Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters

A hybrid approach to full-scale reconstruction of renal arterial network

The renal vasculature, acting as a resource distribution network, plays an important role in both the physiology and pathophysiology of the kidney. However, no imaging techniques allow an assessment of the structure and function of the renal vasculature due to limited spatial and temporal resolution. To develop realistic computer simulations of renal function, and to develop new image-based diagnostic methods based on artificial intelligence, it is necessary to have a realistic full-scale model of the renal vasculature. We propose a hybrid framework to build subject-specific models of the renal vascular network by using semi-automated segmentation of large arteries and estimation of cortex area from a micro-CT scan as a starting point, and by adopting the Global Constructive Optimization algorithm for generating smaller vessels. Our results show a close agreement between the reconstructed vasculature and existing anatomical data obtained from a rat kidney with respect to morphometric and hemodynamic parameters.

Attention-Assisted Adversarial Model for Cerebrovascular Segmentation in 3D TOF-MRA Volumes

Cerebrovascular segmentation in time-of-flight magnetic resonance angiography (TOF-MRA) volumes is essential for a variety of diagnostic and analytical applications. However, accurate cerebrovascular segmentation in 3D TOF-MRA is faced with multiple issues, including vast variations in cerebrovascular morphology and intensity, noisy background, and severe class imbalance between foreground cerebral vessels and background. In this work, a 3D adversarial network model called A-SegAN is proposed to segment cerebral vessels in TOF-MRA volumes. The proposed model is composed of a segmentation network A-SegS to predict segmentation maps, and a critic network A-SegC to discriminate predictions from ground truth. Based on this model, the aforementioned issues are addressed by the prevailing visual attention mechanism. First, A-SegS is incorporated with feature-attention blocks to filter out discriminative feature maps, though the cerebrovascular has varied appearances. Second, a hard-example-attention loss is exploited to boost the training of A-SegS on hard samples. Further, A-SegC is combined with an input-attention layer to attach importance to foreground cerebrovascular class. The proposed methods were evaluated on a self-constructed voxel-wise annotated cerebrovascular TOF-MRA segmentation dataset, and experimental results indicate that A-SegAN achieves competitive or better cerebrovascular segmentation results compared to other deep learning methods, effectively alleviating the above issues.

Open-source algorithm and software for computed tomography-based virtual pancreatoscopy and other applications

Pancreatoscopy plays a significant role in the diagnosis and treatment of pancreatic diseases. However, the risk of pancreatoscopy is remarkably greater than that of other endoscopic procedures, such as gastroscopy and bronchoscopy, owing to its severe invasiveness. In comparison, virtual pancreatoscopy (VP) has shown notable advantages. However, because of the low resolution of current computed tomography (CT) technology and the small diameter of the pancreatic duct, VP has limited clinical use. In this study, an optimal path algorithm and super-resolution technique are investigated for the development of an open-source software platform for VP based on 3D Slicer. The proposed segmentation of the pancreatic duct from the abdominal CT images reached an average Dice coefficient of 0.85 with a standard deviation of 0.04. Owing to the excellent segmentation performance, a fly-through visualization of both the inside and outside of the duct was successfully reconstructed, thereby demonstrating the feasibility of VP. In addition, a quantitative analysis of the wall thickness and topology of the duct provides more insight into pancreatic diseases than a fly-through visualization. The entire VP system developed in this study is available at https://github.com/gaoyi/VirtualEndoscopy.git.

X-ray coronary centerline extraction based on C-UNet and a multifactor reconnection algorithm

BACKGROUND AND OBJECTIVE

Accurate extraction of the coronary artery centerline is crucial in the processes of coronary artery reconstruction, coronary artery stenosis or lesion detection, and surgical navigation. Furthermore, in clinical medicine, the complex background of angiography, low signal-to-noise ratio, and complex vascular structure make coronary artery centerline extraction challenging. In this study, a direct centerline extraction method is proposed that automatically and accurately extracts vascular centerlines from X-ray coronary angiography images based on deep learning and conventional methods.

METHODS

In this study, a coronary artery centerline extraction method is proposed that comprises two parts: the preliminary centerline extraction network based on U-Net with a residual network, called C-UNet, and the multifactor centerline reconnection algorithm based on the geometric characteristics of blood vessels.

RESULTS

The qualitative and quantitative results demonstrate the effectiveness of the presented method. In this study, three widely used evaluation indices were adopted to evaluate the performance of the method: precision, recall, and F1_Score. The experimental results show that this method can accurately extract coronary artery centerlines.

