Variational Segmentation Framework Research Articles

Nonlocal graph theory based transductive learning for hyperspectral image classification

Hyperspectral Image classification plays an important role in the maintenance of remote image analysis, which has been attracting a lot of research interest. Although various approaches, including unsupervised and supervised methods, have been proposed, obtaining a satisfactory classification result is still a challenge. In this paper, an efficient transductive learning method using variational nonlocal graph theory for hyperspectral image classification is proposed. First, the nonlocal vector neighborhood similarity is employed to build sparse graph representation. Then the variational segmentation framework is extended to label space, and the vectorization nonlocal energy function is constructed. Next, a fast comprehensive alternating minimization iteration algorithm is designed to implement labels transductive learning. At the same time, the labeled sample constraints are doubled ensured with simplex projection. Finally, experiments on six widely used hyperspectral image datasets are implemented, compared with other state-of-the-art classification methods, the classification results demonstrate that the proposed method has higher classification performance. Benefiting from graph theory and transductive idea, the proposed classification method can propagate labels and overcome the very high dimensionality and limited labeling problem to some extent.

Automatic Auroral Boundary Determination Algorithm With Deep Feature and Dual Level Set

AbstractThe morphology of the auroral oval is an important geophysical parameter that helps to further understand the solar wind‐magnetosphere‐ionosphere coupling process. However, it is still a challenging task to automatically obtain auroral poleward and equatorward boundaries completely and accurately. In this paper, a new model based on the deep feature and dual level set method is proposed to extract the auroral oval boundaries in the images acquired by the Ultraviolet Imager (UVI) onboard the Polar spacecraft. With the deep feature extracted by the convolutional neural network (CNN), the corresponding deep feature energy functional is constructed and incorporated into the variational segmentation framework. The dual level set method is implemented to extract the accurate poleward and equatorward boundaries with the gradient descent flow. The experimental results on the test data set demonstrate that this model can extract complete auroral oval contours that are consistent well with annotations and owns higher accuracy compared with the previously proposed methods. Comparison between the extracted auroral boundaries and the precipitating boundaries determined by Defense Meteorological Satellite Program (DMSP) SSJ precipitating particle data validates that the proposed method is trustworthy to capture the global morphology of the auroral ovals.

Optimizing the cervix cytological examination based on deep learning and dynamic shape modeling

The task of segmenting nuclei and cytoplasm in Papanicolau smear images is one of the most challenging tasks in automated cervix cytological analysis owing to the high degree of overlapping, the multiform shape of the cells and their complex structures resulting from inconsistent staining, poor contrast, and the presence of inflammatory cells. This article presents a robust variational segmentation framework based on superpixelwise convolutional neutral network and a learned shape prior enabling an accurate analysis of overlapping cervical mass. The cellular components of Pap image are first classified by automatic feature learning and classification model. Then, a learning shape prior model is employed to delineate the actual contour of each individual cytoplasm inside the overlapping mass. The shape prior is dynamically modeled during the segmentation process as a weighted linear combination of shape templates from an over-complete shape dictionary under sparsity constraints. We provide quantitative and qualitative assessment of the proposed method using two databases of 153 cervical cytology images, with 870 cells in total, synthesised by accumulating real isolated cervical cells to generate overlapping cellular masses with a varying number of cells and degree of overlap. The experimental results have demonstrated that our methodology can successfully segment nuclei and cytoplasm from highly overlapping mass. Our segmentation is also competitive when compared to the state-of-the-art methods.

TH‐CD‐206‐06: Regularized Composite Shape Prior Encoding Shape Relevance in Variational Image Segmentation

Purpose:Variational image segmentation incorporating regularized composite shape prior (RCSP) based on a shape dictionary has demonstrated benefits in robustness and accuracy. However, it still has the risk of local minimum in a non‐convex optimization setting. This study aims to drive the variational segmentation towards global optimum by introducing hyper prior on the composite weights of RCSP, which encode the shape priors’ relevance to the specific segmentation task.Methods:In addition to using a RCSP to regularize the variational segmentation, where the RCSP is constructed by a linear combination of the shape dictionary, this study introduces a hyper prior on the linear weights of this shape composite. More specifically, geometric relevance of each shape in the dictionary to the unknown target segmentation is inferred from image based surrogate metrics. Such relevance value is used as hyper prior and imposed on the linear weights of the composite shapes. The resulted RCSP with hyper prior regularization is incorporated in a unified active contour optimization framework and a variational block‐descent algorithm is derived and implemented.Results:The performance was assessed on corpus callosum segmentation using a brain MR dataset, and compared with typical benchmark approaches. The resulted RCSP demonstrated proper composition of training data w.r.t. their individual geometric relevance. The accuracy of ultimate segmentation estimates yielded statistically significant improvement with mean and medium Dice similarity coefficient (DSC) of (.946, .963) compared to (.902, .919), (.932, .946), and (.944, .964) for ATLAS based scheme, Chan Vese active contour model and an existing RCSP model, respectively.Conclusion:This work has developed a hyper prior to encode shape priors’ geometric relevance for RCSP regularization in a variational segmentation framework, leading to superior segmentation over benchmark approaches.

