Shuo Li

Embedding Overlap Priors in Variational Left Ventricle Tracking

We propose to embed overlap priors in variational tracking of the left ventricle (LV) in cardiac magnetic resonance (MR) sequences. The method consists of evolving two curves toward the LV endo- and epicardium boundaries. We derive the curve evolution equations by minimizing two functionals each containing an original overlap prior constraint. The latter measures the conformity of the overlap between the nonparametric (kernel-based) intensity distributions within the three target regions-LV cavity, myocardium and background-to a prior learned from a given segmentation of the first frame. The Bhattacharyya coefficient is used as an overlap measure. Different from existing intensity-driven constraints, the proposed priors do not assume implicitly that the overlap between the intensity distributions within different regions has to be minimal. This prevents both the papillary muscles from being included erroneously in the myocardium and the curves from spilling into the background. Although neither geometric training nor preprocessing were used, quantitative evaluation of the similarities between automatic and independent manual segmentations showed that the proposed method yields a competitive score in comparison with existing methods. This allows more flexibility in clinical use because our solution is based only on the current intensity data, and consequently, the results are not bounded to the characteristics, variability, and mathematical description of a finite training set. We also demonstrate experimentally that the overlap measures are approximately constant over a cardiac sequence, which allows to learn the overlap priors from a single frame.

Intervertebral disc segmentation in MR images using anisotropic oriented flux

This study proposes an unsupervised intervertebral disc segmentation system based on middle sagittal spine MR scans. The proposed system employs the novel anisotropic oriented flux detection scheme which helps distinguish the discs from the neighboring structures with similar intensity, recognize ambiguous disc boundaries, and handle the shape and intensity variation of the discs. Based on minimal user interaction, the proposed system begins with vertebral body tracking to infer the information regarding the positions and orientations of the target intervertebral discs. The information is employed in a set of image descriptors, which jointly constitute an energy functional describing the desired disc segmentation result. The energy functional is minimized by a level set based active contour model to perform disc segmentation. The proposed segmentation system is evaluated using a database consisting of 455 intervertebral discs extracted from 69 middle sagittal slices. It is demonstrated that the proposed method is capable of delivering accurate results for intervertebral disc segmentation.

Graph cuts with invariant object-interaction priors: application to intervertebral disc segmentation

This study investigates novel object-interaction priors for graph cut image segmentation with application to intervertebral disc delineation in magnetic resonance (MR) lumbar spine images. The algorithm optimizes an original cost function which constrains the solution with learned prior knowledge about the geometric interactions between different objects in the image. Based on a global measure of similarity between distributions, the proposed priors are intrinsically invariant with respect to translation and rotation. We further introduce a scale variable from which we derive an original fixed-point equation (FPE), thereby achieving scale-invariance with only few fast computations. The proposed priors relax the need of costly pose estimation (or registration) procedures and large training sets (we used a single subject for training), and can tolerate shape deformations, unlike template-based priors. Our formulation leads to an NP-hard problem which does not afford a form directly amenable to graph cut optimization. We proceeded to a relaxation of the problem via an auxiliary function, thereby obtaining a nearly real-time solution with few graph cuts. Quantitative evaluations over 60 intervertebral discs acquired from 10 subjects demonstrated that the proposed algorithm yields a high correlation with independent manual segmentations by an expert. We further demonstrate experimentally the invariance of the proposed geometric attributes. This supports the fact that a single subject is sufficient for training our algorithm, and confirms the relevance of the proposed priors to disc segmentation.

Left Ventricle Segmentation via Graph Cut Distribution Matching

We present a discrete kernel density matching energy for segmenting the left ventricle cavity in cardiac magnetic resonance sequences. The energy and its graph cut optimization based on an original first-order approximation of the Bhattacharyya measure have not been proposed previously, and yield competitive results in nearly real-time. The algorithm seeks a region within each frame by optimization of two priors, one geometric (distance-based) and the other photometric, each measuring a distribution similarity between the region and a model learned from the first frame. Based on global rather than pixelwise information, the proposed algorithm does not require complex training and optimization with respect to geometric transformations. Unlike related active contour methods, it does not compute iterative updates of computationally expensive kernel densities. Furthermore, the proposed first-order analysis can be used for other intractable energies and, therefore, can lead to segmentation algorithms which share the flexibility of active contours and computational advantages of graph cuts. Quantitative evaluations over 2280 images acquired from 20 subjects demonstrated that the results correlate well with independent manual segmentations by an expert.

Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure

This study investigates fast detection of the left ventricle (LV) endo- and epicardium boundaries in a cardiac magnetic resonance (MR) sequence following the optimization of two original discrete cost functions, each containing global intensity and geometry constraints based on the Bhattacharyya similarity. The cost functions and the corresponding max-flow optimization built upon an original bound of the Bhattacharyya measure yield competitive results in nearly real-time. Within each frame, the algorithm seeks the LV cavity and myocardium regions consistent with subject-specific model distributions learned from the first frame in the sequence. Based on global rather than pixel-wise information, the proposed formulation relaxes the need of a large training set and optimization with respect to geometric transformations. Different from related active contour methods, it does not require a large number of iterative updates of the segmentation and the corresponding computationally onerous kernel density estimates (KDEs). The algorithm requires very few iterations and KDEs to converge. Furthermore, the proposed bound can be used for several other applications and, therefore, can lead to segmentation algorithms which share the flexibility of active contours and computational advantages of max-flow optimization. Quantitative evaluations over 2280 images acquired from 20 subjects demonstrated that the results correlate well with independent manual segmentations by an expert. Moreover, comparisons with a related recent active contour method showed that the proposed framework brings significant improvements in regard to accuracy and computational efficiency.

