Explore the vast range of titles available.

We describe an automated 3-D segmentation system for in vivo brain magnetic resonance images (MRI). Our segmentation method combines a variety of filtering, segmentation, and registration techniques and makes maximum use of the available a priori biomedical expertise, both in an implicit and an explicit form. We approach the issue of boundary finding as a process of fitting a group of deformable templates (simplex mesh surfaces) to the contours of the target structures. These templates evolve in parallel, supervised by a series of rules derived from analyzing the template's dynamics and from medical experience. The templates are also constrained by knowledge on the expected textural and shape properties of the target structures. We apply our system to segment four brain structures (corpus callosum, ventricles, hippocampus, and caudate nuclei) and discuss its robustness to imaging characteristics and acquisition noise.

3D printing as a means of fabrication has seen increasing applications in medicine in the last decade, becoming invaluable for cardiovascular applications. This rapidly developing technology has had a significant impact on cardiovascular research, its clinical translation and education. It has expanded our understanding of the cardiovascular system resulting in better devices, tools and consequently improved patient outcomes. This review discusses the latest developments and future directions of generating medical replicas (‘phantoms’) for use in the cardiovascular field, detailing the end-to-end process from medical imaging to capture structures of interest, to production and use of 3D printed models. We provide comparisons of available imaging modalities and overview of segmentation and post-processing techniques to process images for printing, detailed exploration of latest 3D printing methods and materials, and a comprehensive, up-to-date review of milestone applications and their impact within the cardiovascular domain across research, clinical use and education. We then provide an in-depth exploration of future technologies and innovations around these methods, capturing opportunities and emerging directions across increasingly realistic representations, bioprinting and tissue engineering, and complementary virtual and mixed reality solutions. The next generation of 3D printing techniques allow patient-specific models that are increasingly realistic, replicating properties, anatomy and function.

Recently, region based methods for estimating the 3D pose of an object from a 2D image have gained increasing popularity. They do not require prior knowledge of the object’s texture, making them particularity attractive when the object’s texture is unknown a priori. Region based methods estimate the 3D pose of an object by finding the pose which maximizes the image segmentation in to foreground and background regions. Typically the foreground and background regions are described using global appearance models, and an energy function measuring their fit quality is optimized with respect to the pose parameters. Applying a region based approach on standard 2D-3D pose estimation databases shows its performance is strongly dependent on the scene complexity. In simple scenes, where the statistical properties of the foreground and background do not spatially vary, it performs well. However, in more complex scenes, where the statistical properties of the foreground or background vary, the performance strongly degrades. The global appearance models used to segment the image do not sufficiently capture the spatial variation. Inspired by ideas from local active contours, we propose a framework for simultaneous image segmentation and pose estimation using multiple local appearance models. The local appearance models are capable of capturing spatial variation in statistical properties, where global appearance models are limited. We derive an energy function, measuring the image segmentation, using multiple local regions and optimize it with respect to the pose parameters. Our experiments show a substantially higher probability of estimating the correct pose for heterogeneous objects, whereas for homogeneous objects there is minor improvement.

This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system.

We consider the problem of segmenting multiple rigid-body motions from point correspondences in multiple affine views. We cast this problem as a subspace clustering problem in which point trajectories associated with each motion live in a linear subspace of dimension two, three or four. Our algorithm involves projecting all point trajectories onto a 5-dimensional subspace using the SVD, the PowerFactorization method, or RANSAC, and fitting multiple linear subspaces representing different rigid-body motions to the points in ℝ 5 using GPCA. Unlike previous work, our approach does not restrict the motion subspaces to be four-dimensional and independent. Instead, it deals gracefully with all the spectrum of possible affine motions: from two-dimensional and partially dependent to four-dimensional and fully independent. Our algorithm can handle the case of missing data, meaning that point tracks do not have to be visible in all images, by using the PowerFactorization method to project the data. In addition, our method can handle outlying trajectories by using RANSAC to perform the projection. We compare our approach to other methods on a database of 167 motion sequences with full motions, independent motions, degenerate motions, partially dependent motions, missing data, outliers, etc. On motion sequences with complete data our method achieves a misclassification error of less that 5% for two motions and 29% for three motions.

