Deep Learning for Accurate Segmentation of Venous Thrombus from Black-Blood Magnetic Resonance Images: A Multicenter Study

Objective. Deep vein thrombosis (DVT) is the third-largest cardiovascular disease, and accurate segmentation of venous thrombus from the black-blood magnetic resonance (MR) images can provide additional information for personalized DVT treatment planning. Therefore, a deep learning network is proposed to automatically segment venous thrombus with high accuracy and reliability. Methods. In order to train, test, and external test the developed network, total images of 110 subjects are obtained from three different centers with two different black-blood MR techniques (i.e., DANTE-SPACE and DANTE-FLASH). Two experienced radiologists manually contoured each venous thrombus, followed by reediting, to create the ground truth. 5-fold cross-validation strategy is applied for training and testing. The segmentation performance is measured on pixel and vessel segment levels. For the pixel level, the dice similarity coefficient (DSC), average Hausdorff distance (AHD), and absolute volume difference (AVD) of segmented thrombus are calculated. For the vessel segment level, the sensitivity (SE), specificity (SP), accuracy (ACC), and positive and negative predictive values (PPV and NPV) are used. Results. The proposed network generates segmentation results in good agreement with the ground truth. Based on the pixel level, the proposed network achieves excellent results on testing and the other two external testing sets, DSC are 0.76, 0.76, and 0.73, AHD (mm) are 4.11, 6.45, and 6.49, and AVD are 0.16, 0.18, and 0.22. On the vessel segment level, SE are 0.95, 0.93, and 0.81, SP are 0.97, 0.92, and 0.97, ACC are 0.96, 0.94, and 0.95, PPV are 0.97, 0.82, and 0.96, and NPV are 0.97, 0.96, and 0.94. Conclusions. The proposed deep learning network is effective and stable for fully automatic segmentation of venous thrombus on black blood MR images.

Topology-Aware Retinal Artery–Vein Classification via Deep Vascular Connectivity Prediction

Retinal artery–vein (AV) classification is a prerequisite for quantitative analysis of retinal vessels, which provides a biomarker for neurologic, cardiac, and systemic diseases, as well as ocular diseases. Although convolutional neural networks have presented remarkable performance on AV classification, it often comes with a topological error, like an abrupt class flipping on the same vessel segment or a weakness for thin vessels due to their indistinct appearances. In this paper, we present a new method for AV classification where the underlying vessel topology is estimated to give consistent prediction along the actual vessel structure. We cast the vessel topology estimation as iterative vascular connectivity prediction, which is implemented as deep-learning-based pairwise classification. In consequence, a whole vessel graph is separated into sub-trees, and each of them is classified as an artery or vein in whole via a voting scheme. The effectiveness and efficiency of the proposed method is validated by conducting experiments on two retinal image datasets acquired using different imaging techniques called DRIVE and IOSTAR.

Absence of pontine perforators in vertebrobasilar dolichoectasia on ultra-high resolution cone-beam computed tomography

BackgroundVertebrobasilar dolichoectasia (VBDE) is a rare type of non-saccular intracranial aneurysm, with poor natural history and limited effective treatment options. Visualizing neurovascular microanatomy in patients with VBDE has not been previously reported, but may yield insight into the pathology, and provide important information for treatment planning.ObjectiveTo carry out a retrospective analysis of ultra-high resolution cone-beam computed tomography (UHR-CBCT) in patients with fusiform basilar aneurysms, visualizing neurovascular microanatomy of the posterior circulation with a special focus on the pontine perforators.MethodsUHR-CBCT was performed in seven patients (mean age 59 years; two female) with a VBDE, and in 14 control patients with unrelated conditions.ResultsThe mean maximum diameter of the fusiform vessel segment was 28 mm (range 19–36 mm), and the mean length of the segment was 39 mm (range 15–50 mm). In all patients with VBDE, UHR-CBCT demonstrated an absence of perforating arteries in the fusiform arterial segment and a mean of 3.7 perforators arising from the unaffected vessel segment. The network of interconnected superficial circumferential pontine arteries (brainstem vasocorona) were draping around the aneurysm sac. In controls, a mean of 3.6, 2.5, and 1.2 perforators were demonstrated arising from the distal, mid-, and proximal basilar artery, respectively.ConclusionsThe absence of pontine perforators in the fusiform vessel segment of VBDE is counterbalanced by recruitment of collateral flow from pontine perforators arising from the unaffected segment of the basilar artery, as well as collaterals arising from the anterior inferior cerebellar artery/posterior inferior cerebellar artery and superior cerebellar artery. These alternative routes supply the superficial brainstem arteries (brainstem vasocorona) and sustain brainstem viability. Our findings might have implications for further treatment planning.

