Automated segmentation for patella from lateral knee X-ray images

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

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.

Statistical shape models are often learned from examples based on landmark correspondences between annotated examples. A method is proposed for learning such models from contours with inconsistent bifurcations and loops. Automatic segmentation of tibial and femoral contours in knee X-ray images is investigated as a step towards reliable, quantitative radiographic analysis of osteoarthritis for diagnosis and assessment of progression. Results are presented using various features, the Mahalanobis distance, distance weighted K-nearest neighbours, and two relevance vector machine-based methods as quality of fit measure.

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

A method of extracting, classifying and modelling non-rigid shapes froman image sequence ispresented. Shapes areapproximated by polygonswherethe number of sides is related to the physical features of a shape class ratherthan any particular shape. A method of ‘seeding’ the polygonal approxima-tionisgivenwhere‘seeds’ areautomaticallyextracted fromasetofdata. Mul-tiple models are built using polygons with different numbers of sides to al-low for feature occlusion. Principal component analysis (PCA) is performedon vector representations of the sides of the polygons which are normalisedby the total perimeter. This removes the need for normalisation of scale andtranslationas required in thePointDistributionModel [16]. A ‘fit score’ met-ricisdefinedwhich givesan indicationof howwellagivenshapefitsamodel. 1 Introduction There has been much work carried out on the extraction and classification of non-rigidshapes from image sequences. In this paper a new method of classifying images automat-ically from an image sequence is proposed. This method is applied in the monitoring ofcattle movement to identifya particularnon-rigidobject in a scene (a cow in ourexample)and gain knowledge about the way in which this object changes with time.Kass et al [11] use an active shape model (snake) in which an energy function is min-imisedtoextractanobjectfromascene. TerzopoulosandSzeliski[15]havemadesomere-finementstothistechniquewiththeinclusionofKalmanfiltertechniques(Kalmansnakes).Blake et al [3] have further refined the technique by adding ‘templates’to this process toincorporate a search for a specific shape. In recent years theadvantage of such model-based approaches has been shown where prior informationabout a class of shapes is usedin extraction and classification. The point distributionmodel (PDM) described by Cooteset al [16] is a useful way of describing a class of non-rigid shapeswhere a shape class isdescribed by a fixed number of points. A model is built from a group of shapes fitted withthisfixed number of ‘reference points’ and principalcomponent analysis (PCA) is used toextract ‘modesof variation’fromthedataset. Members ofashapeclass aredescribed withreference to an eigenspace where the axes are the eigenvectors produced from the princi-pal componentanalysis. A ‘valid’shape isconstructedby takingan area inthiseigenspacecentred around the mean shape (origin) and bounded by maximum deviations along eachprincipalaxes whichare related totheeigenvaluesproduced by PCA and thusthevariancewithinthe data set. PDMs rely on accurate positioningof pointsand can only describe ac-curately shape classes which deform in a linear fashion which can result in invalid shapesbeing included in the model.There havebeen a numberof methodsproposedforpointfittingaroundapre-extractedcontour [1, 2] which involve finding a number of reference points (points of high curva-ture,extreme pointsetc) and addingextrapointsspaced evenlyroundthecontoursuch thatthe contour may be approximated by a spline. Hill et al [8] have proposed a new schemewhereby a contour is approximated by an arbitrary number of straight lines as defined bythe critical point detection algorithm described by Zhu and Chirlian [19]. In the compari-sonoftwoshapestheaveragenumberofpointsrequiredtorepresent theshapes isusedand

X-Ray image contains very important information. The information is useful for medical field to diagnose or to analyze any disease or malfunctioned cell. In the analyzing of x-ray image based on computer aided application, object segmentation is very important first step, including tibia and femur segmentation which are part of knee segmentation. Segmentation based Active Shape Model (ASM) can not give perfect result for tibia and femur segmentation. Original version of ASM can not separate each object (tibia and femur) so it creates connection between two segmented object which is disturb the information for image analyzing. To solve this problem, a recovery method for segmentation result based on double labelling object is proposed. Different from other labelling techniques, double labelling technique is performed to achieve more reliable results. The proposed method is a simple to implement by using labeling each object and then removing unused object. To complete this proposed method, dilation is implemented to the two objects which is selected by certain criteria. Experimental results are performed on 10 different images. Based on experiment, it shows that the proposed method gives better result for regular form disturbing area and unused area.

Heart disease is the leading cause of death in the modern world. Cardiac image processing is now routinely applied for detecting, classification and diagnosis of heart diseases. One of the most common uses of processing methods that are now widely applied are cardiac segmentation [1] and registration methods [2], that are used in order to extract the detailed anatomy and function of the heart. Automatic segmentation plays a central role when inspecting reconstructed 3D cardiac images from CT or MR scanners. An accurate classification of the different cardiac regions is usually the first step of tasks like: cardiac visualization, coronary artery inspection, measurement of the ejection fraction for the left and right ventricles and wall motion analysis. In a clinical context, physicians often mentally integrate image information from different modalities. Automatic registration, based on computer programs, might, however, offer better accuracy and repeatability and save time [3]. Cardiac image registration remains a challenge because of the numerous specific problems mainly related to the different motion sources (patient, respiration, heart) and to the specificity of each imaging modality. Up to now, no general method could automatically register any modality with any other modality so far. This paper presents a survey of shape modeling applications to cardiac image analysis from MRI, CT, echocardiography, PET, and SPECT and aims to introduce new methodologies in this field, classify major contributions in image-based cardiac modeling, provide a tutorial to beginners to initiate their own studies, and introduce the major challenges of registration and segmentation and provide practical examples. Image-driven processing methods, such as thresholding, region-based or edge-based techniques, or else pixel classification [4-6], provide a limited framework for further medical image analysis. They can include geometrical information, as well as high level information, in the so-called shape prior based segmentation framework, or through active shape models and active appearance models. At last, atlas guided segmentation also make use of a set of manually segmented images. By using different analysis software of cardiac images, CAD prototypes can be used in clinical routines in order to provide a computer output as a second reader to assist physicians in the detection of abnormalities, quantification of disease progression and differential diagnosis of lesions [7]. Computerized analysis of cardiac images in combination with artificial intelligence can be used in clinical practice and may contribute to more efficient diagnosis.

