Verification of cascade optical coherence tomography for freeform optics form metrology.

Freeform optical components enable dramatic advances for optical systems in both performance and packaging. Surface form metrology of manufactured freeform optics remains a challenge and an active area of research. Towards addressing this challenge, we previously reported on a novel architecture, cascade optical coherence tomography (C-OCT), which was validated for its ability of high-precision sag measurement at a given point. Here, we demonstrate freeform surface measurements, enabled by the development of a custom optical-relay-based scanning mechanism and a unique high-speed rotation mechanism. Experimental results on a flat mirror demonstrate an RMS flatness of 14 nm (∼λ/44 at the He-Ne wavelength). Measurement on a freeform mirror is achieved with an RMS residual of 69 nm (∼λ/9). The system-level investigations and validation provide the groundwork for advancing C-OCT as a viable freeform metrology technique.

PBMDA: A novel and effective path-based computational model for miRNA-disease association prediction.

In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one of pathogenetic factors, the molecular mechanisms underlying human complex diseases still have not been completely understood from the perspective of miRNA. Predicting potential miRNA-disease associations makes important contributions to understanding the pathogenesis of diseases, developing new drugs, and formulating individualized diagnosis and treatment for diverse human complex diseases. Instead of only depending on expensive and time-consuming biological experiments, computational prediction models are effective by predicting potential miRNA-disease associations, prioritizing candidate miRNAs for the investigated diseases, and selecting those miRNAs with higher association probabilities for further experimental validation. In this study, Path-Based MiRNA-Disease Association (PBMDA) prediction model was proposed by integrating known human miRNA-disease associations, miRNA functional similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity for miRNAs and diseases. This model constructed a heterogeneous graph consisting of three interlinked sub-graphs and further adopted depth-first search algorithm to infer potential miRNA-disease associations. As a result, PBMDA achieved reliable performance in the frameworks of both local and global LOOCV (AUCs of 0.8341 and 0.9169, respectively) and 5-fold cross validation (average AUC of 0.9172). In the cases studies of three important human diseases, 88% (Esophageal Neoplasms), 88% (Kidney Neoplasms) and 90% (Colon Neoplasms) of top-50 predicted miRNAs have been manually confirmed by previous experimental reports from literatures. Through the comparison performance between PBMDA and other previous models in case studies, the reliable performance also demonstrates that PBMDA could serve as a powerful computational tool to accelerate the identification of disease-miRNA associations.

Construction and biocompatibility of a thin type I/II collagen composite scaffold.

Articular cartilage injury is a common type of damage observed in clinical practice. A matrix-induced autologous chondrocyte implant was developed to repair articular cartilage as an advancement on the autologous chondrocyte implant procedure. Here, we establish a thin double layer of collagen as a novel and effective bioscaffold for the regeneration of cartilaginous lesions. We created a collagen membrane with double layers using a cover slip, a cover slip, and the collagen was then freeze-dried under vacuum. Carbodiimide as a crosslinking agent was used to obtain a relatively stable collagen construction. The thickness of the knee joint cartilage from grown rabbits was measured from a frozen section. Both type I and type II collagens were characterized using Sodium dodecylsulfate/polyacrylamide gel electrophoresis (SDS-PAGE) and ultraviolet absorption peaks. The aperture size of the scaffold was observed using a scanning electron microscope (SEM). The degradation of the scaffolds in vitro was tested through digestion using collagenase solution. The mechanical capacity of the scaffolds was assessed under dynamic compression. The influence of the scaffold on chondrocyte proliferation was assessed using the methyl thiazolyl tetrazolium (MTT) colourimetric assay and scanning electron microscopy. The frozen sections of the rabbit femoral condyle showed that the thickness of the weight-bearing area of the articular cartilage was less than 1 mm. The results of the SDS-PAGE and ultraviolet absorption peaks of the collagens were in agreement with the standard photographs in the references. SEM showed that the aperture size of the cross-linked scaffold was 82.14 ± 15.70 µm. The in vitro degradation studies indicated that Carbodiimide cross-linking can effectively enhance the biostability of the scaffolds. The Carbodiimide cross-linking protocol resulted in a mean value for the samples that ranged from 8.72 to 15.95 MPa for the compressive strength. The results of the MTT demonstrated that the scaffold had promoted chondrocyte proliferation and SEM observations showed that the scaffold was a good adhesive and growth material for chondrocytes. Thin type I/II collagen composite scaffold can meet the demands of cartilage tissue engineering and have good biocompatibility.

