Shape Model Approach Research Articles

Statistical Shape Modeling Approach to Predict Missing Scapular Bone.

Prediction of complete and premorbid scapular anatomy is an important aspect of successful shoulder arthroplasty surgeries to treat glenohumeral arthritis and which remains elusive in the current literature. We proposed to build a statistical shape model (SSM) of the scapula and use it to build a framework to predict a complete scapular shape from virtually created scapular bone defects. The bone defects were synthetically created to imitate bone loss in the glenoid region and missing bony part in inferior and superior scapular regions. Sixty seven dry scapulae were used to build the SSM while ten external scapular shapes (not used in SSM building) were selected to map scapular shape variability using its anatomical classification. For each external scapula, four virtual bone defects were created in the superior, inferior and glenoid regions by manually removing a part of the original mesh. Using these defective shapes as prior knowledge, original shapes were reconstructed using scapula SSM and Gaussian process regression. Robustness of the scapula SSM was excellent (generality = 0.79mm, specificity = 1.74mm, first 15 principal modes of variations accounted for 95% variability). The validity and quality of the reconstruction of complete scapular bone were evaluated using two methods (1) mesh distances in terms of mean and RMS values and (2) four anatomical measures (three angles: glenoid version, glenoid inclination, and critical shoulder angle, and glenoid center location). The prediction error in the angle measures ranged from 1.0° to 2.2°. For mesh distances, highest mean and RMS error was 0.97mm and 1.30 respectively. DICE similarity coefficient between the original and predicted shapes was excellent (≥ 0.81). This framework provided high reconstruction accuracy and can be effectively embedded in the pre-surgical planning of shoulder arthroplasty or in morphology-based shoulder biomechanics modeling pipelines.

Diffusion Tensor Image segmentation based on multi-atlas Active Shape Model

Active Shape Model (ASM) has been successfully applied in the segmentation of Diffusion Tensor Magnetic Resonance Image (DT-MRI, referred to as DTI) of brain. However, due to multiple anatomical structure types, irregular shapes, small gray-scale and large amount of these images, perfect segmentation performance could not be achieved. Especially, it is sensitive to initial values with high computational complexity. In this paper, we introduce the gray information of multiple atlases and the prior information of target shapes into the ASM and propose the Multi-Atlas Active Shape Model (referred to as MA-ASM) approach for DTI segmentation. It was evaluated in a manually labeled database with 7 Region of Interest (ROI)s for each of 20 subjects. In comparison with the state of art method of STAPLE (Simultaneous Truth Performance Level Estimation), the proposed algorithm was closer to the manual segmentation shape by subjective visual effects, and had higher overlap rates and lower error detection rates on quantitative analysis than STAPLE.

Patch-based facial texture super-resolution by fitting 3D face models

Incorporating 3D models for face hallucination (FH) is an ill-posed problem in light of the low-resolution (LR) conditions. To deal with the challenges, a specific 3D shape modeling approach targeting LR face images is first proposed. Based on a few automatically detected 2D facial feature points, an adaptive fitting scheme to relax the fixed correspondence assumption on the facial contour is devised, allowing for pose-invariant shape recovery. In order to exploit the obtained 3D shape and pose for FH, a resolution-aware approach for registering the training 3D faces with the LR input is designed to avoid warping the LR face. Finally, the LR image formation process is reformulated to facilitate super-resolution (SR) of the 3D facial texture. Using this interpretation, the Lucas–Kanade algorithm is extended for 3D deformable models to rectify the imperfect landmark-based fitting on LR images in a posterior fashion. In this way, the final patch-wise SR stage is able to produce realistic facial textures and synthesize self-occluded regions for non-frontal poses. All in all, our main contribution is a novel and pragmatic “2D landmarks $$\rightarrow $$ 3D dense shape $$\rightarrow $$ LR fitting refinement $$\rightarrow $$ 3D FH” pipeline dedicated for the LR scenario. To justify its advantages, extensive evaluation is conducted on several publicly available datasets, revealing superior accuracy over state-of-the-art methods in 3D fitting and high-quality SR results for in-the-wild faces with an interocular distance of as few as five pixels. Moreover, the frontalized high-resolution texture is also verified to help boost the performance of cross-pose face recognition.

Diffeomorphic Medial Modeling.

