Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms

Stenosis Detection and Quantification of Coronary Artery Using Machine Learning and Deep Learning

The aim of this review is to introduce some applications of artificial intelligence (AI) algorithms for the detection and quantification of coronary stenosis using computed tomography angiography (CTA). The realization of automatic/semi-automatic stenosis detection and quantification includes the following steps: vessel central axis extraction, vessel segmentation, stenosis detection, and quantification. Many new AI techniques, such as machine learning and deep learning, have been widely used in medical image segmentation and stenosis detection. This review also summarizes the recent progress regarding coronary stenosis detection and quantification, and discusses the development trends in this field. Through evaluation and comparison, researchers can better understand the research frontier in related fields, compare the advantages and disadvantages of various methods, and better optimize the new technologies. Machine learning and deep learning will promote the process of automatic detection and quantification of coronary artery stenosis. However, the machine learning and the deep learning methods need a large amount of data, so they also face some challenges because of the lack of professional image annotations (manually add labels by experts).

COACT: Coronary artery centerline tracker

BACKGROUND

The curved planar reformation (CPR) technique is one of the most commonly used methods in clinical practice to locate coronary arteries in medical images.

PURPOSE

The artery centerline is the cornerstone for the generation of the CPR image. Here, we describe the development of a new fully automatic artery centerline tracker with the aim of increasing the efficiency and accuracy of the process.

METHODS

We propose a COronary artery Centerline Tracker (COACT) framework which consists of an ostium point finder (OPFinder) model, an intersection point detector (IPDetector) model and a set of centerline tracking strategies. The output of OPFinder is the ostium points. The function of the IPDetector is to predict the intersections of a sample sphere and the centerlines. The centerline tracking process starts from two ostium points detected by the OPFinder, and combines the results of the IPDetector with a series of strategies to gradually reconstruct the coronary artery centerline tree.

RESULTS

Two coronary CT angiography (CCTA) datasets were used to validate the models. Dataset1 contains 160 cases (32 for test and 128 for training) and dataset2 contains 70 cases (20 for test and 50 for training). The results show that the average distance between the ostium points predicted by the OPFinder and the manually annotated ostium points was 0.88 mm, which is similar to the differences between the results obtained by two observers (0.85 mm). For the IPDetector, the average overlap of the predicted and ground truth intersection points was 97.82% and this is also close to the inter-observer agreement of 98.50%. For the entire coronary centerline tree, the overlap between the results obtained by COACT and the gold standard was 94.33%, which is slightly lower than the inter-observer agreement, 98.39%.

CONCLUSIONS

We have developed a fully automatic centerline tracking method for CCTA scans and achieved a satisfactory result. The proposed algorithms are also incorporated in the medical image analysis platform TIMESlice (https://slice-doc.netlify.app) for further studies.

Graph neural networks for automatic extraction and labeling of the coronary artery tree in CT angiography

Purpose

Automatic comprehensive reporting of coronary artery disease (CAD) requires anatomical localization of the coronary artery pathologies. To address this, we propose a fully automatic method for extraction and anatomical labeling of the coronary artery tree using deep learning.

Approach

We include coronary CT angiography (CCTA) scans of 104 patients from two hospitals. Reference annotations of coronary artery tree centerlines and labels of coronary artery segments were assigned to 10 segment classes following the American Heart Association guidelines. Our automatic method first extracts the coronary artery tree from CCTA, automatically placing a large number of seed points and simultaneous tracking of vessel-like structures from these points. Thereafter, the extracted tree is refined to retain coronary arteries only, which are subsequently labeled with a multi-resolution ensemble of graph convolutional neural networks that combine geometrical and image intensity information from adjacent segments.

Results

The method is evaluated on its ability to extract the coronary tree and to label its segments, by comparing the automatically derived and the reference labels. A separate assessment of tree extraction yielded an F 1 score of 0.85. Evaluation of our combined method leads to an average F 1 score of 0.74.

Conclusions

The results demonstrate that our method enables fully automatic extraction and anatomical labeling of coronary artery trees from CCTA scans. Therefore, it has the potential to facilitate detailed automatic reporting of CAD.

Deep Learning-Based Automated Labeling of Coronary Segments for Structured Reporting of Coronary Computed Tomography Angiography in Accordance With Society of Cardiovascular Computed Tomography Guidelines

PURPOSE

To evaluate a novel deep learning (DL)-based automated coronary labeling approach for structured reporting of coronary artery disease according to the guidelines of the Society of Cardiovascular Computed Tomography (CT) on coronary CT angiography (CCTA).