A unified variational segmentation framework with a level-set based sparse composite shape prior

Image segmentation plays an essential role in many medical applications. Low SNR conditions and various artifacts makes its automation challenging. To achieve robust and accurate segmentation results, a good approach is to introduce proper shape priors. In this study, we present a unified variational segmentation framework that regularizes the target shape with a level-set based sparse composite prior. When the variational problem is solved with a block minimization/decent scheme, the regularizing impact of the sparse composite prior can be observed to adjust to the most recent shape estimate, and may be interpreted as a ‘dynamic’ shape prior, yet without compromising convergence thanks to the unified energy framework. The proposed method was applied to segment corpus callosum from 2D MR images and liver from 3D CT volumes. Its performance was evaluated using Dice Similarity Coefficient and Hausdorff distance, and compared with two benchmark level-set based segmentation methods. The proposed method has achieved statistically significant higher accuracy in both experiments and avoided faulty inclusion/exclusion of surrounding structures with similar intensities, as opposed to the benchmark methods.

Segmentation of embryonic and fetal 3D ultrasound images based on pixel intensity distributions and shape priors.

This paper presents a novel variational segmentation framework combining shape priors and parametric intensity distribution modeling for extracting the fetal envelope on 3D obstetric ultrasound images. To overcome issues related to poor image quality and missing boundaries, we inject three types of information in the segmentation process: tissue-specific parametric modeling of pixel intensities, a shape prior for the fetal envelope and a shape model of the fetus' back. The shape prior is encoded with Legendre moments and used to constraint the evolution of a level-set function. The back model is used to post-process the segmented fetal envelope. Results are presented on 3D ultrasound data and compared to a set of manual segmentations. The robustness of the algorithm is studied, and both visual and quantitative comparisons show satisfactory results obtained by the proposed method on the tested dataset.

A Novel Approach for Lung Nodules Segmentation in Chest CT Using Level Sets

A new variational level set approach is proposed for lung nodule segmentation in lung CT scans. A general lung nodule shape model is proposed using implicit spaces as a signed distance function. The shape model is fused with the image intensity statistical information in a variational segmentation framework. The nodule shape model is mapped to the image domain by a global transformation that includes inhomogeneous scales, rotation, and translation parameters. A matching criteria between the shape model and the image implicit representations is employed to handle the alignment process. Transformation parameters evolve through gradient descent optimization to handle the shape alignment process and hence mark the boundaries of the nodule “head.” The embedding process takes into consideration the image intensity as well as prior shape information. A nonparametric density estimation approach is employed to handle the statistical intensity representation of the nodule and background regions. The proposed technique does not depend on nodule type or location. Exhaustive experimental and validation results are demonstrated on 742 nodules obtained from four different CT lung databases, illustrating the robustness of the approach.

A Variational Framework for Region-Based Segmentation Incorporating Physical Noise Models

Image segmentation is one of the fundamental problems in computer vision and image processing. In the recent years mathematical models based on partial differential equations and variational methods have led to superior results in many applications, e.g., medical imaging. A majority of works on image segmentation implicitly assume the given image to be biased by additive Gaussian noise, for instance the popular Mumford-Shah model. Since this assumption is not suitable for a variety of problems, we propose a region-based variational segmentation framework to segment also images with non-Gaussian noise models. Motivated by applications in biomedical imaging, we discuss the cases of Poisson and multiplicative speckle noise intensively. Analytical results such as the existence of a solution are verified and we investigate the use of different regularization functionals to provide a-priori information regarding the expected solution. The performance of the proposed framework is illustrated by experimental results on synthetic and real data.

3D variational brain tumor segmentation using Dirichlet priors on a clustered feature set

Brain tumor segmentation is a required step before any radiation treatment or surgery. When performed manually, segmentation is time consuming and prone to human errors. Therefore, there have been significant efforts to automate the process. But, automatic tumor segmentation from MRI data is a particularly challenging task. Tumors have a large diversity in shape and appearance with intensities overlapping the normal brain tissues. In addition, an expanding tumor can also deflect and deform nearby tissue. In our work, we propose an automatic brain tumor segmentation method that addresses these last two difficult problems. We use the available MRI modalities (T1, T1c, T2) and their texture characteristics to construct a multidimensional feature set. Then, we extract clusters which provide a compact representation of the essential information in these features. The main idea in this work is to incorporate these clustered features into the 3D variational segmentation framework. In contrast to previous variational approaches, we propose a segmentation method that evolves the contour in a supervised fashion. The segmentation boundary is driven by the learned region statistics in the cluster space. We incorporate prior knowledge about the normal brain tissue appearance during the estimation of these region statistics. In particular, we use a Dirichlet prior that discourages the clusters from the normal brain region to be in the tumor region. This leads to a better disambiguation of the tumor from brain tissue. We evaluated the performance of our automatic segmentation method on 15 real MRI scans of brain tumor patients, with tumors that are inhomogeneous in appearance, small in size and in proximity to the major structures in the brain. Validation with the expert segmentation labels yielded encouraging results: Jaccard (58%), Precision (81%), Recall (67%), Hausdorff distance (24mm). Using priors on the brain/tumor appearance, our proposed automatic 3D variational segmentation method was able to better disambiguate the tumor from the surrounding tissue.