Shuyang Zhang

Semiautomatic segmentation of aortic valve from sequenced ultrasound image using a novel shape-constraint GCV model

PURPOSE Effective and accurate segmentation of the aortic valve (AV) from sequenced ultrasound (US) images remains a technical challenge because of intrinsic factors of ultrasound images that impact the quality and the continuous changes of shape and position of segmented objects. In this paper, a novel shape-constraint gradient Chan-Vese (GCV) model is proposed for segmenting the AV from time serial echocardiography. METHODS The GCV model is derived by incorporating the energy of the gradient vector flow into a CV model framework, where the gradient vector energy term is introduced by calculating the deviation angle between the inward normal force of the evolution contour and the gradient vector force. The flow force enlarges the capture range and enhances the blurred boundaries of objects. This is achieved by adding a circle-like contour (constructed using the AV structure region as a constraint shape) as an energy item to the GCV model through the shape comparison function. This shape-constrained energy can enhance the image constraint force by effectively connecting separate gaps of the object edge as well as driving the evolution contour to quickly approach the ideal object. Because of the slight movement of the AV in adjacent frames, the initial constraint shape is defined by users, with the other constraint shapes being derived from the segmentation results of adjacent sequence frames after morphological filtering. The AV is segmented from the US images by minimizing the proposed energy function. RESULTS To evaluate the performance of the proposed method, five assessment parameters were used to compare it with manual delineations performed by radiologists (gold standards). Three hundred and fifteen images acquired from nine groups were analyzed in the experiment. The area-metric overlap error rate was 6.89% ± 2.88%, the relative area difference rate 3.94% ± 2.63%, the average symmetric contour distance 1.08 ± 0.43 mm, the root mean square symmetric contour distance 1.37 ± 0.52 mm, and the maximum symmetric contour distance was 3.57 ± 1.72 mm. CONCLUSIONS Compared with the CV model, as a result of the combination of the gradient vector and neighborhood shape information, this semiautomatic segmentation method significantly improves the accuracy and robustness of AV segmentation, making it feasible for improved segmentation of aortic valves from US images that have fuzzy boundaries.

Sparse group composition for robust left ventricular epicardium segmentation

Left ventricular (LV) epicardium segmentation in cardiac magnetic resonance images (MRIs) is still a challenging task, where the a-priori knowledge like those that incorporate the heart shape model is usually used to derive reasonable segmentation results. In this paper, we propose a sparse group composition (SGC) approach to model multiple shapes simultaneously, which extends conventional sparsity-based single shape prior modeling to incorporate a-priori spatial constraint information among multiple shapes on-the-fly. Multiple interrelated shapes (shapes of epi- and endo-cardium of myocardium in the case of LV epicardium segmentation) are regarded as a group, and sparse linear composition of training groups is computed to approximate the input group. A framework of iterative procedure of refinement based on SGC and segmentation based on deformation model is utilized for LV epicardium segmentation, in which an improved shape-constraint gradient Chan-Vese model (GCV) acted as deformation model. Compared with the standard sparsity-based single shape prior modeling, the refinement procedure has strong robust for relative gross and not much sparse errors in the input shape and the initial epicardium location can be estimated without complicated landmark detection due to modeling spatial constraint information among multiple shapes effectively. Proposed method was validated on 45 cardiac cine-MR clinical datasets and the results were compared with expert contours. The average perpendicular distance (APD) error of contours is 1.50±0.29mm, and the dice metric (DM) is 0.96±0.01. Compared to the state-of-the-art methods, our proposed approach appealed competitive segmentation performance and improved robustness.

Myocardium segmentation from DE MRI with guided random walks and sparse shape representation

PurposeFor patients with myocardial infarction (MI), delayed enhancement (DE) cardiovascular magnetic resonance imaging (MRI) is a sensitive and well-validated technique for the detection and visualization of MI. The myocardium viability assessment with DE MRI is important in diagnosis and treatment management, where myocardium segmentation is a prerequisite. However, few academic works have focused on automated myocardium segmentation from DE images. In this study, we aim to develop an automatic myocardium segmentation algorithm that targets DE images.MethodsWe propose a segmentation framework based on both prior shape knowledge and image intensity. Instead of the strong request of the pre-segmentation of cine MRI in the same session, we use the sparse representation method to model the myocardium shape. Data from the Cardiac MR Left Ventricle Segmentation Challenge (2009) are used to build the shape template repository. The method of guided random walks is used to integrate the shape model and intensity information. An iterative approach is used to gradually improve the results.ResultsThe proposed method was tested on the DE MRI data from 30 MI patients. The proposed method achieved Dice similarity coefficients (DSC) of 74.60 ± 7.79% with 201 shape templates and 73.56 ± 6.32% with 56 shape templates, which were close to the inter-observer difference (73.94 ± 5.12%). To test the generalization of the proposed method to routine clinical images, the DE images of 10 successive new patients were collected, which were unseen during the method development and parameter tuning, and a DSC of 76.02 ± 7.43% was achieved.ConclusionThe authors propose a novel approach for the segmentation of myocardium from DE MRI by using the sparse representation-based shape model and guided random walks. The sparse representation method effectively models the prior shape with a small number of shape templates, and the proposed method has the potential to achieve clinically relevant results.