PATIENTS AND METHODS

A retrospective cohort of 104 patients (60.3 ± 10.7 y, 61% males) who had undergone prospectively electrocardiogram-synchronized CCTA were included. Coronary centerlines were automatically extracted, labeled, and validated by 2 expert readers according to Society of Cardiovascular CT guidelines. The DL algorithm was trained on 706 radiologist-annotated cases for the task of automatically labeling coronary artery centerlines. The architecture leverages tree-structured long short-term memory recurrent neural networks to capture the full topological information of the coronary trees by using a two-step approach: a bottom-up encoding step, followed by a top-down decoding step. The first module encodes each sub-tree into fixed-sized vector representations. The decoding module then selectively attends to the aggregated global context to perform the local assignation of labels. To assess the performance of the software, percentage overlap was calculated between the labels of the algorithm and the expert readers.

RESULTS

A total number of 1491 segments were identified. The artificial intelligence-based software approach yielded an average overlap of 94.4% compared with the expert readers' labels ranging from 87.1% for the posterior descending artery of the right coronary artery to 100% for the proximal segment of the right coronary artery. The average computational time was 0.5 seconds per case. The interreader overlap was 96.6%.

CONCLUSIONS

The presented fully automated DL-based coronary artery labeling algorithm provides fast and precise labeling of the coronary artery segments bearing the potential to improve automated structured reporting for CCTA.

Reconstructing microvascular network skeletons from 3D images: What is the ground truth?

Structural changes to microvascular networks are increasingly highlighted as markers of pathogenesis in a wide range of disease, e.g. Alzheimer's disease, vascular dementia and tumour growth. This has motivated the development of dedicated 3D imaging techniques, alongside the creation of computational modelling frameworks capable of using 3D reconstructed networks to simulate functional behaviours such as blood flow or transport processes. Extraction of 3D networks from imaging data broadly consists of two image processing steps: segmentation followed by skeletonisation. Much research effort has been devoted to segmentation field, and there are standard and widely-applied methodologies for creating and assessing gold standards or ground truths produced by manual annotation or automated algorithms. The Skeletonisation field, however, lacks widely applied, simple to compute metrics for the validation or optimisation of the numerous algorithms that exist to extract skeletons from binary images. This is particularly problematic as 3D imaging datasets increase in size and visual inspection becomes an insufficient validation approach. In this work, we first demonstrate the extent of the problem by applying 4 widely-used skeletonisation algorithms to 3 different imaging datasets. In doing so we show significant variability between reconstructed skeletons of the same segmented imaging dataset. Moreover, we show that such a structural variability propagates to simulated metrics such as blood flow. To mitigate this variability we introduce a new, fast and easy to compute super metric that compares the volume, connectivity, medialness, bifurcation point identification and homology of the reconstructed skeletons to the original segmented data. We then show that such a metric can be used to select the best performing skeletonisation algorithm for a given dataset, as well as to optimise its parameters. Finally, we demonstrate that the super metric can also be used to quickly identify how a particular skeletonisation algorithm could be improved, becoming a powerful tool in understanding the complex implication of small structural changes in a network.

Learning Better Registration to Learn Better Few-Shot Medical Image Segmentation: Authenticity, Diversity, and Robustness

In this work, we address the task of few-shot medical image segmentation (MIS) with a novel proposed framework based on the learning registration to learn segmentation (LRLS) paradigm. To cope with the limitations of lack of authenticity, diversity, and robustness in the existing LRLS frameworks, we propose the better registration better segmentation (BRBS) framework with three main contributions that are experimentally shown to have substantial practical merit. First, we improve the authenticity in the registration-based generation program and propose the knowledge consistency constraint strategy that constrains the registration network to learn according to the domain knowledge. It brings the semantic-aligned and topology-preserved registration, thus allowing the generation program to output new data with great space and style authenticity. Second, we deeply studied the diversity of the generation process and propose the space-style sampling program, which introduces the modeling of the transformation path of style and space change between few atlases and numerous unlabeled images into the generation program. Therefore, the sampling on the transformation paths provides much more diverse space and style features to the generated data effectively improving the diversity. Third, we first highlight the robustness in the learning of segmentation in the LRLS paradigm and propose the mix misalignment regularization, which simulates the misalignment distortion and constrains the network to reduce the fitting degree of misaligned regions. Therefore, it builds regularization for these regions improving the robustness of segmentation learning. Without any bells and whistles, our approach achieves a new state-of-the-art performance in few-shot MIS on two challenging tasks that outperform the existing LRLS-based few-shot methods. We believe that this novel and effective framework will provide a powerful few-shot benchmark for the field of medical image and efficiently reduce the costs of medical image research. All of our code will be made publicly available online.