CONCLUSIONS

The proposed centerline extraction method accurately extracts centerlines from X-ray coronary angiography images and improves both the accuracy and continuity of centerline extraction.

Simultaneous vessel segmentation and unenhanced prediction using self-supervised dual-task learning in 3D CTA (SVSUP)

BACKGROUND AND OBJECTIVE

The vessel segmentation in CT angiography (CTA) provides an important basis for automatic diagnosis and hemodynamics analysis. Virtual unenhanced (VU) CT images obtained by dual-energy CT can assist clinical diagnosis and reduce radiation dose by obviating true unenhanced imaging (UECT). However, accurate segmentation of all vessels in the head-neck CTA (HNCTA) remains a challenge, and VU images are currently not available from conventional single-energy CT imaging.

METHODS

In this paper, we proposed a self-supervised dual-task deep learning strategy to fully automatically segment all vessels and predict unenhanced CT images from single-energy HNCTA based on a developed iterative residual-sharing scheme. The underlying idea was to use the correlation between the two tasks to improve task performance while avoiding manual annotation for model training.

RESULTS

The feasibility of the strategy was verified using the data of 24 patients. For vessel segmentation task, the proposed model achieves a significantly higher average Dice coefficient (84.83%, P-values 10^-3 in paired t-test) than the state-of-the-art segmentation model, vanilla VNet (78.94%), and several popular 3D vessel segmentation models, including Hessian-matrix based filter (62.59%), optically-oriented flux (66.33%), spherical flux model (66.91%), and deep vessel net (66.47%). For the unenhanced prediction task, the average ROI-based error compared to the UECT in the artery tissue is 6.1±4.5 HU, similar to previously reported 6.4±5.1 HU for VU reconstruction.

CONCLUSIONS

Results show that the proposed dual-task framework can effectively improve the accuracy of vessel segmentation in HNCTA, and it is feasible to predict the unenhanced image from single-energy CTA, providing a potential new approach for radiation dose saving. Moreover, to our best knowledge, this is the first reported annotation-free deep learning-based full-image vessel segmentation for HNCTA.

Unified classification of mouse retinal ganglion cells using function, morphology, and gene expression

Classification and characterization of neuronal types are critical for understanding their function and dysfunction. Neuronal classification schemes typically rely on measurements of electrophysiological, morphological, and molecular features, but aligning such datasets has been challenging. Here, we present a unified classification of mouse retinal ganglion cells (RGCs), the sole retinal output neurons. We use visually evoked responses to classify 1,859 mouse RGCs into 42 types. We also obtain morphological or transcriptomic data from subsets and use these measurements to align the functional classification to publicly available morphological and transcriptomic datasets. We create an online database that allows users to browse or download the data and to classify RGCs from their light responses using a machine learning algorithm. This work provides a resource for studies of RGCs, their upstream circuits in the retina, and their projections in the brain, and establishes a framework for future efforts in neuronal classification and open data distribution.

Cerebral vascular strains in dynamic head impact using an upgraded model with brain material property heterogeneity

Cerebral vascular injury (CVI) is a frequent consequence of traumatic brain injury but has often been neglected. Substantial experimental work exists on vascular material properties and failure/subfailure thresholds. However, little is known about vascular in vivo loading conditions in dynamic head impact, which is necessary to investigate the risk, severity, and extent of CVI. In this study, we resort to the Worcester Head Injury Model (WHIM) V2.1 for investigation. The model embeds the cerebral vasculature network and is further upgraded to incorporate brain material property heterogeneity based on magnetic resonance elastography. The brain material property is calibrated to match with the previously validated anisotropic V1.0 version in terms of whole-brain strains against six experimental datasets of a wide range of blunt impact conditions. The upgraded WHIM is finally used to simulate five representative real-world head impacts drawn from contact sports and automotive crashes. We find that peak strains in veins are considerably higher than those in arteries and that peak circumferential strains are also higher than peak axial strains. For a typical concussive head impact, cerebral vascular axial strains reach the lowest reported yield strain of ∼7-8%. For severe automotive impacts, axial strains could reach ∼20%, which is on the order of the lowest reported ultimate failure strain of ∼24%. These results suggest in vivo mechanical loading conditions of the cerebral vasculature (excluding bridging veins not assessed here) due to rapid head rotation are at the lower end of failure/subfailure thresholds established from ex vivo experiments. This study provides some first insight into the risk, severity, and extent of CVI in real-world head impacts.