Deformable shape modeling approaches that describe objects in terms of their medial axis geometry (e.g., m-reps [10]) yield rich geometrical features that can be useful for analyzing the shape of sheet-like biological structures, such as the myocardium. We present a novel shape analysis approach that combines the benefits of medial shape modeling and diffeomorphometry. Our algorithm is formulated as a problem of matching shapes using diffeomorphic flows under constraints that approximately preserve medial axis geometry during deformation. As the result, correspondence between the medial axes of similar shapes is maintained. The approach is evaluated in the context of modeling the shape of the left ventricular wall from 3D echocardiography images.

Morphologic variations of the scapula in 3-dimensions: a statistical shape model approach

Morphologic variations of the scapula and acromion have been found to be associated with shoulder pathology. This study used statistical shape modelling to quantify these variations in healthy shoulders. A statistical shape model of the scapula was created using 3-dimensional computed tomography reconstructions of 108 survey-confirmed nonpathologic shoulders of 54 patients. The mean shape and the 95% confidence interval were calculated and analyzed in the first 5 shape modes. The first 5 shape modes consisted of consecutively sized (72% of total variation), rotation of the coracoacromial complex (5%), acromial shape and slope (4%), shape of the scapular spine (2%), and acromial overhang (2%). In healthy shoulders, a certain variation in rotation of the coracoacromial complex and in acromial shape and slope was observed. These new parameters might be correlated with shoulder pathology such as glenohumeral osteoarthritis or rotator cuff tears.

Deformable torso phantoms of Chinese adults for personalized anatomy modelling.

In recent years, there has been increasing demand for personalized anatomy modelling for medical and industrial applications, such as ergonomics device development, clinical radiological exposure simulation, biomechanics analysis, and 3D animation character design. In this study, we constructed deformable torso phantoms that can be deformed to match the personal anatomy of Chinese male and female adults. The phantoms were created based on a training set of 79 trunk computed tomography (CT) images (41 males and 38 females) from normal Chinese subjects. Major torso organs were segmented from the CT images, and the statistical shape model (SSM) approach was used to learn the inter-subject anatomical variations. To match thepersonal anatomy, the phantoms were registered to individual body surface scans or medical images using the active shape model method. The constructed SSM demonstrated anatomical variations in body height, fat quantity, respiratory status, organ geometry, male muscle size, and female breast size. The masses of the deformed phantom organs were consistent with Chinese population organ mass ranges. To validate the performance of personal anatomy modelling, the phantoms were registered to the body surface scan and CT images. The registration accuracy measured from 22 test CT images showed a median Dice coefficient over 0.85, a median volume recovery coefficient (RCvlm ) between 0.85 and 1.1, and a median averaged surface distance (ASD)<1.5mm. We hope these phantoms can serve as computational tools for personalized anatomy modelling for the research community.

Deformable Head Atlas of Chinese Adults Incorporating Inter-Subject Anatomical Variations

To date, many digital atlases of the human head have been developed, but few incorporate the anatomical variations of the population. In this paper, for the first time, we constructed two digital head atlases (DHAs) of Chinese male and female adults, which can be deformed to simulate the inter-subject anatomical variations. The atlases were developed to assist with personalized medical treatment, population-based radio magnetic simulation, and medical imaging device design. The statistical shape model approach was used to construct the atlases based on a training set of 65 computed tomography (CT) images (including those of 46 males and 19 females). To evaluate the accuracy of anatomy modeling, we compared the atlas morphometry parameters with the reference values of the Chinese population and observed the reasonable agreement between them. Compared with the existing digital human head atlases, a unique feature of the DHA is the capability of emulating individual head anatomy via model deformation. This feature is validated by registering the DHAs to patient CT images. The registered atlases provide complete anatomy of the target subjects, including the structures that are not clearly visible in the CT images.

Multi-resolution multi-object statistical shape models based on the locality assumption.