Using Deep Learning and B-Splines to Model Blood Vessel Lumen from 3D Images

Accurate geometric modeling of blood vessel lumen from 3D images is crucial for vessel quantification as part of the diagnosis, treatment, and monitoring of vascular diseases. Our method, unlike other approaches which assume a circular or elliptical vessel cross-section, employs parametric B-splines combined with image formation system equations to accurately localize the highly curved lumen boundaries. This approach avoids the need for image segmentation, which may reduce the localization accuracy due to spatial discretization. We demonstrate that the model parameters can be reliably identified by a feedforward neural network which, driven by the cross-section images, predicts the parameter values many times faster than a reference least-squares (LS) model fitting algorithm. We present and discuss two example applications, modeling the lower extremities of artery-vein complexes visualized in steady-state contrast-enhanced magnetic resonance images (MRI) and the coronary arteries pictured in computed tomography angiograms (CTA). Beyond applications in medical diagnosis, blood-flow simulation and vessel-phantom design, the method can serve as a tool for automated annotation of image datasets to train machine-learning algorithms.

AVDNet: Joint coronary artery and vein segmentation with topological consistency

Coronary CT angiography (CCTA) is an effective and non-invasive method for coronary artery disease diagnosis. Extracting an accurate coronary artery tree from CCTA image is essential for centerline extraction, plaque detection, and stenosis quantification. In practice, data quality varies. Sometimes, the arteries and veins have similar intensities and locate closely, which may confuse segmentation algorithms, even deep learning based ones, to obtain accurate arteries. However, it is not always feasible to re-scan the patient for better image quality. In this paper, we propose an artery and vein disentanglement network (AVDNet) for robust and accurate segmentation by incorporating the coronary vein into the segmentation task. This is the first work to segment coronary artery and vein at the same time. The AVDNet consists of an image based vessel recognition network (IVRN) and a topology based vessel refinement network (TVRN). IVRN learns to segment the arteries and veins, while TVRN learns to correct the segmentation errors based on topology consistency. We also design a novel inverse distance weighted dice (IDD) loss function to recover more thin vessel branches and preserve the vascular boundaries. Extensive experiments are conducted on a multi-center dataset of 700 patients. Quantitative and qualitative results demonstrate the effectiveness of the proposed method by comparing it with state-of-the-art methods and different variants. Prediction results of the AVDNet on the Automated Segmentation of Coronary Artery Challenge dataset are avaliabel at https://github.com/WennyJJ/Coronary-Artery-Vein-Segmentation for follow-up research.

Automated Coronary Artery Tracking with a Voronoi-Based 3D Centerline Extraction Algorithm

Coronary artery disease is one of the leading causes of death worldwide, and medical imaging methods such as coronary artery computed tomography are vitally important in its detection. More recently, various computational approaches have been proposed to automatically extract important artery coronary features (e.g., vessel centerlines, cross-sectional areas along vessel branches, etc.) that may ultimately be able to assist with more accurate and timely diagnoses. The current study therefore validated and benchmarked a recently developed automated 3D centerline extraction method for coronary artery centerline tracking using synthetically segmented coronary artery models based on the widely used Rotterdam Coronary Artery Algorithm Evaluation Framework (RCAAEF) training dataset. Based on standard accuracy metrics and the ground truth centerlines of all 32 coronary vessel branches in the RCAAEF training dataset, this 3D divide and conquer Voronoi diagram method performed exceptionally well, achieving an average overlap accuracy (OV) of 99.97%, overlap until first error (OF) of 100%, overlap of the clinically relevant portion of the vessel (OT) of 99.98%, and an average error distance inside the vessels (AI) of only 0.13 mm. Accuracy was also found to be exceptionally for all four coronary artery sub-types, with average OV values of 99.99% for right coronary arteries, 100% for left anterior descending arteries, 99.96% for left circumflex arteries, and 100% for large side-branch vessels. These results validate that the proposed method can be employed to quickly, accurately, and automatically extract 3D centerlines from segmented coronary arteries, and indicate that it is likely worthy of further exploration given the importance of this topic.

Relationships between the coronary fat attenuation index for patients with heart-related disease measured automatically on coronary computed tomography angiography and coronary adverse events and degree of coronary stenosis

Background

Pericoronary artery coronary tissue (PACT) is a type of epicardial fat that can reflect the state of the coronary artery (inflammation, etc.). However, it cannot be reasonably and efficiently utilized in routine computed tomography (CT) examination. The aim of this study was to use artificial intelligence (AI) software to analyze coronary computed tomography angiography (CCTA) and measure the coronary perivascular fat attenuation index (FAI) of patients. The relationship between FAI and the occurrence of coronary adverse events and the degree of coronary stenosis were further analyzed.