LW-FQZip 2: a parallelized reference-based compression of FASTQ files.

BACKGROUND: The rapid progress of high-throughput DNA sequencing techniques has dramatically reduced the costs of whole genome sequencing, which leads to revolutionary advances in gene industry. The explosively increasing volume of raw data outpaces the decreasing disk cost and the storage of huge sequencing data has become a bottleneck of downstream analyses. Data compression is considered as a solution to reduce the dependency on storage. Efficient sequencing data compression methods are highly demanded. RESULTS: In this article, we present a lossless reference-based compression method namely LW-FQZip 2 targeted at FASTQ files. LW-FQZip 2 is improved from LW-FQZip 1 by introducing more efficient coding scheme and parallelism. Particularly, LW-FQZip 2 is equipped with a light-weight mapping model, bitwise prediction by partial matching model, arithmetic coding, and multi-threading parallelism. LW-FQZip 2 is evaluated on both short-read and long-read data generated from various sequencing platforms. The experimental results show that LW-FQZip 2 is able to obtain promising compression ratios at reasonable time and memory space costs. CONCLUSIONS: The competence enables LW-FQZip 2 to serve as a candidate tool for archival or space-sensitive applications of high-throughput DNA sequencing data. LW-FQZip 2 is freely available at http://csse.szu.edu.cn/staff/zhuzx/LWFQZip2 and https://github.com/Zhuzxlab/LW-FQZip2 .

Cartoon Animation Outpainting With Region-Guided Motion Inference.

Cartoon animation video is a popular visual entertainment form worldwide, however many classic animations were produced in a 4:3 aspect ratio that is incompatible with modern widescreen displays. Existing methods like cropping lead to information loss while retargeting causes distortion. Animation companies still rely on manual labor to renovate classic cartoon animations, which is tedious and labor-intensive, but can yield higher-quality videos. Conventional extrapolation or inpainting methods tailored for natural videos struggle with cartoon animations due to the lack of textures in anime, which affects the motion estimation of the objects. In this paper, we propose a novel framework designed to automatically outpaint 4:3 anime to 16:9 via region-guided motion inference. Our core concept is to identify the motion correspondences between frames within a sequence in order to reconstruct missing pixels. Initially, we estimate optical flow guided by region information to address challenges posed by exaggerated movements and solid-color regions in cartoon animations. Subsequently, frames are stitched to produce a pre-filled guide frame, offering structural clues for the extension of optical flow maps. Finally, a voting and fusion scheme utilizes learned fusion weights to blend the aligned neighboring reference frames, resulting in the final outpainting frame. Extensive experiments confirm the superiority of our approach over existing methods.

PolypSeg+: A Lightweight Context-Aware Network for Real-Time Polyp Segmentation.

Automatic polyp segmentation from colonoscopy videos is a prerequisite for the development of a computer-assisted colon cancer examination and diagnosis system. However, it remains a very challenging task owing to the large variation of polyps, the low contrast between polyps and background, and the blurring boundaries of polyps. More importantly, real-time performance is a necessity of this task, as it is anticipated that the segmented results can be immediately presented to the doctor during the colonoscopy intervention for his/her prompt decision and action. It is difficult to develop a model with powerful representation capability, yielding satisfactory segmentation results and, simultaneously, maintaining real-time performance. In this article, we present a novel lightweight context-aware network, namely, PolypSeg+, attempting to capture distinguishable features of polyps without increasing network complexity and sacrificing time performance. To achieve this, a set of novel lightweight techniques is developed and integrated into the proposed PolypSeg+, including an adaptive scale context (ASC) module equipped with a lightweight attention mechanism to tackle the large-scale variation of polyps, an efficient global context (EGC) module to promote the fusion of low-level and high-level features by excluding background noise and preserving boundary details, and a lightweight feature pyramid fusion (FPF) module to further refine the features extracted from the ASC and EGC. We extensively evaluate the proposed PolypSeg+ on two famous public available datasets for the polyp segmentation task: 1) Kvasir-SEG and 2) CVC-Endoscenestill. The experimental results demonstrate that our PolypSeg+ consistently outperforms other state-of-the-art networks by achieving better segmentation accuracy in much less running time. The code is available at https://github.com/szu-zzb/polypsegplus.

