Oriented Active Shape Models

Active Shape Models (ASM) have been applied to various segmentation tasks in medical imaging, most successfully in 2D segmentation of objects that have a fairly consistent shape. However, several difficulties arise when extending 2D ASM to 3D: (1) difficulty in 3D labeling, (2) the requirement of a large number of training samples, (3) the challenging problem of landmark correspondence in 3D, (4) inefficient initialization and optimization in 3D. This paper addresses the 3D segmentation problem by using a small number of effective 2D statistical models called oriented ASM (OASM). We demonstrate that a small number of 2D OASM models, which are derived from a chunk of a contiguous set of slices, are sufficient to capture the shape variation between slices and individual objects. Each model can be matched rapidly to a new slice by using the OASM algorithm¹. Our experiments in segmenting breast and bone of the foot in MR images indicate the following: (1) The accuracy of segmentation via our method is much better than that of 2DASM-based segmentation methods.² (2) Far fewer landmarks are required compared with thousands of landmarks needed in true 3D ASM. Therefore, far fewer training samples are required to capture details. (3) Our method is computationally slightly more expensive than the 2D method2 owing to its 2 level dynamic programming (2LDP) algorithm.

Efficacy of long-term treatment with lurasidone in children and adolescents with bipolar depression: Interim analysis of a 2-year open-label study

Lung field segmentation is a prerequisite for the development of automated computer aided diagnosis of interstitial lung diseases from chest high resolution computed tomography (HRCT) images. The traditional threshold-based or region growing methods tends to fail when dense pathology is present in the lung field. In such cases, it is found that prior shape knowledge increases the efficiency and accuracy of segmentation. The main contribution of this paper is the automated segmentation of lung field from HRCT images. The method is based on active shape model and it is able to segment the lung fields from HRCT images with various pathological regions like honeycomb, cavity, ground glass opacity (GGO), consolidation etc. Multiple atlases of the the lung fields are created using training data of size 100 for both left and right lungs. These atlases are used for the training of active shape model for estimation of lung shape fields. In this paper, after training, the seed selection part is automated in the matching step to ensure minimal human intervention. The result of segmentation is evaluated in terms of the Jaccard index, Dice Similarity Coefficient (DSC) and Modified Hausdorff Distance (MHD) for 80 HRCT slices from a publicly available database. The experimental results proves that the proposed method is reliable for segmentation of pathological lung fields in HRCT images with improved accuracy.

The use of appearance and shape priors in image segmentation is known to improve accuracy; however, existing techniques have several drawbacks. For instance, most active shape and appearance models require landmark points and assume unimodal shape and appearance distributions, and the level set representation does not support construction of local priors. In this paper, we present novel appearance and shape models for image segmentation based on a differentiable implicit parametric shape representation called a disjunctive normal shape model (DNSM). The DNSM is formed by the disjunction of polytopes, which themselves are formed by the conjunctions of half-spaces. The DNSM's parametric nature allows the use of powerful local prior statistics, and its implicit nature removes the need to use landmarks and easily handles topological changes. In a Bayesian inference framework, we model arbitrary shape and appearance distributions using nonparametric density estimations, at any local scale. The proposed local shape prior results in accurate segmentation even when very few training shapes are available, because the method generates a rich set of shape variations by locally combining training samples. We demonstrate the performance of the framework by applying it to both 2-D and 3-D data sets with emphasis on biomedical image segmentation applications.

Obtaining the segmentation of an object in a sequence of images is usually achieved using a tracking methodology. However, in some applications, the whole sequence is available beforehand. This means that the segmentations can be determined simultaneously for all the frames in the sequence and taking into account the motion of the object. This paper proposes a new framework to incorporate motion information in the segmentation of image sequences using an active shape model (ASM). The motion of the object is modeled using a vector field, which is learned and refined online as the segmentation algorithm proceeds. The vector field is determined from the trajectories described by ASM points throughout the sequence. The vector field, in turn, influences the estimation of the ASM parameters by acting as a regularizer, ensuring that the segmentations are in agreement with the expected motion. The results show that coupling these models during the segmentation leads to an increase in performance, in particular by guarantee more consistent segmentations and by avoid gross errors in more challenging frames.

To automatically segment the skull from the MRI data using a model-based three-dimensional segmentation scheme. This study exploited the statistical anatomy extracted from the CT data of a group of subjects by means of constructing an active shape model of the skull surfaces. To construct a reliable shape model, a novel approach was proposed to optimize the automatic landmarking on the coupled surfaces (i.e., the skull vault) by minimizing the description length that incorporated local thickness information. This model was then used to locate the skull shape in MRI of a different group of patients. Compared with performing landmarking separately on the coupled surfaces, the proposed landmarking method constructed models that had better generalization ability and specificity. The segmentation accuracies were measured by the Dice coefficient and the set difference, and compared with the method based on mathematical morphology operations. The proposed approach using the active shape model based on the statistical skull anatomy presented in the head CT data contributes to more reliable segmentation of the skull from MRI data.