Statistical shape models learned from a population of previously observed training shapes are nowadays widely used in medical image analysis to aid segmentation or classification. However, providing an appropriate and representative training population of preferably manual segmentations is typically either very labor-intensive or even impossible. Therefore, statistical shape models in practice frequently suffer from the high-dimension-low-sample-size (HDLSS) problem resulting in models with insufficient expressiveness. In this paper, a novel approach for learning representative multi-resolution multi-object statistical shape models from a small number of training samples that adequately model the variability of each individual object as well as their interrelations is presented. The method is based on the assumption of locality, which means that local shape variations have limited effects in distant areas and, therefore, can be modeled independently. This locality assumption is integrated into the standard statistical shape modeling framework by manipulating the sample covariance matrix (non-zero covariances between distant landmarks are set to zero). To allow for multi-object modeling, a method for computing distances between points located on different object shapes is proposed. Furthermore, different levels of locality are introduced by deriving a multi-resolution scheme, which is equipped with a method to combine variability information modeled at different levels into a single shape model. This combined representation of global and local variability in a single shape model allows the use of the classical active shape model strategy for model-based image segmentation. An extensive evaluation based on a public data base of 247 chest radiographs is performed to show the modeling and segmentation capabilities of the proposed approach in single- and multi-object HDLSS scenarios. The new approach is not only compared to the classical shape modeling method but also to three state-of-the-art shape modeling approaches specifically designed to cope with the HDLSS problem. The results show that the new approach significantly outperforms all other approaches in terms of generalization ability and model-based segmentation accuracy.

Whole Abdominal Wall Segmentation using Augmented Active Shape Models (AASM) with Multi-Atlas Label Fusion and Level Set.

The abdominal wall is an important structure differentiating subcutaneous and visceral compartments and intimately involved with maintaining abdominal structure. Segmentation of the whole abdominal wall on routinely acquired computed tomography (CT) scans remains challenging due to variations and complexities of the wall and surrounding tissues. In this study, we propose a slice-wise augmented active shape model (AASM) approach to robustly segment both the outer and inner surfaces of the abdominal wall. Multi-atlas label fusion (MALF) and level set (LS) techniques are integrated into the traditional ASM framework. The AASM approach globally optimizes the landmark updates in the presence of complicated underlying local anatomical contexts. The proposed approach was validated on 184 axial slices of 20 CT scans. The Hausdorff distance against the manual segmentation was significantly reduced using proposed approach compared to that using ASM, MALF, and LS individually. Our segmentation of the whole abdominal wall enables the subcutaneous and visceral fat measurement, with high correlation to the measurement derived from manual segmentation. This study presents the first generic algorithm that combines ASM, MALF, and LS, and demonstrates practical application for automatically capturing visceral and subcutaneous fat volumes.

Segmentation of the left ventricular endocardium from magnetic resonance images by using different statistical shape models

We evaluate in this paper different strategies for the construction of a statistical shape model (SSM) of the left ventricle (LV) to be used for segmentation in cardiac magnetic resonance (CMR) images. From a large database of LV surfaces obtained throughout the cardiac cycle from 3D echocardiographic (3DE) LV images, different LV shape models were built by varying the considered phase in the cardiac cycle and the registration procedure employed for surface alignment. Principal component analysis was computed to describe the statistical variability of the SSMs, which were then deformed by applying an active shape model (ASM) approach to segment the LV endocardium in CMR images of 45 patients. Segmentation performance was evaluated by comparing LV volumes derived by ASM segmentation with different SSMs and those obtained by manual tracing, considered as a reference. A high correlation (r2>0.92) was found in all cases, with better results when using the SSM models comprising more than one frame of the cardiac cycle.

Patient-specific assessment of dysmorphism of the femoral head-neck junction: a statistical shape model approach.

Objective quantification of anatomical variations about the femur head-neck junction in pre-operative planning for surgical intervention in femoro-acetabular impingement is problematic, as no clear definition of average normal anatomy for a specific subject exists. We have defined the normal-equivalent of a subject's anatomy by using a statistical shape model and geometric shape optimization for finding correspondences, while excluding the femoral head-neck junction during the fitting procedure. The presented technique was evaluated on a cohort of 20 patients. Difference in α-angle measurement between the actual morphology and the predicted normal-equivalent, averaged 1.3° (SD 1.7°) in the control group versus 8° (SD 7.3°) in the patient group (p < 0.05). Defining normal equivalent anatomy is effective in quantifying anatomical dysmorphism of the femoral head-neck junction and as such can improve presurgical analysis of patients diagnosed with femoro-acetabular impingement. Copyright © 2016 John Wiley & Sons, Ltd.

