days for respectively the IMCP-GMM and the MDL methods. Both methods seems to give, at least, similar results for the femur segmentation in MRI. However (1) IMCP-GMM can be used for all types of shape, this is not the case for the MDL method which only works for closed shape, and (2) IMCP- GMM is much faster than MDL.

Statistical Shape Modeling (SSM) is a valuable tool for investigating and quantifying anatomical variations within populations of anatomies. However, traditional correspondence-based SSM generation methods have a prohibitive inference process and require complete geometric proxies (e.g., high-resolution binary volumes or surface meshes) as input shapes to construct the SSM. Unordered 3D point cloud representations of shapes are more easily acquired from various medical imaging practices (e.g., thresholded images and surface scanning). Point cloud deep networks have recently achieved remarkable success in learning permutation-invariant features for different point cloud tasks (e.g., completion, semantic segmentation, classification). However, their application to learning SSM from point clouds is to-date unexplored. In this work, we demonstrate that existing point cloud encoder-decoder-based completion networks can provide an untapped potential for SSM, capturing population-level statistical representations of shapes while reducing the inference burden and relaxing the input requirement. We discuss the limitations of these techniques to the SSM application and suggest future improvements. Our work paves the way for further exploration of point cloud deep learning for SSM, a promising avenue for advancing shape analysis literature and broadening SSM to diverse use cases.