Changhua Wu

Vessel tree reconstruction in thoracic CT scans with application to nodule detection

Vessel tree reconstruction in volumetric data is a necessary prerequisite in various medical imaging applications. Specifically, when considering the application of automated lung nodule detection in thoracic computed tomography (CT) scans, vessel trees can be used to resolve local ambiguities based on global considerations and so improve the performance of nodule detection algorithms. In this study, a novel approach to vessel tree reconstruction and its application to nodule detection in thoracic CT scans was developed by using correlation-based enhancement filters and a fuzzy shape representation of the data. The proposed correlation-based enhancement filters depend on first-order partial derivatives and so are less sensitive to noise compared with Hessian-based filters. Additionally, multiple sets of eigenvalues are used so that a distinction between nodules and vessel junctions becomes possible. The proposed fuzzy shape representation is based on regulated morphological operations that are less sensitive to noise. Consequently, the vessel tree reconstruction algorithm can accommodate vessel bifurcation and discontinuities. A quantitative performance evaluation of the enhancement filters and of the vessel tree reconstruction algorithm was performed. Moreover, the proposed vessel tree reconstruction algorithm reduced the number of false positives generated by an existing nodule detection algorithm by 38%.

Robot-Assisted Sensor Network Deployment and Data Collection

Wireless sensor networks have been widely used in many applications such as environment monitoring, surveillance systems and unmanned space explorations. However, poor deployment of sensor devices leads (1) bad network connectivity which makes data communication or data collection very hard; or (2) redundancy of coverage which wastes energy of sensors and causes redundant data in the network. Thus, in this paper, we propose using a mobile robot to assist the sensor deployment and data collection for unmanned explorations or monitoring. We assume that the robot can carry and deploy the sensor devices, and also have certain communication capacity to collect the data from the sensor devices. Given a set of interest points in an area, we study the following interesting problems: (1) how to decide minimum number of sensor devices to cover all the interest points; (2) how to schedule the robot to place these sensor devices in certain position so that the path of the robot is minimum; and (3) after the deployment of sensors, how to schedule the robot to visit and communicate with these sensor devices to collect data so that the path of the robot is minimum. We propose a complete set of heuristics for all these problems and verify the performances via simulation.

Document Image De-warping for Text/Graphics Recognition

Document analysis and graphics recognition algorithms are normally applied to the processing of images of 2D documents scanned when flattened against a planar surface. Technological advancements in recent years have led to a situation in which digital cameras with high resolution are widely available. Consequently, traditional graphics recognition tasks may be updated to accommodate document images captured through a hand-held camera in an uncontrolled environment. In this paper the problem of perspective and geometric deformations correction in document images is discussed. The proposed approach uses the texture of a document image so as to infer the document structure distortion. A two-pass image warping algorithm is then used to correct the images. In addition to being language independent, the proposed approach may handle document images that include multiple fonts, math notations, and graphics. The de-warped images contain less distortions and so are better suited for existing text/graphics recognition techniques.

Mobile Sensor Networks Self Localization based on Multi-dimensional Scaling

In this paper, we define a mobile self-localization (MSL) problem for sparse mobile sensor networks, and propose an algorithm named mobility assisted MDS-MAP(P), based on multi-dimensional scaling (MDS) for solving the problem. For sparse sensor networks, all the existing localization algorithms fail to work properly due to the lack of distance or connectivity data to uniquely calculate the geo-locations. In MSL, we use mobile sensors to add extra distance constraints to a sparse network, by moving the mobile sensors in the area of deployment and recording distances to neighbors at some intermediate locations. MSL can also be used for localizing and tracking mobile objects in a robotic or body sensor network. Experiments and evaluations of the new algorithm are provided.

Probabilistic modeling based vessel enhancement in thoracic CT scans

Vessel enhancement in volumetric data is a necessary prerequisite in various medical imaging applications with particular importance for automated nodule detection. Ideally, vessel enhancement filters should enhance vessels and vessel junctions while suppressing nodules and other non-vessel elements. A distinction between vessels and nodules is normally obtained through eigenvalue analysis of the curvature tensor which is a second order differential quantity and so is sensitive to noise. Furthermore, by relying on principal curvatures alone, existing vessel enhancement filters are incapable of distinguishing between nodules and vessel junctions. In this paper we propose probabilistic vessel models from which novel vessel enhancement filters capable of enhancing junctions while suppressing nodules are derived. The proposed filters are based on eigenvalue analysis of the structure tensor which is a first order differential quantity and so are less sensitive to noise. The proposed filters are evaluated and compared to known techniques based on actual clinical data.