The use of three-dimensional(3D) printing is broadly across many medical specialties. It is an innovative, and rapidly growing technology to produce custom anatomical models and medical conditions models for medical teaching, surgical planning, and patient education. This study aimed to evaluate the accuracy and feasibility of 3D printing in creating a superficial femoral artery pseudoaneurysm model based on CT scans for endovascular training. A case of a left superficial femoral artery pseudoaneurysm was selected, and the 3D model was created using DICOM files imported into Materialise Mimics 22.0 and Materialise 3-Matic software, then printed using vat polymerization technology. Two 3D-printed models were created, and a series of comparisons were conducted between the 3D segmented images from CT scans and these two 3D-printed models. Ten comparisons involving internal diameters and angles of the specific anatomical location were measured. The study found that the absolute mean difference in diameter between the 3D segmented images and the 3D printed models was 0.179±0.145 mm and 0.216±0.143mm, respectively, with no significant difference between the two sets of models. Additionally, the absolute mean difference in angle was 0.99±0.65° and 1.00±0.91°, respectively, and the absolute mean difference in angle between the two sets of data was not significant. Bland-Altman analysis confirmed a high correlation in dimension measurements between the 3D-printed models and segmented images. Furthermore, the accuracy of a 3D-printed femoral pseudoaneurysm model was further tested through the simulation of a superficial femoral artery pseudoaneurysm coiling procedure using the Philips Azurion7 in the angiography room. 3D printing is a reliable technique for producing a high accuracy 3D anatomical model that closely resemble a patient's anatomy based on CT images. Additionally, 3D printing is a feasible and viable option for use in endovascular training and medical education. In general, 3D printing is an encouraging technology with diverse possibilities in medicine, including surgical planning, medical education, and medical device advancement.

Glioma is the most common type of brain tumor with varying level of malignancies and projection. Designing personalized therapy and to foresee response towards the therapy needs better understanding of tumor biology and diversification between tumors. Using different computational methods, accurate segmentation of tumors within the brain on MRI is the primary stride towards the understanding of tumor biology. The goal of current study is to draw an algorithm for MRI image segmentation of pre-treatment brain tumors and to evaluate its performance. In our research, we designed and implemented a novel 3D U-Net architecture for segmentation of sub-regions including edema, necrosis and enhancing tumor which are radiologically detectable. The group variance between tumor and non-tumorous spots is addressed by presenting weighted patch extraction scheme from tumor border regions. In its framework, context is captured using a contracting path and precise localization is performed by symmetric expanding path. In our study, the architecture based on Deep Convolutional Neural Network (DCNN) is trained on Brain Tumor Segmentation (BraTS) dataset of 750 patients among which 484 scans were labelled and 267 scans were used as training dataset. 3D patches were extracted from the dataset to train the system and results were assessed in terms of Specificity, Sensitivity and Dice Score. Our proposed system achieved Dice scores of 0.90 for whole tumor, 0.85 for tumor core, and 0.77 for enhancing tumor on dataset which shows potential of accurate intra-tumor segmentation of patch-based 3D U-Net architecture.

In this paper, we propose an unconditionally energy-stable linear method with improved consistency for the diffuse-interface (phase-field) model of three-dimensional narrow volume reconstruction based on point clouds. To detect the unorganized point set, a control function is added to the original Allen–Cahn (AC) equation. This modified AC equation is an extension of the image segmentation model in two-dimensional space. By introducing an appropriate time-dependent variable, we first transform the governing equation into an equivalent form. Based on the Crank–Nicolson type discretization in time, the linear time-marching scheme is developed. To improve the consistency between the original and modified energies, we apply a simple and effective correction algorithm after updating the phase-field variable in each time iteration. We can analytically prove the unconditional energy stability of the proposed method. We also describe the fully discrete implementation with spatial discretization using the finite difference method. Computational experiments validate that the proposed scheme is practical for reconstructing narrow volumes based on point clouds.

This study presents the initial results of a pilot project using the Elucis Virtual Reality (VR) platform for fetal heart segmentation. Twelve fetal heart cases, ranging in gestational age from 24 to 30 weeks, including various cardiac conditions, were reconstructed using 3D models facilitated by the Elucis platform’s integration of automated algorithms and manual adjustments. The models, which were evaluated by four experts in virtual and 3D printed formats, were of high quality and offered improved visuospatial visualization and detailed anatomical insights. This research highlights the potential of VR technology to improve prenatal diagnosis and planning for complex cardiac conditions, suggesting significant implications for continuing medical education and clinical practice in fetal cardiology.

Motion is a fundamental grouping cue in video. Many current approaches to motion segmentation in monocular or stereo image sequences rely on sparse interest points or are dense but computationally demanding. We propose an efficient expectation–maximization (EM) framework for dense 3D segmentation of moving rigid parts in RGB-D video. Our approach segments images into pixel regions that undergo coherent 3D rigid-body motion. Our formulation treats background and foreground objects equally and poses no further assumptions on the motion of the camera or the objects than rigidness. While our EM-formulation is not restricted to a specific image representation, we supplement it with efficient image representation and registration for rapid segmentation of RGB-D video. In experiments, we demonstrate that our approach recovers segmentation and 3D motion at good precision.