Shading-guided Manga Screening from Reference.

Manga screening is a critical process in manga production, which still requires intensive labor and cost. Existing manga screening methods either generate simple dotted screentones only or rely on color information and manual hints during screentone selection. Due to the large domain gap between line drawings and screened manga, and the difficulties in generating high-quality, properly selected and shaded screentones, even state-of-the-art deep learning methods cannot convert line drawings to screened manga well. Besides, ambiguity exists in the screening process since different artists may screen differently for the same line drawing. In this paper, we propose to introduce shaded line drawing as the intermediate counterpart of the screened manga so that the manga screening task can be decomposed into two sub-tasks, generating shading from a line drawing and replacing shading with proper screentones. The reference image is adopted to resolve the ambiguity issue and provides options and controls on the generated screened manga. We proposed a reference-based shading generation network and a reference-based screentone generation module to achieve the two sub-tasks individually. We conduct extensive visual and quantitative experiments to verify the effectiveness of our system. Results and statistics show that our method outperforms existing methods on the manga screening task.

Cross-Image Dependency Modeling for Breast Ultrasound Segmentation.

We present a novel deep network (namely BUSSeg) equipped with both within- and cross-image long-range dependency modeling for automated lesions segmentation from breast ultrasound images, which is a quite daunting task due to (1) the large variation of breast lesions, (2) the ambiguous lesion boundaries, and (3) the existence of speckle noise and artifacts in ultrasound images. Our work is motivated by the fact that most existing methods only focus on modeling the within-image dependencies while neglecting the cross-image dependencies, which are essential for this task under limited training data and noise. We first propose a novel cross-image dependency module (CDM) with a cross-image contextual modeling scheme and a cross-image dependency loss (CDL) to capture more consistent feature expression and alleviate noise interference. Compared with existing cross-image methods, the proposed CDM has two merits. First, we utilize more complete spatial features instead of commonly used discrete pixel vectors to capture the semantic dependencies between images, mitigating the negative effects of speckle noise and making the acquired features more representative. Second, the proposed CDM includes both intra- and inter-class contextual modeling rather than just extracting homogeneous contextual dependencies. Furthermore, we develop a parallel bi-encoder architecture (PBA) to tame a Transformer and a convolutional neural network to enhance BUSSeg's capability in capturing within-image long-range dependencies and hence offer richer features for CDM. We conducted extensive experiments on two representative public breast ultrasound datasets, and the results demonstrate that the proposed BUSSeg consistently outperforms state-of-the-art approaches in most metrics.

Feature Masking on Non-Overlapping Regions for Detecting Dense Cells in Blood Smear Image.

Detecting cells in blood smear images is of great significance for automatic diagnosis of blood diseases. However, this task is rather challenging, mainly because there are dense cells that are often overlapping, making some of the occluded boundary parts invisible. In this paper, we propose a generic and effective detection framework that exploits non-overlapping regions (NOR) for providing discriminative and confident information to compensate the intensity deficiency. In particular, we propose a feature masking (FM) to exploit the NOR mask generated from the original annotation information, which can guide the network to extract NOR features as supplementary information. Furthermore, we exploit NOR features to directly predict the NOR bounding boxes (NOR BBoxes). NOR BBoxes are combined with the original BBoxes for generating one-to-one corresponding BBox-pairs that are used for further improving the detection performance. Different from the non-maximum suppression (NMS), our proposed non-overlapping regions NMS (NOR-NMS) uses the NOR BBoxes in the BBox-pairs to calculate intersection over union (IoU) for suppressing redundant BBoxes, and consequently retains the corresponding original BBoxes, circumventing the dilemma of NMS. We conducted extensive experiments on two publicly available datasets, with positive results demonstrating the effectiveness of the proposed method against existing methods.

Separating Shading and Reflectance from Cartoon Illustrations.

Shading plays an important role in cartoon drawings to present the 3D lighting and depth information in a 2D image to improve the visual information and pleasantness. But it also introduces apparent challenges in analyzing and processing the cartoon drawings for different computer graphics and vision applications, such as segmentation, depth estimation, and relighting. Extensive research has been made in removing or separating the shading information to facilitate these applications. Unfortunately, the existing researches only focused on natural images, which are natively different from cartoons since the shading in natural images is physically correct and can be modeled based on physical priors. However, shading in cartoons is manually created by artists, which may be imprecise, abstract, and stylized. This makes it extremely difficult to model the shading in cartoon drawings. Without modeling the shading prior, in the paper, we propose a learning-based solution to separate the shading from the original colors using a two-branch system consisting of two subnetworks. To the best of our knowledge, our method is the first attempt in separating shading information from cartoon drawings. Our method significantly outperforms the methods tailored for natural images. Extensive evaluations have been performed with convincing results in all cases.