Review of current intracranial aneurysm flow diversion technology and clinical use

Endovascular treatment of intracranial aneurysms (IAs) has evolved considerably over the past decades. The technological advances have been driven by the experience that coils fail to completely exclude all IAs from the blood circulation, the need to treat the diseased parent vessel segment leading to the aneurysm formation, and expansion of endovascular therapy to treat more complex IAs. Stents were initially developed to support the placement of coils inside wide neck aneurysms. However, early work on stent-like tubular braided structure led to a more sophisticated construct that then later was coined as a flow diverter (FD) and found its way into clinical application. Although FDs were initially used to treat wide-neck large and giant internal carotid artery aneurysms only amenable to surgical trap with or without a bypass or endovascular vessel sacrifice, its use in other types of IAs and cerebrovascular pathology promptly followed. Lately, we have witnessed an explosion in the application of FDs and subsequently their modifications leading to their ubiquitous use in endovascular therapy. In this review we aim to compile the available FD technology, evaluate the devices’ peculiarities from the authors’ perspective, and analyze the current literature to support initial and expanded indications, recognizing that this may be outdated soon.

Semantic Segmentation to Extract Coronary Arteries in Fluoroscopy Angiograms

Coronary artery disease (CAD) is the leading cause of death worldwide, constituting more than one-fourth of global mortalities every year. Accurate semantic segmentation of each artery in fluoroscopy angiograms is important for assessment of the stenosis and CAD diagnosis and treatment. However, due to the morphological similarity among different types of arteries, it is hard for deep-learning-based models to generate semantic segmentation with an end-toend approach. In this paper, we propose a multi-step semantic segmentation algorithm based on the analysis of graphs extracted from fluoroscopy angiograms. The proposed algorithm firstly extracts the entire arterial binary mask (binary vascular tree) by Feature Pyramid U-Net++. Then we extract the centerline of the binary vascular tree and separate it into different vessel segments. Finally, by extracting the underlying arterial topology, position and pixel features, we construct a powerful coronary artery classifier based on random forest. Each vessel segment is classified into left coronary artery (LCA), left anterior descending (LAD) and other types of arterial segments. We tested the proposed method on a dataset with 69 LAO and 103 RAO fluoroscopic angiograms and achieved classification accuracies of 66.4% and 61.49% respectively. The experimental results show the effectiveness of the proposed algorithm, which can be used to analyze the individual arteries in fluoroscopy angiograms.

Research on elastic recoil and restoration of vessel pulsatility of Zn-Cu biodegradable coronary stents

Coronary stents made of zinc (Zn)-0.8 copper (Cu) (in wt%) alloy were developed as biodegradable metal stents (Zn-Cu stents) in this study. The mechanical properties of the Zn-Cu stents and the possible gain effects were characterized by in vitro and in vivo experiments compared with 316L stainless steel stents (316L stents). Young’s modulus of the as-extruded Zn-0.8Cu alloy and properties of the stents, including their intrinsic elastic recoil, stent trackability were evaluated compared with 316L stents. In vivo study was also conducted to evaluate restoration of pulsatility of vessel segment implanted stents. Both Zn-Cu stents and 316L stents have good acute lumen gain. By comparison, the advantages of Zn-Cu stents are as follows: (I) Zn-Cu stents have less intrinsic elastic recoil than 316L stents; (II) stent trackability indicates that Zn-Cu stents have a smaller push force when passing through curved blood vessels, which may cause less mechanical stimulation to blood vessels; (III) in vivo study suggests that Zn-Cu stents implantation better facilitates the recovery of vascular pulsatility.