A nested parallel multiscale convolution for cerebrovascular segmentation

PURPOSE

Cerebrovascular segmentation in magnetic resonance imaging (MRI) plays an important role in the diagnosis and treatment of cerebrovascular diseases. Many segmentation frameworks based on convolutional neural networks (CNNs) or U-Net-like structures have been proposed for cerebrovascular segmentation. Unfortunately, the segmentation results are still unsatisfactory, particularly in the small/thin cerebrovascular due to the following reasons: (1) the lack of attention to multiscale features in encoder caused by the convolutions with single kernel size; (2) insufficient extraction of shallow and deep-seated features caused by the depth limitation of transmission path between encoder and decoder; (3) insufficient utilization of the extracted features in decoder caused by less attention to multiscale features.

METHODS

Inspired by U-Net++, we propose a novel 3D U-Net-like framework termed Usception for small cerebrovascular. It includes three blocks: Reduction block, Gap block, and Deep block, aiming to: (1) improve feature extraction ability by grouping different convolution sizes; (2) increase the number of multiscale features in different layers by grouping paths of different depths between encoder and decoder; (3) maximize the ability of decoder in recovering multiscale features from Reduction and Gap block by using convolutions with different kernel sizes.

RESULTS

The proposed framework is evaluated on three public and in-house clinical magnetic resonance angiography (MRA) data sets. The experimental results show that our framework reaches an average dice score of 69.29%, 87.40%, 77.77% on three data sets, which outperform existing state-of-the-art methods. We also validate the effectiveness of each block through ablation experiments.

CONCLUSIONS

By means of the combination of Inception-ResNet and dimension-expanded U-Net++, the proposed framework has demonstrated its capability to maximize multiscale feature extraction, thus achieving competitive segmentation results for small cerebrovascular.

Automatic segmentation of peripheral arteries and veins in ferumoxytol-enhanced MR angiography

PURPOSE

To automate the segmentation of the peripheral arteries and veins in the lower extremities based on ferumoxytol-enhanced MR angiography (FE-MRA).

METHODS

Our automated pipeline has 2 sequential stages. In the first stage, we used a 3D U-Net with local attention gates, which was trained based on a combination of the Focal Tversky loss with region mutual loss under a deep supervision mechanism to segment the vasculature from the high-resolution FE-MRA datasets. In the second stage, we used time-resolved images to separate the arteries from the veins. Because the ultimate segmentation quality of the arteries and veins relies on the performance of the first stage, we thoroughly evaluated the different aspects of the segmentation network and compared its performance in blood vessel segmentation with currently accepted state-of-the-art networks, including Volumetric-Net, DeepVesselNet-FCN, and Uception.

RESULTS

We achieved a competitive F1 = 0.8087 and recall = 0.8410 for blood vessel segmentation compared with F1 = (0.7604, 0.7573, 0.7651) and recall = (0.7791, 0.7570, 0.7774) obtained with Volumetric-Net, DeepVesselNet-FCN, and Uception. For the artery and vein separation stage, we achieved F1 = (0.8274/0.7863) in the calf region, which is the most challenging region in peripheral arteries and veins segmentation.

CONCLUSION

Our pipeline is capable of fully automatic vessel segmentation based on FE-MRA without need for human interaction in <4 min. This method improves upon manual segmentation by radiologists, which routinely takes several hours.

Ordered multi-path propagation for vessel centerline extraction

Vessel centerline extraction from x-ray angiography images is essential for vessel structure analysis in the diagnosis of coronary artery disease. However, complete and continuous centerline extraction remains a challenging task due to image noise, poor contrast, and complexity of vessel structure. Thus, an iterative multi-path search framework for automatic vessel centerline extraction is proposed. First, the seed points of the vessel structure are detected and sorted by confidence. With the ordered seed points, multi-bifurcation centerline is searched through multi-path propagation of wavefront and accumulated voting. Finally, the centerline is further extended piecewise by wavefront propagation on the basis of keypoint detection. The latter two steps are performed alternately to obtain the final centerline result. The proposed method is qualitatively and quantitatively evaluated on 1260 synthetic images and 50 clinical angiography images. The results demonstrate that our method has a highF1score of 87.8% ± 2.7% for the angiography images and achieves accurate and continuous results of vessel centerline extraction.