Methods

This study involved patients who experienced CCTA in West China Hospital, Sichuan University, from January 2012 to December 2012. These patients were followed up to 2020 and classified according to the occurrence of coronary adverse events and the degree of stenosis of the lumen. For all patients, AI software was used to analyze the CCTA images of patients, and the FAI of 3 coronary arteries, the left anterior descending artery (LAD), the left circumflex artery (LCX), and the right coronary artery (RCA), was measured. Moreover, the relationship between FAI and patients with different degrees of coronary stenosis and adverse coronary events was determined.

Results

Comparisons between any 2 groups showed that the differences in the FAI among the 4 groups for the LAD were significant (all P values <0.05). There were no significant differences between the group with less-than-moderate stenosis (Mb) without adverse events and the group with moderate-or-above stenosis (M) with no adverse events for the LCX (P>0.05). For the remaining groups, FAI values exhibited statistically significant differences (P<0.05). According to the degree of lumen stenosis, the patients were divided into groups according to LAD, LCX, and RCA and the sum of the 3 vessels. There were significant differences in coronary FAI among the groups with different degrees of lumen stenosis for the sum of the 3 vessels, the LAD, and the LCX (P<0.05).

Conclusions

FAI can reflect the state of the coronary artery, which is related to inflammation of the coronary lumen. Moreover, there is a relationship between FAI and the degree of stenosis in the coronary lumen: the narrower the coronary lumen is, the higher the FAI around the lumen.

A deep learning-based automated algorithm for labeling coronary arteries in computed tomography angiography images

OBJECTIVE

Using two three-dimensional U-Net architectures for myocardium structure extraction and a distance transformation algorithm specifically for the left circumflex artery, we have designed a fully automated algorithm for coronary artery labeling in coronary computed tomography angiography (CCTA) images.

METHODS

In this retrospective analysis, a cohort of 157 patients who had undergone coronary computed tomography angiography (CCTA) was included. An automated coronary artery labeling algorithm was developed using a distance transformation approach to delineate the anatomical segments along the centerlines extracted from the CCTA images. A total of 16 segments were successfully identified and labeled. The algorithm's outcomes were recorded and reviewed by three experts, and the performance of segment detection and labeling was assessed. Additionally, the level of agreement in manually labeled segments between two experts was quantified.

RESULTS

When comparing the labels generated by the experts with those produced by the algorithm, it was necessary to modify or eliminate 117 labels (5.4%) out of 2180 segments assigned by the algorithm. The overall accuracy for label presence was 96.2%, with an average overlap of 94.0% between the expert reference and algorithm-generated labels. Furthermore, the average agreement rate between the two experts stood at 95.0%.

CONCLUSIONS

Based on the labels of the clinical experts, the proposed deep learning algorithm exhibits high accuracy for automatic labeling. Therefore, our proposed method exhibits promising results for the automatic labeling of the coronary arteries and will alleviate the burden on radiologists in the near future.

ImageCAS: A large-scale dataset and benchmark for coronary artery segmentation based on computed tomography angiography images

Cardiovascular disease (CVD) accounts for about half of non-communicable diseases. Vessel stenosis in the coronary artery is considered to be the major risk of CVD. Computed tomography angiography (CTA) is one of the widely used noninvasive imaging modalities in coronary artery diagnosis due to its superior image resolution. Clinically, segmentation of coronary arteries is essential for the diagnosis and quantification of coronary artery disease. Recently, a variety of works have been proposed to address this problem. However, on one hand, most works rely on in-house datasets, and only a few works published their datasets to the public which only contain tens of images. On the other hand, their source code have not been published, and most follow-up works have not made comparison with existing works, which makes it difficult to judge the effectiveness of the methods and hinders the further exploration of this challenging yet critical problem in the community. In this paper, we propose a large-scale dataset for coronary artery segmentation on CTA images. In addition, we have implemented a benchmark in which we have tried our best to implement several typical existing methods. Furthermore, we propose a strong baseline method which combines multi-scale patch fusion and two-stage processing to extract the details of vessels. Comprehensive experiments show that the proposed method achieves better performance than existing works on the proposed large-scale dataset. The benchmark and the dataset are published at https://github.com/XiaoweiXu/ImageCAS-A-Large-Scale-Dataset-and-Benchmark-for-Coronary-Artery-Segmentation-based-on-CT.

