Binh P. Nguyen

Hand gesture guided robot-assisted surgery based on a direct augmented reality interface

Radiofrequency (RF) ablation is a good alternative to hepatic resection for treatment of liver tumors. However, accurate needle insertion requires precise hand-eye coordination and is also affected by the difficulty of RF needle navigation. This paper proposes a cooperative surgical robot system, guided by hand gestures and supported by an augmented reality (AR)-based surgical field, for robot-assisted percutaneous treatment. It establishes a robot-assisted natural AR guidance mechanism that incorporates the advantages of the following three aspects: AR visual guidance information, surgeons experiences and accuracy of robotic surgery. A projector-based AR environment is directly overlaid on a patient to display preoperative and intraoperative information, while a mobile surgical robot system implements specified RF needle insertion plans. Natural hand gestures are used as an intuitive and robust method to interact with both the AR system and surgical robot. The proposed system was evaluated on a mannequin model. Experimental results demonstrated that hand gesture guidance was able to effectively guide the surgical robot, and the robot-assisted implementation was found to improve the accuracy of needle insertion. This human-robot cooperative mechanism is a promising approach for precise transcutaneous ablation therapy.

A clustering-based system to automate transfer function design for medical image visualization

Finding good transfer functions for rendering medical volumes is difficult, non-intuitive, and time-consuming. We introduce a clustering-based framework for the automatic generation of transfer functions for volumetric data. The system first applies mean shift clustering to oversegment the volume boundaries according to their low-high (LH) values and their spatial coordinates, and then uses hierarchical clustering to group similar voxels. A transfer function is then automatically generated for each cluster such that the number of occlusions is reduced. The framework also allows for semi-automatic operation, where the user can vary the hierarchical clustering results or the transfer functions generated. The system improves the efficiency and effectiveness of visualizing medical images and is suitable for medical imaging applications.

Particle-based simulation of blood flow and vessel wall interactions in virtual surgery

We propose a particle-based solution to simulate the interactions between blood flow and vessel wall for virtual surgery. By coupling two particle-based techniques, the smoothed particle hydrodynamics (SPH) and mass-spring model (MSM), we can simulate the blood flow and deformation of vessel seamlessly. At the vessel wall, particles are considered as both boundary particles for SPH solver and mass points for the MSM solver. We implement an improved repulsive boundary condition to simulate the interactions. The computation of blood flow dynamics and vessel wall deformations are performed in an alternating fashion in every time step. To ensure realism, parameters of both SPH and MSM are carefully configured. Experimental results demonstrate the potential of the proposed method in providing real-time and realistic interactions for virtual vascular surgery systems.

Automatic transfer function design for medical visualization using visibility distributions and projective color mapping.

Transfer functions play a key role in volume rendering of medical data, but transfer function manipulation is unintuitive and can be time-consuming; achieving an optimal visualization of patient anatomy or pathology is difficult. To overcome this problem, we present a system for automatic transfer function design based on visibility distribution and projective color mapping. Instead of assigning opacity directly based on voxel intensity and gradient magnitude, the opacity transfer function is automatically derived by matching the observed visibility distribution to a target visibility distribution. An automatic color assignment scheme based on projective mapping is proposed to assign colors that allow for the visual discrimination of different structures, while also reflecting the degree of similarity between them. When our method was tested on several medical volumetric datasets, the key structures within the volume were clearly visualized with minimal user intervention.

An efficient compression scheme for 4-D medical images using hierarchical vector quantization and motion compensation

This paper proposes an efficient compression scheme for compressing time-varying medical volumetric data. The scheme uses 3-D motion estimation to create a homogenous preprocessed data to be compressed by a 3-D image compression algorithm using hierarchical vector quantization. A new block distortion measure, called variance of residual (VOR), and three 3-D fast block matching algorithms are used to improve the motion estimation process in term of speed and data fidelity. The 3-D image compression process involves the application of two different encoding techniques based on the homogeneity of input data. Our method can achieve a higher fidelity and faster decompression time compared to other lossy compression methods producing similar compression ratios. The combination of 3-D motion estimation using VOR and hierarchical vector quantization contributes to the good performance.