Graph cut segmentation with a global constraint: Recovering region distribution via a bound of the Bhattacharyya measure

This study investigates an efficient algorithm for image segmentation with a global constraint based on the Bhattacharyya measure. The problem consists of finding a region consistent with an image distribution learned a priori. We derive an original upper bound of the Bhattacharyya measure by introducing an auxiliary labeling. From this upper bound, we reformulate the problem as an optimization of an auxiliary function by graph cuts. Then, we demonstrate that the proposed procedure converges and give a statistical interpretation of the upper bound. The algorithm requires very few iterations to converge, and finds nearly global optima. Quantitative evaluations and comparisons with state-of-the-art methods on the Microsoft GrabCut segmentation database demonstrated that the proposed algorithm brings improvements in regard to segmentation accuracy, computational efficiency, and optimality. We further demonstrate the flexibility of the algorithm in object tracking.

Semi-automatic computer aided lesion detection in dental X-rays using variational level set

A semi-automatic lesion detection framework is proposed to detect areas of lesions from periapical dental X-rays using level set method. In this framework, first, a new proposed competitive coupled level set method is used to segment the image into three pathologically meaningful regions using two coupled level set functions. Tailored for the dental clinical setting, a two-stage clinical segmentation acceleration scheme is used. The method uses a trained support vector machine (SVM) classifier to provide an initial contour for two coupled level sets. Then, based on the segmentation results, an analysis scheme is applied. Firstly, the scheme builds an uncertainty map from which those areas with radiolucent will be automatically emphasized by a proposed color emphasis scheme. Those radiolucent in the teeth or jaw usually suggested possible lesions. Secondly, the scheme employs a method based on the average intensity profile to isolate the teeth and locate two types of lesions: periapical lesion (PL) and bifurcation lesion (BL). Experimental results show that our proposed segmentation method is able to segment the image into pathological meaningful regions for further analysis; our proposed framework is able to automatically provide direct visual cues for the lesion detection; and when given the orientation of the teeth, it is able to automatically locate the PL and BL with a seriousness level marked for further dental diagnosis. When used in the clinical setting, the framework enables dentist to improve interpretation and to focus their attention on critical areas.

Regression Segmentation for

Clinical routine often requires to analyze spinal images of multiple anatomic structures in multiple anatomic planes from multiple imaging modalities ( M3). Unfortunately, existing methods for segmenting spinal images are still limited to one specific structure, in one specific plane or from one specific modality ( S3). In this paper, we propose a novel approach, Regression Segmentation, that is for the first time able to segment M3 spinal images in one single unified framework. This approach formulates the segmentation task innovatively as a boundary regression problem: modeling a highly nonlinear mapping function from substantially diverse M3 images directly to desired object boundaries. Leveraging the advancement of sparse kernel machines, regression segmentation is fulfilled by a multi-dimensional support vector regressor (MSVR) which operates in an implicit, high dimensional feature space where M3 diversity and specificity can be systematically categorized, extracted, and handled. The proposed regression segmentation approach was thoroughly tested on images from 113 clinical subjects including both disc and vertebral structures, in both sagittal and axial planes, and from both MRI and CT modalities. The overall result reaches a high dice similarity index (DSI) 0.912 and a low boundary distance (BD) 0.928 mm. With our unified and expendable framework, an efficient clinical tool for M3 spinal image segmentation can be easily achieved, and will substantially benefit the diagnosis and treatment of spinal diseases.

M^{3}

This study investigates variational image segmentation with an original data term, referred to as statistical overlap prior, which measures the conformity of overlap between the nonparametric distributions of image data within the segmentation regions to a learned statistical description. This leads to image segmentation and distribution tracking algorithms that relax the assumption of minimal overlap and, as such, are more widely applicable than existing algorithms. We propose to minimize active curve functionals containing the proposed overlap prior, compute the corresponding Euler-Lagrange curve evolution equations, and give an interpretation of how the overlap prior controls such evolution. We model the overlap, measured via the Bhattacharyya coefficient, with a Gaussian prior whose parameters are estimated from a set of relevant training images. Quantitative and comparative performance evaluations of the proposed algorithms over several experiments demonstrate the positive effects of the overlap prior in regard to segmentation accuracy and convergence speed.

Spinal Images

Automating the detection and localization of segmental (regional) left ventricle (LV) abnormalities in magnetic resonance imaging (MRI) has recently sparked an impressive research effort, with promising performances and a breadth of techniques. However, despite such an effort, the problem is still acknowledged to be challenging, with much room for improvements in regard to accuracy. Furthermore, most of the existing techniques are labor intensive, requiring delineations of the endo- and/or epi-cardial boundaries in all frames of a cardiac sequence. The purpose of this study is to investigate a real-time machine-learning approach which uses some image features that can be easily computed, but that nevertheless correlate well with the segmental cardiac function. Starting from a minimum user input in only one frame in a subject dataset, we build for all the regional segments and all subsequent frames a set of statistical MRI features based on a measure of similarity between distributions. We demonstrate that, over a cardiac cycle, the statistical features are related to the proportion of blood within each segment. Therefore, they can characterize segmental contraction without the need for delineating the LV boundaries in all the frames. We first seek the optimal direction along which the proposed image features are most descriptive via a linear discriminant analysis. Then, using the results as inputs to a linear support vector machine classifier, we obtain an abnormality assessment of each of the standard cardiac segments in real-time. We report a comprehensive experimental evaluation of the proposed algorithm over 928 cardiac segments obtained from 58 subjects. Compared against ground-truth evaluations by experienced radiologists, the proposed algorithm performed competitively, with an overall classification accuracy of 86.09% and a kappa measure of 0.73.