Active shape models (ASM) are widely employed for recognizing anatomic structures and for delineating them in medical images. In this paper, a novel strategy called oriented active shape models (OASM) is presented in an attempt to overcome the following five limitations of ASM: 1) lower delineation accuracy, 2) the requirement of a large number of landmarks, 3) sensitivity to search range, 4) sensitivity to initialization, and 5) inability to fully exploit the specific information present in the given image to be segmented. OASM effectively combines the rich statistical shape information embodied in ASM with the boundary orientedness property and the globally optimal delineation capability of the live wire methodology of boundary segmentation. The latter characteristics allow live wire to effectively separate an object boundary from other nonobject boundaries with similar properties especially when they come very close in the image domain. The approach leads to a two-level dynamic programming method, wherein the first level corresponds to boundary recognition and the second level corresponds to boundary delineation, and to an effective automatic initialization method. The method outputs a globally optimal boundary that agrees with the shape model if the recognition step is successful in bringing the model close to the boundary in the image. Extensive evaluation experiments have been conducted by utilizing 40 image (magnetic resonance and computed tomography) data sets in each of five different application areas for segmenting breast, liver, bones of the foot, and cervical vertebrae of the spine. Comparisons are made between OASM and ASM based on precision, accuracy, and efficiency of segmentation. Accuracy is assessed using both region-based false positive and false negative measures and boundary-based distance measures. The results indicate the following: 1) The accuracy of segmentation via OASM is considerably better than that of ASM; 2) The number of landmarks can be reduced by a factor of 3 in OASM over that in ASM; 3) OASM becomes largely independent of search range and initialization becomes automatic. All three benefits of OASM ensue mainly from the severe constraints brought in by the boundary-orientedness property of live wire and the globally optimal solution found by the 2-level dynamic programming algorithm.

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.

Many of the 2D/3D registration for joint use 3D bone model obtained by MRI and CT. Making a bone model only use the X-ray image (lateral view) contribute to reducing the cost and exposure dose of X-ray. We have developed the reconstruction methods of subject's 3D bone model from X-ray lateral image and prepared 3D bone model that consists of voxels. In this study, the proposal method was adopted to the cervical spine. Using the 3D bone models made from CT and 3D bone model that was reconstructed the proposed method, template pattern matching was carried out, and the accuracy of pose estimation was compared. Estimation accuracy of the proposed method was θ_x=2.60±2.00deg, θ_y=1.68±1.43deg. Estimation accuracy of the conventional method was θ_x=0.36±0.13deg, θ_y=0.83±0.44deg. Because the present method is to modify the prepared 3D bone model based on only lateral X-ray image, bone shape, especially about the depth direction, cannot exactly reflect subject's bone shape. The method can't reproduction the bone shape with a recessed shape, such as bottom of vertebral body. These problems affect the estimation accuracy.

Semiautomatic Segmentation of Vertebrae in Lateral X-rays Using a Conditional Shape Model

BackgroundAccurate estimation of implant size before surgery is crucial in preparing for total knee arthroplasty. However, this task is time-consuming and labor-intensive. To alleviate this burden on surgeons, we developed a reliable artificial intelligence (AI) model to predict implant size.MethodsWe enrolled 714 patients with knee osteoarthritis who underwent total knee arthroplasty from March 2010 to February 2014. All surgeries were performed by the same surgeon using implants from the same manufacturer. We collected 1412 knee anteroposterior (AP) and lateral view x-ray images and retrospectively investigated the implant size. We trained the AI model using both AP and lateral images without any clinical or demographic information and performed data augmentation to resolve issues of uneven distribution and insufficient data. Using data augmentation techniques, we generated 500 images for each size of the femur and tibia, which were then used to train the model. Using data augmentation techniques, we generated 500 images for each size of the femur and tibia, which were then used to train the model. We used ResNet-101 and optimized the model with the aim of minimizing the cross-entropy loss function using both the Stochastic Gradient Descent (SGD) and Adam optimizer.ResultsThe SGD optimizer achieved the best performance in internal validation. The model showed micro F1-score 0.91 for femur and 0.87 for tibia. For predicting within ± one size, micro F1-score was 0.99 for femur and 0.98 for tibia.ConclusionWe developed a deep learning model with high predictive power for implant size using only simple x-ray images. This could help surgeons reduce the time and labor required for preoperative preparation in total knee arthroplasty. While similar studies have been conducted, our work is unique in its use of simple x-ray images without any other data, like demographic features, to achieve a model with strong predictive power.

Degenerative changes to the cervical spine can be accompanied by neck pain, which can result from narrowing of the intervertebral disc space and growth of osteophytes. In a lateral x-ray image of the cervical spine, degenerative changes are characterized by vertebral bodies that have indistinct boundaries and limited spacing between vertebrae. In this paper, we present a machine learning approach to detect and localize degenerative changes in lateral x-ray images of the cervical spine. Starting from a user-supplied set of points in the center of each vertebral body, we fit a central spline, from which a region of interest is extracted and image features are computed. A Random Forest classifier labels regions as degenerative change or normal. Leave-one-out cross-validation studies performed on a dataset of 103 patients demonstrates performance of above 95% accuracy.

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.

Interactive segmentation of abdominal aortic aneurysms in CTA images