Minimization of annotation work: diagnosis of mammographic masses via active learning

The prerequisite for establishing an effective prediction system for mammographic diagnosis is the annotation of each mammographic image. The manual annotation work is time-consuming and laborious, which becomes a great hindrance for researchers. In this article, we propose a novel active learning algorithm that can adequately address this problem, leading to the minimization of the labeling costs on the premise of guaranteed performance. Our proposed method is different from the existing active learning methods designed for the general problem as it is specifically designed for mammographic images. Through its modified discriminant functions and improved sample query criteria, the proposed method can fully utilize the pairing of mammographic images and select the most valuable images from both the mediolateral and craniocaudal views. Moreover, in order to extend active learning to the ordinal regression problem, which has no precedent in existing studies, but is essential for mammographic diagnosis (mammographic diagnosis is not only a classification task, but also an ordinal regression task for predicting an ordinal variable, viz. the malignancy risk of lesions), multiple sample query criteria need to be taken into consideration simultaneously. We formulate it as a criteria integration problem and further present an algorithm based on self-adaptive weighted rank aggregation to achieve a good solution. The efficacy of the proposed method was demonstrated on thousands of mammographic images from the digital database for screening mammography. The labeling costs of obtaining optimal performance in the classification and ordinal regression task respectively fell to 33.8 and 19.8 percent of their original costs. The proposed method also generated 1228 wins, 369 ties and 47 losses for the classification task, and 1933 wins, 258 ties and 185 losses for the ordinal regression task compared to the other state-of-the-art active learning algorithms. By taking the particularities of mammographic images, the proposed AL method can indeed reduce the manual annotation work to a great extent without sacrificing the performance of the prediction system for mammographic diagnosis.

Vesselness-constrained robust PCA for vessel enhancement in x-ray coronary angiograms

Effective vessel enhancement in x-ray coronary angiograms (XCA) is essential for the diagnosis of coronary artery disease, yet challenged by complex background structures of varying intensities as well as motion patterns. As a typical layer-separation method, robust principal component analysis (RPCA) has been proposed to automatically improve vessel visibility via sparse and low-rank decomposition. However, the attenuated motion of vessels in x-ray angiograms leads to the unsatisfactory vessel enhancement performance of the decomposition framework. To address this problem, we propose a vesselness-constrained RPCA method (VC-RPCA), where a vessel-like appearance prior is incorporated into the layer separation framework for accurate vessel enhancement. We first pre-compute the vessel-like appearance prior based on a Frangi filter to highlight the curvilinear structures. After removing large-scale background structures via a morphological closing operation, we then integrate the pre-computed vessel-like appearance prior into a low-rank decomposition framework to separate the fine vessel structures. In addition, we develop an adaptive regularization strategy that imposes structured-sparse constraints to solve the scale issue and capture vessels without salient motion. The proposed method was validated on 13 clinical XCA sequences containing 777 images in total. The contrast-to-noise ratio, Dice coefficient and area under the ROC curve were employed for quantitative evaluation of the vessel enhancement performance. Experiments show that (1) the adaptive regularization strategy helps to obtain a complete coronary tree in the separated vessel layer; (2) our low-rank decomposition framework is robust against false positive/negative responses of the Frangi filter; and (3) the proposed VC-RPCA is computationally fast and outperforms other state-of-the-art RPCA methods for vessel enhancement in the full-contrast and low-contrast scenarios. The results demonstrate that the proposed VC-RPCA can accurately separate coronary arteries and prominently improve vessel visibility in x-ray angiograms.