Coronary artery segmentation under class imbalance using a U-Net based architecture on computed tomography angiography images

Coronary artery disease is caused primarily by vessel narrowing. Extraction of the coronary artery area from images is the preferred procedure for diagnosing coronary diseases. In this study, a U-Net-based network architecture, 3D Dense-U-Net, was adopted to perform fully automatic segmentation of the coronary artery. The network was applied to 474 coronary computed tomography (CT) angiography scans performed at Wanfang Hospital, Taiwan. Of these, 10% were used for testing. The CT scans were divided into patches of 16 original high-resolution slices. The slices were overlapped between patches to take advantage of surrounding imaging information. However, an imbalance between the foreground and background presents a challenge in smaller-object segmentation such as with coronary arteries. The network was optimized and achieved a promising result when the focal loss concept was adopted. To evaluate the accuracy of the automatic segmentation approach, the dice similarity coefficient (DSC) was calculated, and an existing clinical tool was used. The subjective ratings of three experienced radiologists were used to compare the two ratings. The results show that the proposed approach can achieve a DSC of 0.9691, which is significantly higher than other studies using a deep learning approach. In the main trunk, the results of automatic segmentation agree with those of the clinical tool; they were significantly better in some small branches. In our study, automatic segmentation tool shows high-performance detection in coronary lumen vessels, thereby providing potential power in assisting clinical diagnosis.

Learning-based algorithms for vessel tracking: A review

Developing efficient vessel-tracking algorithms is crucial for imaging-based diagnosis and treatment of vascular diseases. Vessel tracking aims to solve recognition problems such as key (seed) point detection, centerline extraction, and vascular segmentation. Extensive image-processing techniques have been developed to overcome the problems of vessel tracking that are mainly attributed to the complex morphologies of vessels and image characteristics of angiography. This paper presents a literature review on vessel-tracking methods, focusing on machine-learning-based methods. First, the conventional machine-learning-based algorithms are reviewed, and then, a general survey of deep-learning-based frameworks is provided. On the basis of the reviewed methods, the evaluation issues are introduced. The paper is concluded with discussions about the remaining exigencies and future research.

DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes

We present DeepVesselNet, an architecture tailored to the challenges faced when extracting vessel trees and networks and corresponding features in 3-D angiographic volumes using deep learning. We discuss the problems of low execution speed and high memory requirements associated with full 3-D networks, high-class imbalance arising from the low percentage (<3%) of vessel voxels, and unavailability of accurately annotated 3-D training data-and offer solutions as the building blocks of DeepVesselNet. First, we formulate 2-D orthogonal cross-hair filters which make use of 3-D context information at a reduced computational burden. Second, we introduce a class balancing cross-entropy loss function with false-positive rate correction to handle the high-class imbalance and high false positive rate problems associated with existing loss functions. Finally, we generate a synthetic dataset using a computational angiogenesis model capable of simulating vascular tree growth under physiological constraints on local network structure and topology and use these data for transfer learning. We demonstrate the performance on a range of angiographic volumes at different spatial scales including clinical MRA data of the human brain, as well as CTA microscopy scans of the rat brain. Our results show that cross-hair filters achieve over 23% improvement in speed, lower memory footprint, lower network complexity which prevents overfitting and comparable accuracy that does not differ from full 3-D filters. Our class balancing metric is crucial for training the network, and transfer learning with synthetic data is an efficient, robust, and very generalizable approach leading to a network that excels in a variety of angiography segmentation tasks. We observe that sub-sampling and max pooling layers may lead to a drop in performance in tasks that involve voxel-sized structures. To this end, the DeepVesselNet architecture does not use any form of sub-sampling layer and works well for vessel segmentation, centerline prediction, and bifurcation detection. We make our synthetic training data publicly available, fostering future research, and serving as one of the first public datasets for brain vessel tree segmentation and analysis.

Segmentation of Cerebrovascular Anatomy from TOF-MRA Using Length-Strained Enhancement and Random Walker

Cerebrovascular rupture can cause a severe stroke. Three-dimensional time-of-flight (TOF) magnetic resonance angiography (MRA) is a common method of obtaining vascular information. This work proposes a fully automated segmentation method for extracting the vascular anatomy from TOF-MRA. The steps of the method are as follows. First, the brain is extracted on the basis of regional growth and path planning. Next, the brain's highlighted connected area is explored to obtain seed point information, and the Hessian matrix is used to enhance the contrast of image. Finally, a random walker combined with seed points and enhanced images is used to complete vascular anatomy segmentation. The method is tested using 12 sets of data and compared with two traditional vascular segmentation methods. Results show that the described method obtains an average Dice coefficient of 90.68%, and better results were obtained in comparison with the traditional methods.

