Stephen K. Y. Chang

Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation

The performance of the level set segmentation is subject to appropriate initialization and optimal configuration of controlling parameters, which require substantial manual intervention. A new fuzzy level set algorithm is proposed in this paper to facilitate medical image segmentation. It is able to directly evolve from the initial segmentation by spatial fuzzy clustering. The controlling parameters of level set evolution are also estimated from the results of fuzzy clustering. Moreover the fuzzy level set algorithm is enhanced with locally regularized evolution. Such improvements facilitate level set manipulation and lead to more robust segmentation. Performance evaluation of the proposed algorithm was carried on medical images from different modalities. The results confirm its effectiveness for medical image segmentation.

A new unified level set method for semi-automatic liver tumor segmentation on contrast-enhanced CT images

Highlights? Computerized liver tumor segmentation is a challenging issue. ? Segmentation confronts great variations of shape, intensity and contrast-enhancement. ? Common level set models are not robust for contrast-enhanced liver tumor segmentation. ? We propose a level set model to unify image gradient, region competition and prior knowledge. ObjectiveComputerized liver tumor segmentation on computed tomography (CT) images is a challenging problem. Level set methods have been proposed for CT liver and tumor segmentation. However, the common models using image gradient or region competition have inherent drawbacks, and are not very robust for liver tumor segmentation. MethodsWe propose a new unified level set model to integrate image gradient, region competition and prior information for CT liver tumor segmentation. The probabilistic distribution of liver tumors is estimated by unsupervised fuzzy clustering, and is utilized to enhance the object indication function, define the directional balloon force and regulate region competition. This unified model has been evaluated on 25 two-dimensional (2D) CT scans and 4 three-dimensional (3D) CT scans with 10 tumors. ResultsFor the 2D dataset, the area overlapping error (AOE) is 12.75?5.76%, the relative area difference (RAD) is -4.28?9.58%, the average contour distance (ACD) is 1.66?1.09mm, and the maximum contour distance (MCD) is 4.29?2.75mm. For the 3D dataset, the volume overlapping error (VOE) is 26.31?5.79%, the relative volume difference (RVD) is -10.64?7.55%, the average surface distance (ASD) is 1.06?0.38mm, and the maximum surface distance (MSD) is 8.66?3.17mm. All results are competitive with that of the state-of-the-art methods. ConclusionThe new unified level set model is an effective solution for liver tumor segmentation on contrast-enhanced CT images.

Single-port laparoscopic spleen preserving distal pancreatectomy.

Single-port laparoscopic surgery has become increasingly popular, with widened indication to more types of surgery. This report will present our initial experience with spleen-preserving distal pancreatectomy technique through a small transumbilical incision using the single-port approach for a cystic tumor of pancreatic body. The surgery was done using specialized single-port instruments and normal laparoscopic instruments. The total operative time for this surgery is 233 minutes, and it was completed without drains. Patient was discharged from the hospital on the third day postoperatively in good condition.

Integrating FCM and Level Sets for Liver Tumor Segmentation

Liver and liver tumor segmentations are very important for a contemporary planning system of liver surgery. However, both liver and liver tumor segmentations are a grand challenge in clinics. In this paper, we proposed an integrated paradigm with fuzzy c-means (FCM) and level set method for computerized liver tumor segmentation. An innovation in this paper is to interface the initial segmentations from FCM and the fine delineation with level set method by morphological operations. The results in real medical images confirm the effectiveness of such integrated paradigm for liver tumor segmentation.

Modeling shear modulus distribution in magnetic resonance elastography with piecewise constant level sets

Magnetic resonance elastography (MRE) is designed for imaging the mechanical properties of soft tissues. However, the interpretation of shear modulus distribution is often confusing and cumbersome. For reliable evaluation, a common practice is to specify the regions of interest and consider regional elasticity. Such an experience-dependent protocol is susceptible to intrapersonal and interpersonal variability. In this study we propose to remodel shear modulus distribution with piecewise constant level sets by referring to the corresponding magnitude image. Optimal segmentation and registration are achieved by a new hybrid level set model comprised of alternating global and local region competitions. Experimental results on the simulated MRE data sets show that the mean error of elasticity reconstruction is 11.33% for local frequency estimation and 18.87% for algebraic inversion of differential equation. Piecewise constant level set modeling is effective to improve the quality of shear modulus distribution, and facilitates MRE analysis and interpretation.

Volume Preserved Mass–Spring Model with Novel Constraints for Soft Tissue Deformation

An interactive surgical simulation system needs to meet three main requirements, speed, accuracy, and stability. In this paper, we present a stable and accurate method for animating mass-spring systems in real time. An integration scheme derived from explicit integration is used to obtain interactive realistic animation for a multiobject environment. We explore a predictor- corrector approach by correcting the estimation of the explicit integration in a poststep process. We introduce novel constraints on positions into the mass-spring model (MSM) to model the nonlinearity and preserve volume for the realistic simulation of the incompressibility. We verify the proposed MSM by comparing its deformations with the reference deformations of the nonlinear finite-element method. Moreover, experiments on porcine organs are designed for the evaluation of the multiobject deformation. Using a pair of freshly harvested porcine liver and gallbladder, the real organ deformations are acquired by computed tomography and used as the reference ground truth. Compared to the porcine model, our model achieves a 1.502 mm mean absolute error measured at landmark locations for cases with small deformation (the largest deformation is 49.109 mm) and a 3.639 mm mean absolute error for cases with large deformation (the largest deformation is 83.137 mm). The changes of volume for the two deformations are limited to 0.030% and 0.057%, respectively. Finally, an implementation in a virtual reality environment for laparoscopic cholecystectomy demonstrates that our model is capable to simulate large deformation and preserve volume in real-time calculations.

