Wenjian Qin

An accurate and effective FMM-based approach for freehand 3D ultrasound reconstruction

Abstract Freehand three-dimensional ultrasound imaging is a highly attractive research area because it is capable of volumetric visualization and analysis of tissues and organs. The reconstruction algorithm plays a key role to the construction of three-dimensional ultrasound volume data with higher image quality and faster reconstruction speed. However, a systematic approach to such problem is still missing. A new fast marching method (FMM) for three-dimensional ultrasound volume reconstruction using the tracked and hand-held probe is proposed in this paper. Our reconstruction approach consists of two stages: bin-filling stage and hole-filling stage. Each pixel in the B-scan images is traversed and its intensity value is assigned to its nearest voxel in the bin-filling stage. For the efficient and accurate reconstruction, we present a new hole-filling algorithm based on the fast marching method. Our algorithm advances the interpolation boundary along its normal direction and fills the area closest to known voxel points in first, which ensure that the structural details of image can be preserved. Experimental results on both ultrasonic abdominal phantom and in vivo urinary bladder of human subject and comparisons with some popular algorithms are used to demonstrate its improvement in both reconstruction accuracy and efficiency.

A shape-optimized framework for kidney segmentation in ultrasound images using NLTV denoising and DRLSE

BackgroundComputer-assisted surgical navigation aims to provide surgeons with anatomical target localization and critical structure observation, where medical image processing methods such as segmentation, registration and visualization play a critical role. Percutaneous renal intervention plays an important role in several minimally-invasive surgeries of kidney, such as Percutaneous Nephrolithotomy (PCNL) and Radio-Frequency Ablation (RFA) of kidney tumors, which refers to a surgical procedure where access to a target inside the kidney by a needle puncture of the skin. Thus, kidney segmentation is a key step in developing any ultrasound-based computer-aided diagnosis systems for percutaneous renal intervention.MethodsIn this paper, we proposed a novel framework for kidney segmentation of ultrasound (US) images combined with nonlocal total variation (NLTV) image denoising, distance regularized level set evolution (DRLSE) and shape prior. Firstly, a denoised US image was obtained by NLTV image denoising. Secondly, DRLSE was applied in the kidney segmentation to get binary image. In this case, black and white region represented the kidney and the background respectively. The last stage is that the shape prior was applied to get a shape with the smooth boundary from the kidney shape space, which was used to optimize the segmentation result of the second step. The alignment model was used occasionally to enlarge the shape space in order to increase segmentation accuracy. Experimental results on both synthetic images and US data are given to demonstrate the effectiveness and accuracy of the proposed algorithm.ResultsWe applied our segmentation framework on synthetic and real US images to demonstrate the better segmentation results of our method. From the qualitative results, the experiment results show that the segmentation results are much closer to the manual segmentations. The sensitivity (SN), specificity (SP) and positive predictive value (PPV) of our segmentation result can reach 95%, 96% and 91% respectively; As well as we compared our results with the edge-based level set and level set with shape prior method by means of the same quantitative index, such as SN, SP, PPV, which have corresponding values of 97%, 88%, 78% and 81%, 91%, 80% respectively.ConclusionsWe have found NLTV denosing method is a good initial process for the ultrasound segmentation. This initial process can make us use simple segmentation method to get satisfied results. Furthermore, we can get the final segmentation results with smooth boundary by using the shape prior after the segmentation process. Every step enjoy simple energy model and every step in this framework is needed to keep a good robust and convergence property.

Reconstruction of freehand 3D ultrasound based on kernel regression

IntroductionFreehand three-dimensional (3D) ultrasound has the advantages of flexibility for allowing clinicians to manipulate the ultrasound probe over the examined body surface with less constraint in comparison with other scanning protocols. Thus it is widely used in clinical diagnose and image-guided surgery. However, as the data scanning of freehand–style is subjective, the collected B-scan images are usually irregular and highly sparse. One of the key procedures in freehand ultrasound imaging system is the volume reconstruction, which plays an important role in improving the reconstructed image quality.System and methodsA novel freehand 3D ultrasound volume reconstruction method based on kernel regression model is proposed in this paper. Our method consists of two steps: bin-filling and regression. Firstly, the bin-filling step is used to map each pixel in the sampled B-scan images to its corresponding voxel in the reconstructed volume data. Secondly, the regression step is used to make the nonparametric estimation for the whole volume data from the previous sampled sparse data. The kernel penalizes distance away from the current approximation center within a local neighborhood.Experiments and resultsTo evaluate the quality and performance of our proposed kernel regression algorithm for freehand 3D ultrasound reconstruction, a phantom and an in-vivo liver organ of human subject are scanned with our freehand 3D ultrasound imaging system. Root mean square error (RMSE) is used for the quantitative evaluation. Both of the qualitative and quantitative experimental results demonstrate that our method can reconstruct image with less artifacts and higher quality.ConclusionThe proposed kernel regression based reconstruction method is capable of constructing volume data with improved accuracy from irregularly sampled sparse data for freehand 3D ultrasound imaging system.