Multi-Channel Surface EMG Spatio-Temporal Image Enhancement Using Multi-Scale Hessian-Based Filters

Surface electromyography (sEMG) signals acquired with linear electrode array are useful in analyzing muscle anatomy and physiology. Most algorithms for signal processing, detection, and estimation require adequate quality of the input signals, however, multi-channel sEMG signals are commonly contaminated due to several noise sources. The sEMG signal needs to be enhanced prior to the digital signal and image processing to achieve the best results. This study is using spatio-temporal images to represent surface EMG signals. The motor unit action potential (MUAP) in these images looks like a linear structure, making certain angles with the x-axis, depending on the conduction velocity of the MU. A multi-scale Hessian-based filter is used to enhance the linear structure, i.e., the MUAP region, and to suppress the background noise. The proposed framework is compared with some of the existing algorithms using synthetic, simulated, and experimental sEMG signals. Results show improved detection accuracy of the motor unit action potential after the proposed enhancement as a preprocessing step.

Machine learning analysis of whole mouse brain vasculature

Tissue clearing methods enable the imaging of biological specimens without sectioning. However, reliable and scalable analysis of large imaging datasets in three dimensions remains a challenge. Here we developed a deep learning-based framework to quantify and analyze brain vasculature, named Vessel Segmentation & Analysis Pipeline (VesSAP). Our pipeline uses a convolutional neural network (CNN) with a transfer learning approach for segmentation and achieves human-level accuracy. By using VesSAP, we analyzed the vascular features of whole C57BL/6J, CD1 and BALB/c mouse brains at the micrometer scale after registering them to the Allen mouse brain atlas. We report evidence of secondary intracranial collateral vascularization in CD1 mice and find reduced vascularization of the brainstem in comparison to the cerebrum. Thus, VesSAP enables unbiased and scalable quantifications of the angioarchitecture of cleared mouse brains and yields biological insights into the vascular function of the brain.

Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme

BACKGROUND

Proper segmentation of the liver from medical images is critical for computer-assisted diagnosis, therapy and surgical planning. Knowledge of its vascular structure allows division of the liver into eight functionally independent segments, each with its own vascular inflow, known as the Couinaud scheme. Couinaud's description is the most widely used classification, since it is well-suited for surgery and accurate for the localization of lesions. However, automatic segmentation of the liver and its vascular structure to construct the Couinaud scheme remains a challenging task.

METHODS

We present a complete framework to obtain Couinaud's classification in three main steps; first, we propose a model-based liver segmentation, then a vascular segmentation based on a skeleton process, and finally, the construction of the eight independent liver segments. Our algorithms are automatic and allow 3D visualizations.

RESULTS

We validate these algorithms on various databases with different imaging modalities (Magnetic Resonance Imaging (MRI) and Computed Tomography (CT)). Experimental results are presented on diseased livers, which pose complex challenges because both the overall organ shape and the vessels can be severely deformed. A mean DICE score of 0.915 is obtained for the liver segmentation, and an average accuracy of 0.98 for the vascular network. Finally, we present an evaluation of our method for performing the Couinaud segmentation thanks to medical reports with promising results.

CONCLUSIONS

We were able to automatically reconstruct 3-D volumes of the liver and its vessels on MRI and CT scans. Our goal is to develop an improved method to help radiologists with tumor localization.

Accurate vessel extraction via tensor completion of background layer in X-ray coronary angiograms

This paper proposes an effective method for accurately recovering vessel structures and intensity information from the X-ray coronary angiography (XCA) images of moving organs or tissues. Specifically, a global logarithm transformation of XCA images is implemented to fit the X-ray attenuation sum model of vessel/background layers into a low-rank, sparse decomposition model for vessel/background separation. The contrast-filled vessel structures are extracted by distinguishing the vessels from the low-rank backgrounds by using a robust principal component analysis and by constructing a vessel mask via Radon-like feature filtering plus spatially adaptive thresholding. Subsequently, the low-rankness and inter-frame spatio-temporal connectivity in the complex and noisy backgrounds are used to recover the vessel-masked background regions using tensor completion of all other background regions, while the twist tensor nuclear norm is minimized to complete the background layers. Finally, the method is able to accurately extract vessels' intensities from the noisy XCA data by subtracting the completed background layers from the overall XCA images. We evaluated the vessel visibility of resulting images on real X-ray angiography data and evaluated the accuracy of vessel intensity recovery on synthetic data. Experiment results show the superiority of the proposed method over the state-of-the-art methods.

Interactive virtual 3D models of renal cancer patient anatomies alter partial nephrectomy surgical planning decisions and increase surgeon confidence compared to volume-rendered images

Purpose

To determine whether the interactive visualisation of patient-specific virtual 3D models of the renal anatomy influences the pre-operative decision-making process of urological surgeons for complex renal cancer operations.