A general framework for vessel segmentation in retinal images

We present a general framework for vessel segmentation in retinal images with a particular focus on small vessels. The retinal images are first processed by a nonlinear diffusion filter to smooth vessels along their principal direction. The vessels are then enhanced using a compound vessel enhancement filter that combines the eigenvalues of the Hessian matrix, the response of matched filters, and edge constraints on multiple scales. The eigenvectors of the Hessian matrix provide the orientation of vessels and so only one matched filter is necessary at each pixel on a given scale. This makes the enhancement filter is more efficient compared with existing multiscale matched filters. Edge constraints are used to suppress the response of spurious boundary edges. Finally, the center lines of vessels are tracked from seeds obtained using multiple thresholds of the enhanced image. Evaluation of the enhancement filter and the segmentation is performed on the publicly available DRIVE database.

Regulated morphology approach to fuzzy shape analysis with application to blood vessel extraction in thoracic CT scans

Blood vessel segmentation in volumetric data is a necessary prerequisite in various medical imaging applications. Specifically, when considering the application of automatic lung nodule detection in thoracic CT scans, segmented blood vessels can be used in order to resolve local ambiguities based on global considerations and so improve the performance of lung nodule detection algorithms. In this paper, a novel regulated morphology approach to fuzzy shape analysis is described in the context of blood vessel extraction in thoracic CT scans. The fuzzy shape representation is obtained by using regulated morphological operations. Such a representation is necessary due to noise present in the data and due to the discrete nature of the volumetric data produced by CT scans, and particularly the interslice spacing. Regulated morphological operations are a generalization of ordinary morphological operations which relax the extreme strictness inherent to ordinary morphological operations. Based on constraints of collinearity, size, and global direction, a tracking algorithm produces a set of connected trees representing blood vessels and nodules in the volume. The produced tree structures are composed of fuzzy spheres in which the degree of object membership is proportional to the ratio between the occupied volume and the volume of the discrete sphere encompassing it. The performance of the blood vessel extraction algorithm described in the paper is evaluated based on a distance measure between a known blood vessel structure and a recovered one. As the generation of synthetic data for which the true vessel network is known may not be sufficiently realistic, our evaluation is based on different versions of real data corrupted by multiplicative Gaussian noise.

A HYBRID FILTERING APPROACH TO RETINAL VESSEL SEGMENTATION

We propose a novel vessel enhancement filter for retinal images. The filter can be used as a preprocessing step in applications such as vessel segmentation/visualization, and pathology detection. The proposed filter combines the eigenvalues of the Hessian matrix, the response of matched filters, and edge constraints on multiple scales. The eigenvectors of the Hessian matrix provide the orientation of vessels and so only one matched filter is necessary at each pixel in a given scale. This makes the proposed filter more efficient compared with existing multiscale matched filters. Edge constraints are used to suppress the response of spurious boundary edges. Experimental evaluation on the publicly available DRIVE dataset demonstrate improved performance of the proposed filter compared with known techniques.

Distributed multi-robot work load partition in manufacturing automation

This paper presents strategies for systematic ways to deploy multiple mobile robots for servicing large numbers of points of interest in a distributed fashion. The mobile robots in such systems are responsible for providing several essential services. For example, in manufacturing automation, the tasks could include parts inspection, parts changing and data collection, etc. The efficiency, responsiveness, and service life of the mobile robots depend on the balanced allocation of the entire work load to the individual robots. Starting from an initial random deployment of the robots, the proposed distributed load balancing algorithm computes the load share of each robot using virtual potential force method. The load imbalance is used as the virtual force to dynamically move the robots until a more balanced distribution is achieved. The total travelling cost to visit all the points of interest in a partition and the cost of servicing individual points are combined to compute the load in each partition. To verify the effectiveness of the proposed algorithms, we conducted simulations by applying them in inspection applications and obtained satisfactory results.

Rigidity guided localisation for mobile robotic sensor networks

This paper introduces a rigidity-guided localisation approach for mobile robotic sensor networks. The localisation uses a distance graph composed of both the robot-to-robot ranging data and the motion trajectories from robot odometry. The motion of a robot depends on the result of the rigidity test of its local distance graph: if the graph is not uniquely localisable, the robot moves around in its neighbourhood to collect at least two extra ranging data with each of its neighbours in order to make the extended graph uniquely localisable. Locally unique maps are then merged into a globally consistent map.