Segmentation of abdomen MR images using kernel graph cuts with shape priors

BackgroundAbdominal organs segmentation of magnetic resonance (MR) images is an important but challenging task in medical image processing. Especially for abdominal tissues or organs, such as liver and kidney, MR imaging is a very difficult task due to the fact that MR images are affected by intensity inhomogeneity, weak boundary, noise and the presence of similar objects close to each other.MethodIn this study, a novel method for tissue or organ segmentation in abdomen MR imaging is proposed; this method combines kernel graph cuts (KGC) with shape priors. First, the region growing algorithm and morphology operations are used to obtain the initial contour. Second, shape priors are obtained by training the shape templates, which were collected from different human subjects with kernel principle component analysis (KPCA) after the registration between all the shape templates and the initial contour. Finally, a new model is constructed by integrating the shape priors into the kernel graph cuts energy function. The entire process aims to obtain an accurate image segmentation.ResultsThe proposed segmentation method has been applied to abdominal organs MR images. The results showed that a satisfying segmentation without boundary leakage and segmentation incorrect can be obtained also in presence of similar tissues. Quantitative experiments were conducted for comparing the proposed segmentation with other three methods: DRLSE, initial erosion contour and KGC without shape priors. The comparison is based on two quantitative performance measurements: the probabilistic rand index (PRI) and the variation of information (VoI). The proposed method has the highest PRI value (0.9912, 0.9983 and 0.9980 for liver, right kidney and left kidney respectively) and the lowest VoI values (1.6193, 0.3205 and 0.3217 for liver, right kidney and left kidney respectively).ConclusionThe proposed method can overcome boundary leakage. Moreover it can segment liver and kidneys in abdominal MR images without segmentation errors due to the presence of similar tissues. The shape priors based on KPCA was integrated into fully automatic graph cuts algorithm (KGC) to make the segmentation algorithm become more robust and accurate. Furthermore, if a shelter is placed onto the target boundary, the proposed method can still obtain satisfying segmentation results.

An Approach to Biometric Verification Based on Human Body Communication in Wearable Devices

In this paper, an approach to biometric verification based on human body communication (HBC) is presented for wearable devices. For this purpose, the transmission gain S21 of volunteer’s forearm is measured by vector network analyzer (VNA). Specifically, in order to determine the chosen frequency for biometric verification, 1800 groups of data are acquired from 10 volunteers in the frequency range 0.3 MHz to 1500 MHz, and each group includes 1601 sample data. In addition, to achieve the rapid verification, 30 groups of data for each volunteer are acquired at the chosen frequency, and each group contains only 21 sample data. Furthermore, a threshold-adaptive template matching (TATM) algorithm based on weighted Euclidean distance is proposed for rapid verification in this work. The results indicate that the chosen frequency for biometric verification is from 650 MHz to 750 MHz. The false acceptance rate (FAR) and false rejection rate (FRR) based on TATM are approximately 5.79% and 6.74%, respectively. In contrast, the FAR and FRR were 4.17% and 37.5%, 3.37% and 33.33%, and 3.80% and 34.17% using K-nearest neighbor (KNN) classification, support vector machines (SVM), and naive Bayesian method (NBM) classification, respectively. In addition, the running time of TATM is 0.019 s, whereas the running times of KNN, SVM and NBM are 0.310 s, 0.0385 s, and 0.168 s, respectively. Therefore, TATM is suggested to be appropriate for rapid verification use in wearable devices.

Nonlocal Total-Variation–Based Speckle Filtering for Ultrasound Images

Ultrasound is one of the most important medical imaging modalities for its real-time and portable imaging advantages. However, the contrast resolution and important details are degraded by the speckle in ultrasound images. Many speckle filtering methods have been developed, but they are suffered from several limitations, difficult to reach a balance between speckle reduction and edge preservation. In this paper, an adaptation of the nonlocal total variation (NLTV) filter is proposed for speckle reduction in ultrasound images. The speckle is modeled via a signal-dependent noise distribution for the log-compressed ultrasound images. Instead of the Euclidian distance, the statistical Pearson distance is introduced in this study for the similarity calculation between image patches via the Bayesian framework. And the Split-Bregman fast algorithm is used to solve the adapted NLTV despeckling functional. Experimental results on synthetic and clinical ultrasound images and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both speckle noise reduction and tissue boundary preservation for ultrasound images.