Methods

Five historic renal cancer patient pre-operative computed tomography (CT) datasets were retrospectively selected based on RENAL nephrectomy score and variety of anatomy. Interactive virtual 3D models were generated for each dataset using image segmentation software and were made available for online visualisation and manipulation. Consultant urologists were invited to participate in the survey which consisted of CT and volume-rendered images (VRI) for the control arm, and CT with segmentation overlay and the virtual 3D model for the intervention arm. A questionnaire regarding anatomical structures, surgical approach, and confidence was administered.

Results

Twenty-five participants were recruited (54% response rate), with 19/25 having > 5 years of renal surgery experience. The median anatomical clarity score increased from 3 for the control to 5 for the intervention arm. A change in planned surgical approach was reported in 19% of cases. Virtual 3D models increased surgeon confidence in the surgical decisions in 4/5 patient datasets. There was a statistically significant improvement in surgeon opinion of the potential utility for decision-making purposes of virtual 3D models as compared to VRI at the multidisciplinary team meeting, theatre planning, and intra-operative stages.

Conclusion

The use of pre-operative interactive virtual 3D models for surgery planning influences surgical decision-making. Further studies are needed to investigate if the use of these models changes renal cancer surgery outcomes.

Electronic supplementary material

The online version of this article (10.1007/s11548-019-01913-5) contains supplementary material, which is available to authorized users.

The Relation Between Capillary Transit Times and Hemoglobin Saturation Heterogeneity. Part 2: Capillary Networks

Brain metabolism is highly dependent on continuous oxygen supply. Cortical microvascular networks exhibit heterogeneous blood flow, leading to non-uniform tissue oxygenation and capillary hemoglobin saturation. We recently proposed capillary outflow saturation heterogeneity (COSH) to represent effects of heterogeneity on oxygen supply to tissue regions most vulnerable to hypoxia, and showed that diffusive oxygen exchange among red blood cells within capillaries and among capillaries (diffusive interaction) significantly reduces COSH in simplified geometrical configurations. Here, numerical simulations of oxygen transport in capillary network geometries derived from mouse somatosensory cortex are presented. Diffusive interaction was found to reduce COSH by 41 to 62% compared to simulations where diffusive interaction was excluded. Hemoglobin saturation drop across the microvascular network is strongly correlated with red blood cell transit time, but the coefficient of variation of saturation drop is approximately one third lower. Unexpectedly, the radius of the tissue cylinder supplied by a capillary correlates weakly with the anatomical tissue cylinder radius, but strongly with hemoglobin saturation. Thus, diffusive interaction contributes greatly to the microcirculation's ability to achieve tissue oxygenation, despite heterogeneous capillary transit time and hematocrit distribution. These findings provide insight into the effects of cerebral small vessel disease on tissue oxygenation and brain function.

Toward quantitative three-dimensional microvascular networks segmentation with multiview light-sheet fluorescence microscopy

Three-dimensional (3-D) large-scale imaging of microvascular networks is of interest in various areas of biology and medicine related to structural, functional, developmental, and pathological issues. Light-sheet fluorescence microscopy (LSFM) techniques are rapidly spreading and are now on the way to offer operational solutions for large-scale tissue imaging. This contribution describes how reliable vessel segmentation can be handled from LSFM data in very large tissue volumes using a suitable image analysis workflow. Since capillaries are tubular objects of a few microns scale radius, they represent challenging structures to reliably reconstruct without distortion and artifacts. We provide a systematic analysis of multiview deconvolution image processing workflow to control and evaluate the accuracy of the reconstructed vascular network using various low to high level, metrics. We show that even if low-level structural metrics are sensitive to isotropic imaging enhancement provided by a larger number of views, functional high-level metrics, including perfusion permeability, are less sensitive. Hence, combining deconvolution and registration onto a few number of views appears sufficient for a reliable quantitative 3-D vessel segmentation for their possible use for perfusion modeling.

Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images

Accurate segmentation of perivascular spaces (PVSs) is an important step for quantitative study of PVS morphology. However, since PVSs are the thin tubular structures with relatively low contrast and also the number of PVSs is often large, it is challenging and time-consuming for manual delineation of PVSs. Although several automatic/semi-automatic methods, especially the traditional learning-based approaches, have been proposed for segmentation of 3D PVSs, their performance often depends on the hand-crafted image features, as well as sophisticated preprocessing operations prior to segmentation (e.g., specially defined regions-of-interest (ROIs)). In this paper, a novel fully convolutional neural network (FCN) with no requirement of any specified hand-crafted features and ROIs is proposed for efficient segmentation of PVSs. Particularly, the original T2-weighted 7T magnetic resonance (MR) images are first filtered via a non-local Haar-transform-based line singularity representation method to enhance the thin tubular structures. Both the original and enhanced MR images are used as multi-channel inputs to complementarily provide detailed image information and enhanced tubular structural information for the localization of PVSs. Multi-scale features are then automatically learned to characterize the spatial associations between PVSs and adjacent brain tissues. Finally, the produced PVS probability maps are recursively loaded into the network as an additional channel of inputs to provide the auxiliary contextual information for further refining the segmentation results. The proposed multi-channel multi-scale FCN has been evaluated on the 7T brain MR images scanned from 20 subjects. The experimental results show its superior performance compared with several state-of-the-art methods.