Image processing-based model for tortuosity measurement of retinal blood vessels

Purpose: The study of retinal blood vessel morphology is of great importance in retinal image analysis. The retinal blood vessels have a number of distinct features such as width, diameter, tortuosity, etc. In this paper, a method is proposed to measure the tortuosity of retinal blood vessels obtained from retinal fundus images. Tortuosity is a situation in which blood vessels become tortuous, that is, curved or non-smooth. It is one of the earliest changes that occur in blood vessels in some retinal diseases. Hence, its detection at an early stage can prevent the progression of retinal diseases such as diabetic retinopathy, hypertensive retinopathy, retinopathy of prematurity, etc. The present study focuses on the measurement of retinal blood vessel tortuosity for the analysis of hypertensive retinopathy. Hypertensive retinopathy is a condition in which the retinal vessels undergo changes and become tortuous due to long term high blood pressure. Early recognition of hypertensive retinopathy signs remains an important step in determining the target-organ damage and risk assessment of hypertensive patients. Hence, this paper attempts to estimate tortuosity using image-processing techniques that have been tested on artery and vein segments of retinal images. Design: Image processing-based model designed to measure blood vessel tortuosity. Methods: In this paper, a novel image processing-based model is proposed for tortuosity measurement. This parameter will be helpful for analyzing hypertensive retinopathy. To test the eff ectiveness of the system in determining tortuosity, the method is first applied on a set of synthetically generated blood vessels. Then, the method is repeated on blood vessel (both artery and vein) segments extracted from retinal images collected from publicly available databases and on images collected from a local eye hospital. The blood vessel segment images that are used in the method are binary images where blood vessels are represented by white pixels (foreground), while black pixels represent the background. Vessels are then classified into normal, moderately tortuous, and severely tortuous by following the analysis performed on the images in the Retinal Vessel Tortuosity Data Set (RET-TORT) obtained from BioIm Lab, Laboratory of Biomedical Imaging (Padova, Italy). This database consists of 30 artery segments and 30 vein segments, which were manually ordered on the basis of increasing tortuosity by Dr. S. Piermarocchi, a retinal specialist belonging to the Department of Ophthalmology of the University of Padova (Italy). The artery and vein segments with the fewest number of turns are given a low tortuosity ranking, while those with the greatest number of turns are given a high tortuosity ranking by the expert. Based on this concept, our proposed method defines retinal image segments as normal when they present the fewest number of twists/turns, moderately tortuous when they present more twists/turns than normal but fewer than severely tortuous vessels, and severely tortuous when they present a greater number of twists/turns than moderately tortuous vessels. On implementing our image processing-based method on binary blood vessel segment images that are represented by white pixels, it is found that the vessel pixel (white pixels) count increases with increasing vessel tortuosity. That is, for normal blood vessels, the white pixel count is less compared to moderately tortuous and severely tortuous vessels. It should be noted that the images obtained from the different databases and from the local hospital for this experiment are not hypertensive retinopathy images. Instead, they are mostly normal eye images and very few of them show tortuous blood vessels. Results: The results of the synthetically generated vessel segment images from the baseline for the evaluation of retinal blood vessel tortuosity. The proposed method is then applied on the retinal vessel segments that are obtained from the DRIVE and HRF databases, respectively. Finally, to evaluate the capability of the proposed method in determining the tortuosity level of the blood vessels, the method is tested with a standard tortuous database, namely, the RET-TORT database. The results are then compared with the tortuosity level mentioned in the database. It was found that our method is able to classify blood vessel images as normal, moderately tortuous, and severely tortuous, with results closely matching the clinical ordering provided by the expert in the RET-TORT database. Subjective evaluation was also performed by research scholars and postgraduate students to cross-validate the results. Conclusion: The close correlation between the tortuosity evaluation using the proposed method and the clinical ordering of retinal vessels as provided by the retinal specialist in the RET-TORT database shows that, although simple, this method can evaluate the tortuosity of vessel segments effectively.

Inflow mapping method for numerical flow simulations of OCT-based patient-specific vessels using CFD

Alteration of the flow characteristics in coronary vessels is correlated with coronary heart disease (CHD). In particular, wall shear stress (WSS) appears to be a hemody-namic key factor in the genesis of CHD. Since computational fluid dynamics (CFD) is a well-known method for the inves-tigation of WSS, it may be a valuable tool for the prediction of CHD. Latest imaging techniques, such as optical coher-ence tomography (OCT) in conjunction with angiography deliver precise 2D data sets of patient-specific vessel geome-try, which can be used for CFD analysis. Current CFD stud-ies utilize patient-specific geometries, but are lacking well defined physiologic inflow conditions.In this study, we present an inflow mapping method for patient-specific arterial vessels, which is capable of consider-ing the influence of bifurcations located proximal of the OCT-data set. At first, the patient-specific vessel was recon-structed. For this purpose the OCT-based vessel cross sec-tions were arranged along an angiographic based vessel pathway. Secondly, we simulated the flow field in a generic bifurcation model by means of CFD. Thereafter the flow field of a side branch was extracted and transferred (mapped) to the inlet of the patient-specific vessel.To evaluate the influence of the physiological inlet the WSS distribution of the same patient-specific vessel was calculated using an axial-symmetric inflow condition. Analy-sis of the simulation data yielded deviations of the WSS distribution in the proximal vessel segment. A bifurcation, located upstream of the relevant vessel segment strongly affects the flow in the OCT-based vessel reconstruction and has a strong influence on the results of the numerical analy-sis. Therefore, it is important to implement not only the pa-tient-specific geometry, but also an inlet boundary condition adapted to the upstream velocity distribution reflecting the actual proximal flow situation of the vessel.