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.

Feature competition and partial sparse shape modeling for cardiac image sequences segmentation

Automatic 3D liver segmentation is a fundamental step in the liver disease diagnosis and surgery planning. This paper presents a novel fully automatic algorithm for 3D liver segmentation in clinical 3D computed tomography (CT) images. Based on image features, we propose a new Mahalanobis distance cost function using an active shape model (ASM). We call our method MD-ASM. Unlike the standard active shape model (ST-ASM), the proposed method introduces a new feature-constrained Mahalanobis distance cost function to measure the distance between the generated shape during the iterative step and the mean shape model. The proposed Mahalanobis distance function is learned from a public database of liver segmentation challenge (MICCAI-SLiver07). As a refinement step, we propose the use of a 3D graph-cut segmentation. Foreground and background labels are automatically selected using texture features of the learned Mahalanobis distance. Quantitatively, the proposed method is evaluated using two clinical 3D CT scan databases (MICCAI-SLiver07 and MIDAS). The evaluation of the MICCAI-SLiver07 database is obtained by the challenge organizers using five different metric scores. The experimental results demonstrate the availability of the proposed method by achieving an accurate liver segmentation compared to the state-of-the-art methods.

Accurate bone segmentation is necessary to develop chair-side manufacturing of implants based on additive manufacturing. Various automatic segmentation techniques have been proposed to streamline the process (e.g. graph-cut or deep-learning), but these techniques do not provide anatomical correspondences during the segmentation process, which makes exploitation of segmentation more difficult to predict missing bone parts in case of fracture or its premorbid shape for degenerative diseases. Bone segmentation using active shape model (ASM) would provide anatomical correspondences. However, this technique is error prone for thin structures, such as the scapular blade or orbital walls. Therefore, we developed a new method relying on shape model fitting and local correction relying on image similarities. The method was evaluated on three challenging anatomical locations: (i) healthy and osteoarthritic scapulae, (ii) orbital bones, and (iii) mandible. On average, results were accurate with surface distance of about 0.5 mm and average Dice coefficients above 90%. This approach was able to separate joint bone surfaces, even in challenging pathological situations such as osteoarthritis. Since anatomical correspondences are propagated during segmentation, the method can directly provide anatomical measurements, define personalized cutting guides, or determine the bone regions to be used to contour patient-specific implants.

We make some simple extensions to the Active Shape Model of Cootes et al. [4], and use it to locate features in frontal views of upright faces. We show on independent test data that with the extensions the Active Shape Model compares favorably with more sophisticated methods. The extensions are (i) fitting more landmarks than are actually needed (ii) selectively using two- instead of one-dimensional landmark templates (iii) adding noise to the training set (iv) relaxing the shape model where advantageous (v) trimming covariance matrices by setting most entries to zero, and (vi) stacking two Active Shape Models in series.

Manual quantitative analysis of cardiac left ventricular function using Multislice CT and MR is arduous because of the large data volume. In this paper, we present a 3-D active shape model (ASM) for semiautomatic segmentation of cardiac CT and MR volumes, without the requirement of retraining the underlying statistical shape model. A fuzzy c-means based fuzzy inference system was incorporated into the model. Thus, relative gray-level differences instead of absolute gray values were used for classification of 3-D regions of interest (ROIs), removing the necessity of training different models for different modalities/acquisition protocols. The 3-D ASM was evaluated using 25 CT and 15 MR datasets. Automatically generated contours were compared to expert contours in 100 locations. For CT, 82.4% of epicardial contours and 74.1% of endocardial contours had a maximum error of 5 mm along 95% of the contour arc length. For MR, those numbers were 93.2% (epicardium) and 91.4% (endocardium). Volume regression analysis revealed good linear correlations between manual and semiautomatic volumes, r(2) >/= 0.98. This study shows that the fuzzy inference 3-D ASM is a robust promising instrument for semiautomatic cardiac left ventricle segmentation. Without retraining its statistical shape component, it is applicable to routinely acquired CT and MR studies.