Structured Learning for 3-D Perivascular Space Segmentation Using Vascular Features

OBJECTIVE

The goal of this paper is to automatically segment perivascular spaces (PVSs) in brain from high-resolution 7T magnetic resonance (MR) images.

METHODS

We propose a structured-learning-based segmentation framework to extract the PVSs from high-resolution 7T MR images. Specifically, we integrate three types of vascular filter responses into a structured random forest for classifying voxels into two categories, i.e., PVS and background. In addition, we propose a novel entropy-based sampling strategy to extract informative samples in the background for training an explicit classification model. Since the vascular filters can extract various vascular features, even thin and low-contrast structures can be effectively extracted from noisy backgrounds. Moreover, continuous and smooth segmentation results can be obtained by utilizing patch-based structured labels.

RESULTS

The performance of our proposed method is evaluated on 19 subjects with 7T MR images, with the Dice similarity coefficient reaching 66%.

CONCLUSION

The joint use of entropy-based sampling strategy, vascular features, and structured learning can improve the segmentation accuracy.

SIGNIFICANCE

Instead of manual annotation, our method provides an automatic way for PVS segmentation. Moreover, our method can be potentially used for other vascular structure segmentation because of its data-driven property.

Accurate model-based segmentation of gynecologic brachytherapy catheter collections in MRI-images

The gynecological cancer mortality rate, including cervical, ovarian, vaginal and vulvar cancers, is more than 20,000 annually in the US alone. In many countries, including the US, external-beam radiotherapy followed by high dose rate brachytherapy is the standard-of-care. The superior ability of MR to visualize soft tissue has led to an increase in its usage in planning and delivering brachytherapy treatment. A technical challenge associated with the use of MRI imaging for brachytherapy, in contrast to that of CT imaging, is the visualization of catheters that are used to place radiation sources into cancerous tissue. We describe here a precise, accurate method for achieving catheter segmentation and visualization. The algorithm, with the assistance of manually provided tip locations, performs segmentation using image-features, and is guided by a catheter-specific, estimated mechanical model. A final quality control step removes outliers or conflicting catheter trajectories. The mean Hausdorff error on a 54 patient, 760 catheter reference database was 1.49  mm; 51 of the outliers deviated more than two catheter widths (3.4  mm) from the gold standard, corresponding to catheter identification accuracy of 93% in a Syed-Neblett template. In a multi-user simulation experiment for evaluating RMS precision by simulating varying manually-provided superior tip positions, 3σ maximum errors were 2.44  mm. The average segmentation time for a single catheter was 3 s on a standard PC. The segmentation time, accuracy and precision, are promising indicators of the value of this method for clinical translation of MR-guidance in gynecologic brachytherapy and other catheter-based interventional procedures.

Liver vessel segmentation and identification based on oriented flux symmetry and graph cuts

BACKGROUND AND OBJECTIVE

Accurate segmentation of liver vessels from abdominal computer tomography angiography (CTA) volume is very important for liver-vessel analysis and living-related liver transplants. This paper presents a novel liver-vessel segmentation and identification method.

METHODS

Firstly, an anisotropic diffusion filter is used to smooth noise while preserving vessel boundaries. Then, based on the gradient symmetry and antisymmetry pattern of vessel structures, optimal oriented flux (OOF) and oriented flux antisymmetry (OFA) measures are respectively applied to detect liver vessels and their boundaries, and further to slenderize vessels. Next, according to vessel geometrical structure, a centerline extraction measure based on height ridge traversal and leaf node line-growing (LNLG) is proposed for the extraction of liver-vessel centerlines, and an intensity model based on fast marching is integrated into graph cuts (GCs) for effective segmentation of liver vessels. Finally, a distance voting mechanism is applied to separate the hepatic vein and portal vein.

RESULTS

The experiment results on abdominal CTA images show that the proposed method can effectively segment liver vessels, achieving an average accuracy, sensitivity, and specificity of 97.7%, 79.8%, and 98.6%, respectively, and has a good performance on thin-vessel extraction.

