PixelTopoIS: a pixel-topology-coupled guidewire tip segmentation framework for robot-assisted intervention.

PURPOSE: Existing works showed great performance in pixel-level guidewire segmentation. However, topology-level segmentation has not been fully exploited in these works. Guidewire (tip) endpoint localization and (guidewire) loop detection are typical topology-level guidewire segmentation tasks. A superb guidewire segmentation algorithm should achieve both low endpoint localization error and high loop detection accuracy. METHODS: This paper focuses on pixel-topology-coupled guidewire (tip) segmentation. The contributions are (1) two algorithmic improvements including an iterative segmentation framework and a pixel-topology-coupled loss function (2) a new metric that comprehensively evaluates the segmentation results at both pixel and topology level (3) the first publicly available guidewire dataset (The dataset can be downloaded from www.njzdyyrobocgsu.com ) containing 4500+ X-ray images with radiologist-annotated results. RESULTS: The algorithm rivals the state-of-the-art methods in pixel-level metric (0.06-4.21% for the F1-score) in most sequences, achieving performance comparable to the best method on two sequences. Our method also shows competitive performance (20% for the loop existence accuracy) on the newly introduced metric. Experiments are also performed to quantitatively validate the functionality of different components in our framework. CONCLUSION: The framework is effective in segmenting the guidewire by considering pixel and topology equally, providing an accurate position of the tip's endpoint (pixel-level) to the surgeon/robot and preserving the clinically meaningful guidewire structure (topology-level) simultaneously.

A novel multi-DoF surgical robotic system for brachytherapy on liver tumor: Design and control.

PURPOSE: Radioactive seed implantation is an effective invasive treatment method for malignant liver tumors in hepatocellular carcinomas. However, challenges of the manual procedure may degrade the efficacy of the technique, such as the high accuracy requirement and radiation exposure to the surgeons. This paper aims to develop a robotic system and its control methods for assisting surgeons on the treatment. METHOD: We present an interventional robotic system, which consists of a 5 Degree-of-Freedom (DoF) positioning robotic arm (a 3-DoF translational joint and a 2-DoF revolute joint) and a needle actuator used for needle insertion and radioactive seeds implantation. Control strategy is designed for the system to ensure the safety of the motion. In the designed framework, an artificial potential field (APF)-based motion planning and an ultrasound (US) image-based contacting methods are proposed for the control. RESULT: Experiments were performed to evaluate position and orientation accuracy as well as validate the motion planning procedure of the system. The mean and standard deviation of targeting error is 0.69 mm and 0.33 mm, respectively. Needle placement accuracy is 1.10 mm by mean. The feasibility of the control strategy, including path planning and the contacting methods, is demonstrated by simulation and experiments based on an abdominal phantom. CONCLUSION: This paper presents a robotic system with force and US image feedback in assisting surgeons performing brachytherapy on liver tumors. The proposed robotic system is capable of executing an accurate needle insertion task with by optical tracking. The proposed methods improve the safety of the robot's motion and automate the process of US probe contacting under the feedback of US-image.

A Sparse Volume Reconstruction Method for Fetal Brain MRI Using Adaptive Kernel Regression.

Slice-to-volume reconstruction (SVR) method can deal well with motion artifacts and provide high-quality 3D image data for fetal brain MRI. However, the problem of sparse sampling is not well addressed in the SVR method. In this paper, we mainly focus on the sparse volume reconstruction of fetal brain MRI from multiple stacks corrupted with motion artifacts. Based on the SVR framework, our approach includes the slice-to-volume 2D/3D registration, the point spread function- (PSF-) based volume update, and the adaptive kernel regression-based volume update. The adaptive kernel regression can deal well with the sparse sampling data and enhance the detailed preservation by capturing the local structure through covariance matrix. Experimental results performed on clinical data show that kernel regression results in statistical improvement of image quality for sparse sampling data with the parameter setting of the structure sensitivity 0.4, the steering kernel size of 7 × 7 × 7 and steering smoothing bandwidth of 0.5. The computational performance of the proposed GPU-based method can be over 90 times faster than that on CPU.

A Novel Ultrasound Probe Spatial Calibration Method Using a Combined Phantom and Stylus.

Intra-operative ultrasound (US) is a popular imaging modality for its non-radiative and real-time advantages. However, it is still challenging to perform an interventional procedure under two-dimensional (2-D) US image guidance. Accordingly, the trend has been to perform three-dimensional (3-D) US image guidance by equipping the US probe with a spatial position tracking device, which requires accurate probe calibration for determining the spatial position between the B-scan image and the tracked probe. In this report, we propose a novel probe spatial calibration method by developing a calibration phantom combined with the tracking stylus. The calibration phantom is custom-designed to simplify the alignment between the stylus tip and the B-scan image plane. The spatial position of the stylus tip is tracked in real time, and its 2-D image pixel location is extracted and collected simultaneously. Gaussian distribution is used to model the spatial position of the stylus tip and the iterative closest point-based optimization algorithm is used to estimate the spatial transformation that matches these two point sets. Once the probe is calibrated, its trajectory and the B-scan image are collected and used for the volume reconstruction in our freehand 3-D US imaging system. Experimental results demonstrate that the probe calibration approach results in less than 1-mm mean point reconstruction accuracy. It requires less than 5 min for an inexperienced user to complete the probe calibration procedure with minimal training. The mockup test shows that the 3-D images are geometrically correct with 0.28°-angle accuracy and 0.40-mm distance accuracy.

MutScan: fast detection and visualization of target mutations by scanning FASTQ data.