In recent decades, more types and quantities of medical data have been collected due to advanced technology. A large number of significant and critical information is contained in these medical data. High efficient and automated computational methods are urgently needed to process and analyze all available medical data in order to provide the physicians with recommendations and predictions on diagnostic decisions and treatment planning. Traumatic pelvic injury is a severe yet common injury in the United States, often caused by motor vehicle accidents or fall. Information contained in the pelvic Computed Tomography (CT) images is very important for assessing the severity and prognosis of traumatic pelvic injuries. Each pelvic CT scan includes a large number of slices. Meanwhile, each slice contains a large quantity of data that may not be thoroughly and accurately analyzed via simple visual inspection with the desired accuracy and speed. Hence, a computer-assisted pelvic trauma decision-making system is needed to assist physicians in making accurate diagnostic decisions and determining treatment planning in a short period of time. Pelvic bone segmentation is a vital step in analyzing pelvic CT images and assisting physicians with diagnostic decisions in traumatic pelvic injuries. In this study, a new hierarchical segmentation algorithm is proposed to automatically extract multiple-level bone structures using a combination of anatomical knowledge and computational techniques. First, morphological operations, image enhancement, and edge detection are performed for preliminary bone segmentation. The proposed algorithm then uses a template-based best shape matching method that provides an entirely automated segmentation process. This is followed by the proposed Registered Active Shape Model (RASM) algorithm that extracts pelvic bone tissues using more robust training models than the Standard ASM algorithm. In addition, a novel hierarchical initialization process for RASM is proposed in order to address the shortcoming of the Standard ASM, i.e. high sensitivity to initialization. Two suitable measures are defined to evaluate the segmentation results: Mean Distance and Mis-segmented Area to quantify the segmentation accuracy. Successful segmentation results indicate effectiveness and robustness of the proposed algorithm. Comparison of segmentation performance is also conducted using both the proposed method and the Snake method. A cross-validation process is designed to demonstrate the effectiveness of the training models. 3D pelvic bone models are built after pelvic bone structures are segmented from consecutive 2D CT slices. Automatic and accurate detection of the fractures from segmented bones in traumatic pelvic injuries can help physicians detect the severity of injuries in patients. The extraction of fracture features (such as presence and location of fractures) as well as fracture displacement measurement, are vital for assisting physicians in making faster and more accurate decisions. In this project, after bone segmentation, fracture detection is performed using a hierarchical algorithm based on wavelet transformation, adaptive windowing, boundary tracing and masking. Also, a quantitative measure of fracture severity based on pelvic CT scans is defined and explored. The results are promising, demonstrating that the proposed method not only capable of automatically detecting both major and minor fractures, but also has potentials to be used for clinical applications.

We have been developing user-steered image segmentation methods for situations which require considerable user assistance in object definition. In such situations, our segmentation methods aim (1) to provide effective control to the user on the segmentation process while it is being executed and (2) to minimize the total user's time required in the process. In the past, we have presented two paradigms, referred to as live wire and live lane, for segmenting 3D/4D object boundaries in a slice-by-slice fashion. In this paper, we introduce a 3D extension of the live wire approach which can further reduce the time spent by the user in the segmentation process. In 2D live wire, given a slice, for two specified points (pixel vertices) on the boundary of the object, the best boundary segment (as a set of oriented pixel edges) is the minimum-cost path between the two points. This segment is found via dynamic programming in real time as the user anchors the first point and moves the cursor to indicate the second point. A complete 2D boundary in this slice is identified as a set of consecutive boundary segments forming a 'closed,' 'connected,' 'oriented' contour. The strategy of the 3D extension is that, first, users specify contours via live- wiring on a few orthogonal slices. If these slices are selected strategically, then we have a sufficient number of points on the 3D boundary of the object to do live-wiring automatically on all axial slices of the 3D scene. Based on several validation studies involving segmentation of the bones of the foot in MR images, we found that the 3D extension of live wire is statistically significantly (p less than 0.0001) more repeatable and 2 - 6 times faster (p less than 0.01) than the 2D live wire method and 3 - 15 times faster than manual tracing.

Femur segmentation from computed tomography (CT) images is a fundamental problem in femur-related computer-assisted diagnosis and surgical planning/navigation. In this study, an automatic approach for the segmentation of proximal femur from CT images that incorporates the statistical shape prior into the graph-cut framework (SP-GC) is proposed. The proposed segmentation framework includes two major processes, namely training and segmentation. In the training stage, a training set of three-dimensional CT images from a group of normal subjects were segmented semi-automatically. The shape prior was generated by active shape modeling that included mean shape and shape variance information. In the segmentation stage, two shape terms originated from the training stage were included in the GC energy function. The minimization of the energy function was achieved using a max-flow/min-cut algorithm. The performance of the proposed segmentation method was evaluated by testing on 60 CT datasets from bilateral femurs of 30 normal subjects. Qualitative and quantitative analyses of the segmentation results of the proposed method were performed and the results were compared with two widely used methods, namely the active shape model (ASM) and traditional GC, with results from manual delineation used as the ground truth. The mean dice similarity coefficient of the proposed SP-GC was 0.9600, which is higher than those of ASM and GC (0.8769 and 0.9358, respectively). The mean normalized error rate of the SP-GC results was 10 and 6 % lower than those of ASM and GC, respectively. In terms of the average surface distance measurement, the value for SP-GC was 0.885 mm, compared with 2.148 and 1.154 mm for ASM and GC, respectively. In comparison with ASM, SP-GC has superior performance given a small training set (e.g., n = 12). With increasing number of training samples, the segmentation accuracy of ASM saturated, but that of SP-GC slightly increased.