CONCLUSIONS

The proposed method does not require manual selection of the centerlines and vessel seeds, and can effectively segment liver vessels and identify hepatic vein and portal vein.

A Combined Random Forests and Active Contour Model Approach for Fully Automatic Segmentation of the Left Atrium in Volumetric MRI

Segmentation of the left atrium (LA) from cardiac magnetic resonance imaging (MRI) datasets is of great importance for image guided atrial fibrillation ablation, LA fibrosis quantification, and cardiac biophysical modelling. However, automated LA segmentation from cardiac MRI is challenging due to limited image resolution, considerable variability in anatomical structures across subjects, and dynamic motion of the heart. In this work, we propose a combined random forests (RFs) and active contour model (ACM) approach for fully automatic segmentation of the LA from cardiac volumetric MRI. Specifically, we employ the RFs within an autocontext scheme to effectively integrate contextual and appearance information from multisource images together for LA shape inferring. The inferred shape is then incorporated into a volume-scalable ACM for further improving the segmentation accuracy. We validated the proposed method on the cardiac volumetric MRI datasets from the STACOM 2013 and HVSMR 2016 databases and showed that it outperforms other latest automated LA segmentation methods. Validation metrics, average Dice coefficient (DC) and average surface-to-surface distance (S2S), were computed as 0.9227 ± 0.0598 and 1.14 ± 1.205 mm, versus those of 0.6222-0.878 and 1.34-8.72 mm, obtained by other methods, respectively.

Nogo-A regulates vascular network architecture in the postnatal brain

Recently, we discovered a new role for the well-known axonal growth inhibitory molecule Nogo-A as a negative regulator of angiogenesis in the developing central nervous system. However, how Nogo-A affected the three-dimensional (3D) central nervous system (CNS) vascular network architecture remained unknown. Here, using vascular corrosion casting, hierarchical, synchrotron radiation μCT-based network imaging and computer-aided network analysis, we found that genetic ablation of Nogo-A significantly increased the three-dimensional vascular volume fraction in the postnatal day 10 (P10) mouse brain. More detailed analysis of the cerebral cortex revealed that this effect was mainly due to an increased number of capillaries and capillary branchpoints. Interestingly, other vascular parameters such as vessel diameter, -length, -tortuosity, and -volume were comparable between both genotypes for non-capillary vessels and capillaries. Taken together, our three-dimensional data showing more vessel segments and branchpoints at unchanged vessel morphology suggest that stimulated angiogenesis upon Nogo-A gene deletion results in the insertion of complete capillary micro-networks and not just single vessels into existing vascular networks. These findings significantly enhance our understanding of how angiogenesis, vascular remodeling, and three-dimensional vessel network architecture are regulated during central nervous system development. Nogo-A may therefore be a potential novel target for angiogenesis-dependent central nervous system pathologies such as brain tumors or stroke.

Simulation of MR angiography imaging for validation of cerebral arteries segmentation algorithms

BACKGROUND AND OBJECTIVE

Accurate vessel segmentation of magnetic resonance angiography (MRA) images is essential for computer-aided diagnosis of cerebrovascular diseases such as stenosis or aneurysm. The ability of a segmentation algorithm to correctly reproduce the geometry of the arterial system should be expressed quantitatively and observer-independently to ensure objectivism of the evaluation.

METHODS

This paper introduces a methodology for validating vessel segmentation algorithms using a custom-designed MRA simulation framework. For this purpose, a realistic reference model of an intracranial arterial tree was developed based on a real Time-of-Flight (TOF) MRA data set. With this specific geometry blood flow was simulated and a series of TOF images was synthesized using various acquisition protocol parameters and signal-to-noise ratios. The synthesized arterial tree was then reconstructed using a level-set segmentation algorithm available in the Vascular Modeling Toolkit (VMTK). Moreover, to present versatile application of the proposed methodology, validation was also performed for two alternative techniques: a multi-scale vessel enhancement filter and the Chan-Vese variant of the level-set-based approach, as implemented in the Insight Segmentation and Registration Toolkit (ITK). The segmentation results were compared against the reference model.

RESULTS

The accuracy in determining the vessels centerline courses was very high for each tested segmentation algorithm (mean error rate = 5.6% if using VMTK). However, the estimated radii exhibited deviations from ground truth values with mean error rates ranging from 7% up to 79%, depending on the vessel size, image acquisition and segmentation method.

CONCLUSIONS

We demonstrated the practical application of the designed MRA simulator as a reliable tool for quantitative validation of MRA image processing algorithms that provides objective, reproducible results and is observer independent.