Robust Biometric Recognition From Palm Depth Images for Gloved Hands

Biometric recognition can be used to improve gesture-based interfaces by automatically identifying operators. Traditional palm biometric recognition techniques depend on palm appearance features, but these features are not available in an operating theater where gloves are worn. We propose a depth-based solution for palm biometric recognition. Based on the depth image, our system automatically segments the users palm and extracts finger dimensions. The finger dimensions are further scaled according to the sensed depth to obtain the true finger dimensions, which are then used as features to characterize the palm. Finally, a modified k-nearest neighbors algorithm that assigns class labels based on the centroid displacement of each class in the neighboring points is applied to recognize the palm based on the geometric features. An accuracy of 96.24% was achieved for the biometric recognition of 4057 gloved palm samples captured at different angles and depths from 27 users. This accuracy is comparable with those of other state-of-the-art classification algorithms and demonstrates that biometric recognition may be viable for settings with gloved hands such as surgery.

Automated brain tumor segmentation using kernel dictionary learning and superpixel-level features

Brain tumor segmentation, an essential but challenging task, has long attracted much attention from the medical imaging community. Recently, successful applications of sparse coding and dictionary learning has emerged in various vision problems including image segmentation. In this paper, a superpixel-based framework for automated brain tumor segmentation is introduced. The kernel trick is adopted in dictionary learning to transform superpixel-level features to a high-dimensional feature space where their nonlinear similarities are considered to generate discriminative sparse codes. A graph is constructed from the approximation errors given by dictionaries modeling different brain tumor structures so that superpixels belonging to particular tumor regions can be efficiently identified. The proposed framework is evaluated on brain magnetic resonance images of high-grade glioma (HGG) patients provided by the multi-modal Brain Tumor Segmentation (BRATS) Benchmark. Results show that the proposed framework achieves competitive performance when compared with the state-of-the-art methods.

Embedded Real-Time Model Predictive Control for Glucose Regulation

This paper reports our investigation on a model predictive control (MPC) with constraints for continuous diabetes management, and its implementation on the microcontroller of our artificial pancreas. The operational constraints for the MPC are rate of change, amplitude and output constraints, while the associated optimization problem is solved using a primal-dual interior-point algorithm based on predicator-corrector method. Our real-time implantable close-loop system is able to achieve desired diabetes management by maintaining the blood sugar level at less than 140 mg/dl, and consistently within the range of 70–120 mg/dl. Experimental results demonstrate that the low power 16-bit microcontroller in our prototype artificial pancreas can provide sufficient computational power with our computational efficient embedded system solution.

Reworking Multilabel Brain Tumor Segmentation: An Automated Framework Using Structured Kernel Sparse Representation

Advances in the field over the years have made medical imaging an indispensable part of medicine. Today, the use of medical images is often critical for diagnosis and treatment planning. The efficient processing and analysis of the large imaging data sets that have accompanied the rise in popularity of medical imaging have presented significant challenges that have yet to be successfully overcome. Medical image analysis and volume visualization are topics that attract much attention from the image-processing community. The former extracts useful knowledge for specific purposes, such as tumor segmentation, while the latter creates vivid two-dimensional representations of three-dimensional volumetric data. Our research projects have focused on the sparse and compressible properties of signals in some representation systems with the general objective of fully utilizing these properties for the development of effective and efficient algorithms for medical image analysis and volume visualization. In this article, we introduce one of our research projects, which aims to address the significant but challenging task of multilabel brain tumor segmentation. In this work, we proposed a superpixel-based framework for this specific task using structured kernel sparse representation.

Superpixel-based segmentation of muscle fibers in multi-channel microscopy

BackgroundConfetti fluorescence and other multi-color genetic labelling strategies are useful for observing stem cell regeneration and for other problems of cell lineage tracing. One difficulty of such strategies is segmenting the cell boundaries, which is a very different problem from segmenting color images from the real world. This paper addresses the difficulties and presents a superpixel-based framework for segmentation of regenerated muscle fibers in mice.ResultsWe propose to integrate an edge detector into a superpixel algorithm and customize the method for multi-channel images. The enhanced superpixel method outperforms the original and another advanced superpixel algorithm in terms of both boundary recall and under-segmentation error. Our framework was applied to cross-section and lateral section images of regenerated muscle fibers from confetti-fluorescent mice. Compared with “ground-truth” segmentations, our framework yielded median Dice similarity coefficients of 0.92 and higher.ConclusionOur segmentation framework is flexible and provides very good segmentations of multi-color muscle fibers. We anticipate our methods will be useful for segmenting a variety of tissues in confetti fluorecent mice and in mice with similar multi-color labels.