Patient-specific respiratory motion estimation using Sparse Motion Field Presentation

Respiratory motion estimation plays a significant role in radiation therapy. Previous motion estimation approaches usually depended on 4DCT, which introduced extra radio dose for patients, and the local motion details were ignored in the statistical model. In this paper, we propose a novel estimation framework, which employs the Sparse Motion Field Presentation (SMFP) method to obtain a coarse motion estimation which preserves patient-specific respiratory motion details and an Adaptive Variable Coefficient (AVC) motion prior registration approach is applied for the accurate estimation. The experimental results show that the proposed framework effectively preserved the local motion details and achieved more accurate motion estimations compared to the Mean Motion Model (MMM) and the Principal Component Analysis (PCA) model. We achieved motion estimations for diaphragmatic breathing type, thoracic breathing type and mixed type, respectively. The accuracy measured in the average symmetric surface distance (standard deviation) were 1.9(0.9) mm, 2.4(1.1) mm and 2.2(1.0) mm, when the sum of squared intensity difference (SSD) were 5.0, 6.1 and 5.6, respectively.Respiratory motion estimation plays a significant role in radiation therapy. Previous motion estimation approaches usually depended on 4DCT, which introduced extra radio dose for patients, and the local motion details were ignored in the statistical model. In this paper, we propose a novel estimation framework, which employs the Sparse Motion Field Presentation (SMFP) method to obtain a coarse motion estimation which preserves patient-specific respiratory motion details and an Adaptive Variable Coefficient (AVC) motion prior registration approach is applied for the accurate estimation. The experimental results show that the proposed framework effectively preserved the local motion details and achieved more accurate motion estimations compared to the Mean Motion Model (MMM) and the Principal Component Analysis (PCA) model. We achieved motion estimations for diaphragmatic breathing type, thoracic breathing type and mixed type, respectively. The accuracy measured in the average symmetric surface distance (standard deviation) were 1.9(0.9) mm, 2.4(1.1) mm and 2.2(1.0) mm, when the sum of squared intensity difference (SSD) were 5.0, 6.1 and 5.6, respectively.

Pilot study on vascular intervention training based on blood flow effected guidewire simulation

A decent guidewire behavior simulation is vital to the virtual vascular intervention training. The influence of blood flow has rarely been taken into consideration in former works of guidewire simulation. This paper addresses the problem by integrating blood flow analysis and proposes a novel guidewire simulation model.The blood flow distribution inside arterial vasculature is computed by separating the vascular model into discrete cylindrical vessels and modeling the flow in each vessel with the Poiseuille Law. The blood flow computation is then integrated into a Kirchhoff rods model. The simulation could be run in real time with hardware acceleration at least 30 fps. To validate the result, an experiment environment with a 3D printed vascular phantom and an electromagnetic tracking(EMT) system was set up with clinical-used guidewire sensors applied in phantom to trace its motion as the standard for comparison. Experiment results reveal that the shown blood flow effected model presents better physical credibility with a lower and more stable root-mean-square(RMS) at 2.14mm ± 1.24mm, better than the Kirchhoff model of 4.81mm±3.80mm.A decent guidewire behavior simulation is vital to the virtual vascular intervention training. The influence of blood flow has rarely been taken into consideration in former works of guidewire simulation. This paper addresses the problem by integrating blood flow analysis and proposes a novel guidewire simulation model.

Lung respiration motion modeling: a sparse motion field presentation method using biplane x-ray images

Respiration-introduced tumor location uncertainty is a challenge in the precise lung biopsy for lung lesions. Current statistical modeling approaches hardly capture the complex local respiratory motion information. In this study, we formulate a statistical respiratory motion model using biplane x-ray images to improve the accuracy of motion field estimation by efficiently preserving local motion details for specific patients. Given CT data sets of 18 healthy subjects at end-expiratory and end-inspiratory breathing phases, the respiratory motion field is constructed based on deformation vector fields which are extracted from these CT data sets, and a lung contour motion repository respiratory is generated dependent on displacements of boundary control points. By varying the sparse weight coefficients of the statistical sparse motion field presentation (SMFP) method, the newly-input motion field is approximately presented by a sparse linear combination of a subset of the motion repository. The SMFP method is employed twice in the coefficient optimization process. Finally, these non-zero coefficients are fine-tuned to maximize the similarity between the projection image of reconstructed volumetric images and the current x-ray image. We performed the proposed method for estimating respiratory motion field on ten subject datasets and compared the result with the PCA method. The maximum average target registration error of the PCA-based and the SMFP-based respiratory motion field estimation are 3.1(2.0) and 2.9(1.6) mm, respectively. The maximum average symmetric surface distance of two methods are 2.5(1.6) and 2.4(1.3) mm, respectively.