A visual analytics perspective on shape analysis: State of the art and future prospects

The combination of long established techniques in morphometrics with novel shape modeling approaches in geometry processing has opened new ways of visualizations of shape variability in different application areas like biology, medicine, epidemiology and agriculture. For the first time highly resolved 3D representations became accessible for statistical analysis as well as visualizations. In order to reveal causes for shape variability targeted statistical analysis correlating shape features against external and internal factors is necessary but due to the complexity of the problem often not feasible in an automated way. Therefore, visual analytics methods found their way into the field of morphometrics. This led to numerous publications in recent years that might be subsumed under the novel term visual shape analytics. In this paper we try to put these works into the context of visual analytics, outline the basic principles underlying these approaches and review the current state of the art. Finally, future challenges and possibilities in visual shape analytics are identified.

Statistical modeling to characterize relationships between knee anatomy and kinematics

The mechanics of the knee are complex and dependent on the shape of the articular surfaces and their relative alignment. Insight into how anatomy relates to kinematics can establish biomechanical norms, support the diagnosis and treatment of various pathologies (e.g., patellar maltracking) and inform implant design. Prior studies have used correlations to identify anatomical measures related to specific motions. The objective of this study was to describe relationships between knee anatomy and tibiofemoral (TF) and patellofemoral (PF) kinematics using a statistical shape and function modeling approach. A principal component (PC) analysis was performed on a 20-specimen dataset consisting of shape of the bone and cartilage for the femur, tibia and patella derived from imaging and six-degree-of-freedom TF and PF kinematics from cadaveric testing during a simulated squat. The PC modes characterized links between anatomy and kinematics; the first mode captured scaling and shape changes in the condylar radii and their influence on TF anterior-posterior translation, internal-external rotation, and the location of the femoral lowest point. Subsequent modes described relations in patella shape and alta/baja alignment impacting PF kinematics. The complex interactions described with the data-driven statistical approach provide insight into knee mechanics that is useful clinically and in implant design.

Automatic bone segmentation and bone-cartilage interface extraction for the shoulder joint from magnetic resonance images

We present a statistical shape model approach for automated segmentation of the proximal humerus and scapula with subsequent bone-cartilage interface (BCI) extraction from 3D magnetic resonance (MR) images of the shoulder region. Manual and automated bone segmentations from shoulder MR examinations from 25 healthy subjects acquired using steady-state free precession sequences were compared with the Dice similarity coefficient (DSC). The mean DSC scores between the manual and automated segmentations of the humerus and scapula bone volumes surrounding the BCI region were 0.926 ± 0.050 and 0.837 ± 0.059, respectively. The mean DSC values obtained for BCI extraction were 0.806 ± 0.133 for the humerus and 0.795 ± 0.117 for the scapula. The current model-based approach successfully provided automated bone segmentation and BCI extraction from MR images of the shoulder. In future work, this framework appears to provide a promising avenue for automated segmentation and quantitative analysis of cartilage in the glenohumeral joint.

Automatic cardiac LV segmentation in MRI using modified graph cuts with smoothness and interslice constraints

Magnetic resonance imaging (MRI), specifically late-enhanced MRI, is the standard clinical imaging protocol to assess cardiac viability. Segmentation of myocardial walls is a prerequisite for this assessment. Automatic and robust multisequence segmentation is required to support processing massive quantities of data. A generic rule-based framework to automatically segment the left ventricle myocardium is presented here. We use intensity information, and include shape and interslice smoothness constraints, providing robustness to subject- and study-specific changes. Our automatic initialization considers the geometrical and appearance properties of the left ventricle, as well as interslice information. The segmentation algorithm uses a decoupled, modified graph cut approach with control points, providing a good balance between flexibility and robustness. The method was evaluated on late-enhanced MRI images from a 20-patient in-house database, and on cine-MRI images from a 15-patient open access database, both using as reference manually delineated contours. Segmentation agreement, measured using the Dice coefficient, was 0.81±0.05 and 0.92±0.04 for late-enhanced MRI and cine-MRI, respectively. The method was also compared favorably to a three-dimensional Active Shape Model approach. The experimental validation with two magnetic resonance sequences demonstrates increased accuracy and versatility.

A statistical finite element model of the knee accounting for shape and alignment variability

By characterizing anatomical differences in size and shape between subjects, statistical shape models enable population-based evaluations in biomechanics. Statistical models have largely focused on individual bones with application to implant sizing, bone fracture and osteoarthritis; however, in joint mechanics applications, the statistical models must consider the geometry of multiple structures of a joint and their relative position. Accordingly, the objectives of this study were to develop a statistical shape and alignment modeling (SSAM) approach to characterize the intersubject variability in bone morphology and alignment for the structures of the knee, to demonstrate the statistical model's ability to describe variability in a training set and to generate realistic instances for use in finite element evaluation of joint mechanics. The statistical model included representations of the bone and cartilage for the femur, tibia and patella from magnetic resonance images and relative alignment of the structures at a known, loaded position in an experimental knee simulator for a training set of 20 specimens. The statistical model described relationships or modes of variation in shape and relative alignment of the knee structures. By generating new ‘virtual subjects’ with physiologically realistic knee anatomy, the modeling approach can efficiently perform investigations into joint mechanics and implant design which benefit from population-based considerations.