Semi-supervised segmentation of echocardiography videos via noise-resilient spatiotemporal semantic calibration and fusion.

We present a novel model for left ventricle endocardium segmentation from echocardiography video, which is of great significance in clinical practice and yet a challenging task due to (1) the severe speckle noise in echocardiography videos, (2) the irregular motion of pathological heart, and (3) the limited training data caused by high annotation cost. The proposed model has three compelling characteristics. First, we propose a novel adaptive spatiotemporal semantic calibration method to align the feature maps of consecutive frames, where the spatiotemporal correspondences are figured out based on feature maps instead of pixels, thereby mitigating the adverse effects of speckle noise in the calibration. Second, we further learn the importance of each feature map of neighbouring frames to the current frame from the temporal perspective so as to distinctively rather than uniformly harness the temporal information to tackle the irregular and anisotropic motions. Third, we integrate these techniques into the mean teacher semi-supervised architecture to leverage a large amount of unlabeled data to improve the segmentation accuracy. We extensively evaluate the proposed method on two public echocardiography video datasets (EchoNet-Dynamic and CAMUS), where the average dice coefficient on the left ventricular endocardium segmentation achieves 92.87% and 93.79%, respectively. Comparisons with state-of-the-art methods also demonstrate the effectiveness of the proposed method by achieving a better segmentation performance with a faster speed.

FAT-Net: Feature adaptive transformers for automated skin lesion segmentation.

Skin lesion segmentation from dermoscopic image is essential for improving the quantitative analysis of melanoma. However, it is still a challenging task due to the large scale variations and irregular shapes of the skin lesions. In addition, the blurred lesion boundaries between the skin lesions and the surrounding tissues may also increase the probability of incorrect segmentation. Due to the inherent limitations of traditional convolutional neural networks (CNNs) in capturing global context information, traditional CNN-based methods usually cannot achieve a satisfactory segmentation performance. In this paper, we propose a novel feature adaptive transformer network based on the classical encoder-decoder architecture, named FAT-Net, which integrates an extra transformer branch to effectively capture long-range dependencies and global context information. Furthermore, we also employ a memory-efficient decoder and a feature adaptation module to enhance the feature fusion between the adjacent-level features by activating the effective channels and restraining the irrelevant background noise. We have performed extensive experiments to verify the effectiveness of our proposed method on four public skin lesion segmentation datasets, including the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets. Ablation studies demonstrate the effectiveness of our feature adaptive transformers and memory-efficient strategies. Comparisons with state-of-the-art methods also verify the superiority of our proposed FAT-Net in terms of both accuracy and inference speed. The code is available at https://github.com/SZUcsh/FAT-Net.

Automated left ventricular segmentation from cardiac magnetic resonance images via adversarial learning with multi-stage pose estimation network and co-discriminator.

Left ventricular (LV) segmentation is essential for the early diagnosis of cardiovascular diseases, which has been reported as the leading cause of death all over the world. However, automated LV segmentation from cardiac magnetic resonance images (CMRI) using the traditional convolutional neural networks (CNNs) is still a challenging task due to the limited labeled CMRI data and low tolerances to irregular scales, shapes and deformations of LV. In this paper, we propose an automated LV segmentation method based on adversarial learning by integrating a multi-stage pose estimation network (MSPN) and a co-discrimination network. Different from existing CNNs, we use a MSPN with multi-scale dilated convolution (MDC) modules to enhance the ranges of receptive field for deep feature extraction. To fully utilize both labeled and unlabeled CMRI data, we propose a novel generative adversarial network (GAN) framework for LV segmentation by combining MSPN with co-discrimination networks. Specifically, the labeled CMRI are first used to initialize our segmentation network (MSPN) and co-discrimination network. Our GAN training includes two different kinds of epochs fed with both labeled and unlabeled CMRI data alternatively, which are different from the traditional CNNs only relied on the limited labeled samples to train the segmentation networks. As both ground truth and unlabeled samples are involved in guiding training, our method not only can converge faster but also obtain a better performance in LV segmentation. Our method is evaluated using MICCAI 2009 and 2017 challenge databases. Experimental results show that our method has obtained promising performance in LV segmentation, which also outperforms the state-of-the-art methods in terms of LV segmentation accuracy from the comparison results.