Physiological analysis on oscillatory behavior of glucose-insulin regulation by model with delays.

In artificial pancreas, glucose level measurement and insulin infusion are often implemented in the subcutaneous tissues. Understanding the dynamics of glucose and insulin in the subcutaneous tissues is important in the regulation of blood glucose level. We propose a new two-compartmental model of glucose-insulin interaction with two explicit delays that can study the interaction of glucose in different organs and the oscillatory behavior of the glucose-insulin system. The glucose and insulin space are split into plasma compartment and interstitial fluids compartment, respectively. The four m parameters of insulin dynamics and the two delays are analyzed for their influence on the glucose-insulin regulatory system. The ranges of the six parameters are estimated for sustaining the oscillation of glucose and insulin, and ranges for different subjects are discussed based on simulation results. The effect of these parameters on the oscillatory system is related to diseases and irregular blood glucose level. The lag between glucose and insulin in the two compartments has provided an insight on the distribution and metabolism of glucose and insulin in quick- and slow-equilibrating organs and tissues. We have reported in this paper, a model that can effectively deal with concentration of glucose and insulin in the interstitial compartment. This is important for the development of artificial pancreas.

Quasi-linear viscoelastic modeling of arterial wall for surgical simulation

PurposeRealistic soft tissue deformation modeling and haptic rendering for surgical simulation require accurate knowledge of tissue material characteristics. Biomechanical experiments on porcine tissue were performed, and a reduced quasi-linear viscoelastic model was developed to describe the strain-dependent relaxation behavior of the arterial wall. This information is used in surgical simulation to provide a realistic sensation of reduction in strength when the user holds a virtual blood vessel strained at different levels.Materials and methodsTwelve pieces of porcine abdominal artery were tested with uniaxial elongation and relaxation test in both circumferential and longitudinal directions. The mechanical property testing system consists of automated environment control, testing, and data collection mechanism. A combined logarithm and polynomial strain energy equation was applied to model the elastic response of the specimens. The reduced relaxation function was modified by integrating a rational equation as a corrective factor to precisely describe the strain-dependent relaxation effects.ResultsThe experiments revealed that (1) stress is insensitive to strain rate in arterial tissue when the loading rate is low, and (2) the rate of stress relaxation of arterial wall is highly strain dependent. The proposed model can accurately represent the experimental data. Stress–strain function derived from the combined strain energy function is able to fit the tensile experimental data with R2 equals to 0.9995 in circumferential direction and 0.999 in longitudinal direction. Modified reduced relaxation function is able to model the strain-dependent relaxation with R2 equals to 0.9686 in circumferential direction and 0.988 in longitudinal direction.ConclusionThe proposed model, based on extensive biomechanical experiments, can be used for accurate simulation of arterial deformation and haptic rendering in surgical simulation. The resultant model enables stress relaxation status to be determined when subjected to different strain levels.

A semi-automatic approach to the segmentation of liver parenchyma from 3D CT images with Extreme Learning Machine

This paper presents a semi-automatic approach to segmentation of liver parenchyma from 3D computed tomography (CT) images. Specifically, liver segmentation is formalized as a pattern recognition problem, where a given voxel is to be assigned a correct label - either in a liver or a non-liver class. Each voxel is associated with a feature vector that describes image textures. Based on the generated features, an Extreme Learning Machine (ELM) classifier is employed to perform the voxel classification. Since preliminary voxel segmentation tends to be less accurate at the boundary, and there are other non-liver tissue voxels with similar texture characteristics as liver parenchyma, morphological smoothing and 3D level set refinement are applied to enhance the accuracy of segmentation. Our approach is validated on a set of CT data. The experiment shows that the proposed approach with ELM has the reasonably good performance for liver parenchyma segmentation. It demonstrates a comparable result in accuracy of classification but with a much faster training and classification speed compared with support vector machine (SVM).

Mechanism of a Learning Robot Manipulator for Laparoscopic Surgical Training

This paper presents a robot manipulator for hand-over-hand guidance training of laparoscopic surgery. Details of the mechanical design, kinematic analysis and control mechanism of the robot are presented. The robot records motion of surgical tool manipulated by master surgeon, and provides physical guidance to the trainee based on the recorded motion. The robotic manipulator can accurately reproduce the five degree of freedom manipulation of laparoscopic instrument during surgery. A hybrid spherical mechanism is applied for decoupling and reproducing the motion of surgical tool to facilitate implementation of control mechanism. The manipulators for left and right hands are capable of precise execution of a recorded trajectory with observed maximum error of 2.12 mm and 2 mm respectively during an experiment on user interaction.