BACKGROUND: Some types of clinical genetic tests, such as cancer testing using circulating tumor DNA (ctDNA), require sensitive detection of known target mutations. However, conventional next-generation sequencing (NGS) data analysis pipelines typically involve different steps of filtering, which may cause miss-detection of key mutations with low frequencies. Variant validation is also indicated for key mutations detected by bioinformatics pipelines. Typically, this process can be executed using alignment visualization tools such as IGV or GenomeBrowse. However, these tools are too heavy and therefore unsuitable for validating mutations in ultra-deep sequencing data. RESULT: We developed MutScan to address problems of sensitive detection and efficient validation for target mutations. MutScan involves highly optimized string-searching algorithms, which can scan input FASTQ files to grab all reads that support target mutations. The collected supporting reads for each target mutation will be piled up and visualized using web technologies such as HTML and JavaScript. Algorithms such as rolling hash and bloom filter are applied to accelerate scanning and make MutScan applicable to detect or visualize target mutations in a very fast way. CONCLUSION: MutScan is a tool for the detection and visualization of target mutations by only scanning FASTQ raw data directly. Compared to conventional pipelines, this offers a very high performance, executing about 20 times faster, and offering maximal sensitivity since it can grab mutations with even one single supporting read. MutScan visualizes detected mutations by generating interactive pile-ups using web technologies. These can serve to validate target mutations, thus avoiding false positives. Furthermore, MutScan can visualize all mutation records in a VCF file to HTML pages for cloud-friendly VCF validation. MutScan is an open source tool available at GitHub: https://github.com/OpenGene/MutScan.

Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images.

Due to the low contrast and ambiguous boundaries of the tumors in breast ultrasound (BUS) images, it is still a challenging task to automatically segment the breast tumors from the ultrasound. In this paper, we proposed a novel computational framework that can detect and segment breast lesions fully automatic in the whole ultrasound images. This framework includes several key components: pre-processing, contour initialization, and tumor segmentation. In the pre-processing step, we applied non-local low-rank (NLLR) filter to reduce the speckle noise. In contour initialization step, we cascaded a two-step Otsu-based adaptive thresholding (OBAT) algorithm with morphologic operations to effectively locate the tumor regions and initialize the tumor contours. Finally, given the initial tumor contours, the improved Chan-Vese model based on the ratio of exponentially weighted averages (CV-ROEWA) method was utilized. This pipeline was tested on a set of 61 breast ultrasound (BUS) images with diagnosed tumors. The experimental results in clinical ultrasound images prove the high accuracy and robustness of the proposed framework, indicating its potential applications in clinical practice. Graphical abstract ᅟ.

Nonlocal total variation based on symmetric Kullback-Leibler divergence for the ultrasound image despeckling.

BACKGROUND: Ultrasound imaging is safer than other imaging modalities, because it is noninvasive and nonradiative. Speckle noise degrades the quality of ultrasound images and has negative effects on visual perception and diagnostic operations. METHODS: In this paper, a nonlocal total variation (NLTV) method for ultrasonic speckle reduction is proposed. A spatiogram similarity measurement is introduced for the similarity calculation between image patches. It is based on symmetric Kullback-Leibler (KL) divergence and signal-dependent speckle model for log-compressed ultrasound images. Each patch is regarded as a spatiogram, and the spatial distribution of each bin of the spatiogram is regarded as a weighted Gamma distribution. The similarity between the corresponding bins of the two spatiograms is computed by the symmetric KL divergence. The Split-Bregman fast algorithm is then used to solve the adapted NLTV object function. Kolmogorov-Smirnov (KS) test is performed on synthetic noisy images and real ultrasound images. RESULTS: We validate our method on synthetic noisy images and clinical ultrasound images. Three measures are adopted for the quantitative evaluation of the despeckling performance: the signal-to-noise ratio (SNR), structural similarity index (SSIM), and natural image quality evaluator (NIQE). For synthetic noisy images, when the noise level increases, the proposed algorithm achieves slightly higher SNRS than that of the other two algorithms, and the SSIMS yielded by the proposed algorithm is obviously higher than that of the other two algorithms. For liver, IVUS and 3DUS images, the NIQE values are 8.25, 6.42 and 9.01, all of which are higher than that of the other two algorithms. CONCLUSIONS: The results of the experiments over synthetic and real ultrasound images demonstrate that the proposed method outperforms current state-of-the-art despeckling methods with respect to speckle reduction and tissue texture preservation.

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 [Formula: see text] 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.

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.

Reconstruction of freehand 3D ultrasound based on kernel regression.

INTRODUCTION: Freehand 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 METHODS: A 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 RESULTS: To 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. CONCLUSION: The 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.

BACKGROUND: Abdominal 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. METHOD: In 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. RESULTS: The 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). CONCLUSION: The 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.

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

BACKGROUND: Computer-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. METHODS: In 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. RESULTS: We 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. CONCLUSIONS: We 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.

An acceleration-based control framework for interactive gaming.

In this paper we presented a 3-D acceleration-based interactive framework using Body Sensor Networks (BSN) for real-time game controls. The framework consists of three modules: a wireless signal acquisition module that senses the accelerations of body movements, a signal processing module that uses the Kalman filter to rectify the contaminated acceleration data, and a control module that makes interactive gaming strategies. Our framework enables a wearable gaming control solution that differs from the conventional methods using joysticks, key boards or mice. The framework was implemented on a racing-type game. The results suggested that our framework was fully functioning. It was capable of combining moderate physical exercises with the computer game, at the meantime brought in more funs and motivations to exercises.