Automatic Symmetry Detection From Brain MRI Based on a 2-Channel Convolutional Neural Network.

Symmetry detection is a method to extract the ideal mid-sagittal plane (MSP) from brain magnetic resonance (MR) images, which can significantly improve the diagnostic accuracy of brain diseases. In this article, we propose an automatic symmetry detection method for brain MR images in 2-D slices based on a 2-channel convolutional neural network (CNN). Different from the existing detection methods that mainly rely on the local image features (gradient, edge, etc.) to determine the MSP, we use a CNN-based model to implement the brain symmetry detection, which does not require any local feature detections and feature matchings. By training to learn a wide variety of benchmarks in the brain images, we can further use a 2-channel CNN to evaluate the similarity between the pairs of brain patches, which are randomly extracted from the whole brain slice based on a Poisson sampling. Finally, a scoring and ranking scheme is used to identify the optimal symmetry axis for each input brain MR slice. Our method was evaluated in 2166 artificial synthesized brain images and 3064 collected in vivo MR images, which included both healthy and pathological cases. The experimental results display that our method achieves excellent performance for symmetry detection. Comparisons with the state-of-the-art methods also demonstrate the effectiveness and advantages for our approach in achieving higher accuracy than the previous competitors.

Automated Skin Lesion Segmentation Via an Adaptive Dual Attention Module.

We present a convolutional neural network (CNN) equipped with a novel and efficient adaptive dual attention module (ADAM) for automated skin lesion segmentation from dermoscopic images, which is an essential yet challenging step for the development of a computer-assisted skin disease diagnosis system. The proposed ADAM has three compelling characteristics. First, we integrate two global context modeling mechanisms into the ADAM, one aiming at capturing the boundary continuity of skin lesion by global average pooling while the other dealing with the shape irregularity by pixel-wise correlation. In this regard, our network, thanks to the proposed ADAM, is capable of extracting more comprehensive and discriminative features for recognizing the boundary of skin lesions. Second, the proposed ADAM supports multi-scale resolution fusion, and hence can capture multi-scale features to further improve the segmentation accuracy. Third, as we harness a spatial information weighting method in the proposed network, our method can reduce a lot of redundancies compared with traditional CNNs. The proposed network is implemented based on a dual encoder architecture, which is able to enlarge the receptive field without greatly increasing the network parameters. In addition, we assign different dilation rates to different ADAMs so that it can adaptively capture distinguishing features according to the size of a lesion. We extensively evaluate the proposed method on both ISBI2017 and ISIC2018 datasets and the experimental results demonstrate that, without using network ensemble schemes, our method is capable of achieving better segmentation performance than state-of-the-art deep learning models, particularly those equipped with attention mechanisms.

SCS-Net: A Scale and Context Sensitive Network for Retinal Vessel Segmentation.

Accurately segmenting retinal vessel from retinal images is essential for the detection and diagnosis of many eye diseases. However, it remains a challenging task due to (1) the large variations of scale in the retinal vessels and (2) the complicated anatomical context of retinal vessels, including complex vasculature and morphology, the low contrast between some vessels and the background, and the existence of exudates and hemorrhage. It is difficult for a model to capture representative and distinguishing features for retinal vessels under such large scale and semantics variations. Limited training data also make this task even harder. In order to comprehensively tackle these challenges, we propose a novel scale and context sensitive network (a.k.a., SCS-Net) for retinal vessel segmentation. We first propose a scale-aware feature aggregation (SFA) module, aiming at dynamically adjusting the receptive fields to effectively extract multi-scale features. Then, an adaptive feature fusion (AFF) module is designed to guide efficient fusion between adjacent hierarchical features to capture more semantic information. Finally, a multi-level semantic supervision (MSS) module is employed to learn more distinctive semantic representation for refining the vessel maps. We conduct extensive experiments on the six mainstream retinal image databases (DRIVE, CHASEDB1, STARE, IOSTAR, HRF, and LES-AV). The experimental results demonstrate the effectiveness of the proposed SCS-Net, which is capable of achieving better segmentation performance than other state-of-the-art approaches, especially for the challenging cases with large scale variations and complex context environments.