Freehand 3D ultrasound reconstruction for image-guided surgery

Three-dimensional (3D) ultrasound (US) is increasingly being introduced in the clinic, both for diagnostics and image guidance. Obtaining 3D volumes with 2D US probes is a two-step process. First, a positioning sensor must be attached to the probe; second, a reconstruction of a 3D volume can be performed into a regular voxel grid. Various algorithms have been used for performing 3D reconstruction based on 2D images. In this paper, we propose a new Hole-filling algorithm using Distance Weight interpolation, and we also apply it to generate the volume in our Image-guided for surgical robot. First, the ultrasound frames and position information are compounded into a 3D volume using the Bin-filling method. Then, the Hole-filling method is used to repair gaps in the volume. We define the empty voxels by sorting the neighboring voxels into three parts, and averaging them to obtain the value to fill the empty voxels according to distance weighted. The empty voxel estimation can be improved by thresholding the range width of its neighboring voxels and adjusting it to the average values. The method is tested on a Hole-manipulated volume derived from a cropped 3D ultrasound volume of chicken kidney. Our method shows improved result compared to several tested existing methods, including voxel nearest neighbour(VNN) and spline function interpolation.

Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation

Segmentation of liver in abdominal computed tomography (CT) is an important step for radiation therapy planning of hepatocellular carcinoma. Practically, a fully automatic segmentation of liver remains challenging because of low soft tissue contrast between liver and its surrounding organs, and its highly deformable shape. The purpose of this work is to develop a novel superpixel-based and boundary sensitive convolutional neural network (SBBS-CNN) pipeline for automated liver segmentation. The entire CT images were first partitioned into superpixel regions, where nearby pixels with similar CT number were aggregated. Secondly, we converted the conventional binary segmentation into a multinomial classification by labeling the superpixels into three classes: interior liver, liver boundary, and non-liver background. By doing this, the boundary region of the liver was explicitly identified and highlighted for the subsequent classification. Thirdly, we computed an entropy-based saliency map for each CT volume, and leveraged this map to guide the sampling of image patches over the superpixels. In this way, more patches were extracted from informative regions (e.g. the liver boundary with irregular changes) and fewer patches were extracted from homogeneous regions. Finally, deep CNN pipeline was built and trained to predict the probability map of the liver boundary. We tested the proposed algorithm in a cohort of 100 patients. With 10-fold cross validation, the SBBS-CNN achieved mean Dice similarity coefficients of 97.31  ±  0.36% and average symmetric surface distance of 1.77  ±  0.49 mm. Moreover, it showed superior performance in comparison with state-of-art methods, including U-Net, pixel-based CNN, active contour, level-sets and graph-cut algorithms. SBBS-CNN provides an accurate and effective tool for automated liver segmentation. It is also envisioned that the proposed framework is directly applicable in other medical image segmentation scenarios.

Multiscale Geometric Active Contour Model and Boundary Extraction in Kidney MR Images

Active contour methods (ACM) are model-based approaches for image segmentation and were developed in the late 1980s. ACM can be divided into two classes: parametric active contour model and geometric active contour model. Geometric method is intrinsic model. Because of its completeness in mathematics, geometric active contour model overcomes many difficulties of the parametric active contour model. However, in medical images with heavy structural noise, the evolution of the geometric active contour will be seriously affected. To handle this problem, this paper proposed a multiscale geometric active contour model, based on the multiscale analysis method—bidimensional empirical mode decomposition. In the human kidney MR images, the proposed multiscale geometric active contour model successfully extracts the complex kidney contour.

GPU-accelerated Kernel Regression Reconstruction for Freehand 3D Ultrasound Imaging:

Volume reconstruction method plays an important role in improving reconstructed volumetric image quality for freehand three-dimensional (3D) ultrasound imaging. By utilizing the capability of programmable graphics processing unit (GPU), we can achieve a real-time incremental volume reconstruction at a speed of 25-50 frames per second (fps). After incremental reconstruction and visualization, hole-filling is performed on GPU to fill remaining empty voxels. However, traditional pixel nearest neighbor–based hole-filling fails to reconstruct volume with high image quality. On the contrary, the kernel regression provides an accurate volume reconstruction method for 3D ultrasound imaging but with the cost of heavy computational complexity. In this paper, a GPU-based fast kernel regression method is proposed for high-quality volume after the incremental reconstruction of freehand ultrasound. The experimental results show that improved image quality for speckle reduction and details preservation can be obtained with the parameter setting of kernel window size of 5 × 5 × 5 and kernel bandwidth of 1.0. The computational performance of the proposed GPU-based method can be over 200 times faster than that on central processing unit (CPU), and the volume with size of 50 million voxels in our experiment can be reconstructed within 10 seconds.