Cervical spine mobility analysis on radiographs: A fully automatic approach

Conventional X-ray radiography remains nowadays the most common method to analyze spinal mobility in two dimensions. Therefore, the objective of this paper is to develop a framework dedicated to the fully automatic cervical spine mobility analysis on X-ray images. To this aim, we propose an approach based on three main steps: fully automatic vertebra detection, vertebra segmentation and angular measurement. The accuracy of the method was assessed for a total of 245 vertebræ. For the vertebra detection, we proposed an adapted version of two descriptors, namely Scale-invariant Feature Transform (SIFT) and Speeded-up Robust Features (SURF), coupled with a multi-class Support Vector Machine (SVM) classifier. Vertebræ are successfully detected in 89.8% of cases and it is demonstrated that SURF slightly outperforms SIFT. The Active Shape Model approach was considered as a segmentation procedure. We observed that a statistical shape model specific to the vertebral level improves the results. Angular errors of cervical spine mobility are presented. We showed that these errors remain within the inter-operator variability of the reference method.

Spherical DCB-Spline Surfaces with Hierarchical and Adaptive Knot Insertion

This paper develops a novel surface fitting scheme for automatically reconstructing a genus-0 object into a continuous parametric spline surface. A key contribution for making such a fitting method both practical and accurate is our spherical generalization of the Delaunay configuration B-spline (DCB-spline), a new non-tensor-product spline. In this framework, we efficiently compute Delaunay configurations on sphere by the union of two planar Delaunay configurations. Also, we develop a hierarchical and adaptive method that progressively improves the fitting quality by new knot-insertion strategies guided by surface geometry and fitting error. Within our framework, a genus-0 model can be converted to a single spherical spline representation whose root mean square error is tightly bounded within a user-specified tolerance. The reconstructed continuous representation has many attractive properties such as global smoothness and no auxiliary knots. We conduct several experiments to demonstrate the efficacy of our new approach for reverse engineering and shape modeling.

Feature, design intention and constraint preservation for direct modeling of 3D freeform surfaces

Direct modeling has recently emerged as a suitable approach for 3D free-form shape modeling in industrial design. It has several advantages over the conventional, parametric modeling techniques, including natural user interactions, as well as the underlying, automatic feature-preserving shape deformation algorithms. However, current direct modeling packages still lack several capabilities critical for product design, such as managing aesthetic design intentions, and enforcing dimensional, geometric constraints.In this paper, we describe a novel 3D surface editing system capable of jointly accommodating aesthetic design intentions expressed in the form of surface painting and color-coded annotations, as well as engineering constraints expressed as dimensions. The proposed system is built upon differential coordinates and constrained least squares, and is intended for conceptual design that involves frequent shape tuning and explorations. We also provide an extensive review of the state-of-the-art direct modeling approaches for 3D mesh-based, freeform surfaces, with an emphasis on the two broad categories of shape deformation algorithms developed in the relevant field of geometric modeling.

Automated 3-D Segmentation of Lungs With Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach

Segmentation of lungs with (large) lung cancer regions is a nontrivial problem. We present a new fully automated approach for segmentation of lungs with such high-density pathologies. Our method consists of two main processing steps. First, a novel robust active shape model (RASM) matching method is utilized to roughly segment the outline of the lungs. The initial position of the RASM is found by means of a rib cage detection method. Second, an optimal surface finding approach is utilized to further adapt the initial segmentation result to the lung. Left and right lungs are segmented individually. An evaluation on 30 data sets with 40 abnormal (lung cancer) and 20 normal left/right lungs resulted in an average Dice coefficient of 0.975±0.006 and a mean absolute surface distance error of 0.84±0.23 mm, respectively. Experiments on the same 30 data sets showed that our methods delivered statistically significant better segmentation results, compared to two commercially available lung segmentation approaches. In addition, our RASM approach is generally applicable and suitable for large shape models.