LRLSHMDA: Laplacian Regularized Least Squares for Human Microbe-Disease Association prediction.

An increasing number of evidences indicate microbes are implicated in human physiological mechanisms, including complicated disease pathology. Some microbes have been demonstrated to be associated with diverse important human diseases or disorders. Through investigating these disease-related microbes, we can obtain a better understanding of human disease mechanisms for advancing medical scientific progress in terms of disease diagnosis, treatment, prevention, prognosis and drug discovery. Based on the known microbe-disease association network, we developed a semi-supervised computational model of Laplacian Regularized Least Squares for Human Microbe-Disease Association (LRLSHMDA) by introducing Gaussian interaction profile kernel similarity calculation and Laplacian regularized least squares classifier. LRLSHMDA reached the reliable AUCs of 0.8909 and 0.7657 based on the global and local leave-one-out cross validations, respectively. In the framework of 5-fold cross validation, average AUC value of 0.8794 +/-0.0029 further demonstrated its promising prediction ability. In case studies, 9, 9 and 8 of top-10 predicted microbes have been manually certified to be associated with asthma, colorectal carcinoma and chronic obstructive pulmonary disease by published literature evidence. Our proposed model achieves better prediction performance relative to the previous model. We expect that LRLSHMDA could offer insights into identifying more promising human microbe-disease associations in the future.

PBHMDA: Path-Based Human Microbe-Disease Association Prediction.

With the advance of sequencing technology and microbiology, the microorganisms have been found to be closely related to various important human diseases. The increasing identification of human microbe-disease associations offers important insights into the underlying disease mechanism understanding from the perspective of human microbes, which are greatly helpful for investigating pathogenesis, promoting early diagnosis and improving precision medicine. However, the current knowledge in this domain is still limited and far from complete. Here, we present the computational model of Path-Based Human Microbe-Disease Association prediction (PBHMDA) based on the integration of known microbe-disease associations and the Gaussian interaction profile kernel similarity for microbes and diseases. A special depth-first search algorithm was implemented to traverse all possible paths between microbes and diseases for inferring the most possible disease-related microbes. As a result, PBHMDA obtained a reliable prediction performance with AUCs (The area under ROC curve) of 0.9169 and 0.8767 in the frameworks of both global and local leave-one-out cross validations, respectively. Based on 5-fold cross validation, average AUCs of 0.9082 ± 0.0061 further demonstrated the efficiency of the proposed model. For the case studies of liver cirrhosis, type 1 diabetes, and asthma, 9, 7, and 9 out of predicted microbes in the top 10 have been confirmed by previously published experimental literatures, respectively. We have publicly released the prioritized microbe-disease associations, which may help to select the most potential pairs for further guiding the experimental confirmation. In conclusion, PBHMDA may have potential to boost the discovery of novel microbe-disease associations and aid future research efforts toward microbe involvement in human disease mechanism. The code and data of PBHMDA is freely available at http://www.escience.cn/system/file?fileId=85214.

Midsagittal plane extraction from brain images based on 3D SIFT.

Midsagittal plane (MSP) extraction from 3D brain images is considered as a promising technique for human brain symmetry analysis. In this paper, we present a fast and robust MSP extraction method based on 3D scale-invariant feature transform (SIFT). Unlike the existing brain MSP extraction methods, which mainly rely on the gray similarity, 3D edge registration or parameterized surface matching to determine the fissure plane, our proposed method is based on distinctive 3D SIFT features, in which the fissure plane is determined by parallel 3D SIFT matching and iterative least-median of squares plane regression. By considering the relative scales, orientations and flipped descriptors between two 3D SIFT features, we propose a novel metric to measure the symmetry magnitude for 3D SIFT features. By clustering and indexing the extracted SIFT features using a k-dimensional tree (KD-tree) implemented on graphics processing units, we can match multiple pairs of 3D SIFT features in parallel and solve the optimal MSP on-the-fly. The proposed method is evaluated by synthetic and in vivo datasets, of normal and pathological cases, and validated by comparisons with the state-of-the-art methods. Experimental results demonstrated that our method has achieved a real-time performance with better accuracy yielding an average yaw angle error below 0.91° and an average roll angle error no more than 0.89°.