Mining multi-center heterogeneous medical data with distributed synthetic learning

Overcoming barriers on the use of multi-center data for medical analytics is challenging due to privacy protection and data heterogeneity in the healthcare system. In this study, we propose the Distributed Synthetic Learning (DSL) architecture to learn across multiple medical centers and ensure the protection of sensitive personal information. DSL enables the building of a homogeneous dataset with entirely synthetic medical images via a form of GAN-based synthetic learning. The proposed DSL architecture has the following key functionalities: multi-modality learning, missing modality completion learning, and continual learning. We systematically evaluate the performance of DSL on different medical applications using cardiac computed tomography angiography (CTA), brain tumor MRI, and histopathology nuclei datasets. Extensive experiments demonstrate the superior performance of DSL as a high-quality synthetic medical image provider by the use of an ideal synthetic quality metric called Dist-FID. We show that DSL can be adapted to heterogeneous data and remarkably outperforms the real misaligned modalities segmentation model by 55% and the temporal datasets segmentation model by 8%.

3D vessel extraction using a scale-adaptive hybrid parametric tracker

3D vessel extraction has great significance in the diagnosis of vascular diseases. However, accurate extraction of vessels from computed tomography angiography (CTA) data is challenging. For one thing, vessels in different body parts have a wide range of scales and large curvatures; for another, the intensity distributions of vessels in different CTA data vary considerably. Besides, surrounding interfering tissue, like bones or veins with similar intensity, also seriously affects vessel extraction. Considering all the above imaging and structural features of vessels, we propose a new scale-adaptive hybrid parametric tracker (SAHPT) to extract arbitrary vessels of different body parts. First, a geometry-intensity parametric model is constructed to calculate the geometry-intensity response. While geometry parameters are calculated to adapt to the variation in scale, intensity parameters can also be estimated to meet non-uniform intensity distributions. Then, a gradient parametric model is proposed to calculate the gradient response based on a multiscale symmetric normalized gradient filter which can effectively separate the target vessel from surrounding interfering tissue. Last, a hybrid parametric model that combines the geometry-intensity and gradient parametric models is constructed to evaluate how well it fits a local image patch. In the extraction process, a multipath spherical sampling strategy is used to solve the problem of anatomical complexity. We have conducted many quantitative experiments using the synthetic and clinical CTA data, asserting its superior performance compared to traditional or deep learning-based baselines.

The Association of Coronary Fat Attenuation Index Quantified by Automated Software on Coronary Computed Tomography Angiography with Adverse Events in Patients with Less than Moderate Coronary Artery Stenosis

OBJECTIVE

This study analyzed the relationship between the coronary FAI on CCTA and coronary adverse events in patients with moderate coronary artery disease based on machine learning.

METHODS

A total of 172 patients with coronary artery disease with moderate or lower coronary artery stenosis were included. According to whether the patients had coronary adverse events, the patients were divided into an adverse group and a non-adverse group. The coronary FAI of patients was quantified via machine learning, and significant differences between the two groups were analyzed via t-test.

RESULTS

The age difference between the two groups was statistically significant (p < 0.001). The group that had adverse reactions was older, and there was no statistically significant difference between the two groups in terms of sex and smoking status. There was no statistical significance in the blood biochemical indexes between the two groups (p > 0.05). There was a significant difference in the FAIs between the two groups (p < 0.05), with the FAI of the defective group being greater than that of the nonperforming group. Taking the age of patients as a covariate, an analysis of covariance showed that after excluding the influence of age, the FAIs between the two groups were still significantly different (p < 0.001).

LIVE-Net: Comprehensive 3D vessel extraction framework in CT angiography

The extraction of vessels from computed tomography angiography (CTA) is significant in diagnosing and evaluating vascular diseases. However, due to the anatomical complexity, wide intensity distribution, and small volume proportion of vessels, vessel extraction is laborious and time-consuming, and it is easy to lead to error-prone diagnostic results in clinical practice. This study proposes a novel comprehensive vessel extraction framework, called the Local Iterative-based Vessel Extraction Network (LIVE-Net), to achieve 3D vessel segmentation while tracking vessel centerlines. LIVE-Net contains dual dataflow pathways that work alternately: an iterative tracking network and a local segmentation network. The former can generate the fine-grain direction and radius prediction of a vascular patch by using the attention-embedded atrous pyramid network (aAPN), and the latter can achieve 3D vascular lumen segmentation by constructing the multi-order self-attention U-shape network (MOSA-UNet). LIVE-Net is trained and evaluated on two datasets: the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08) dataset and head and neck CTA dataset from the clinic. Experimental results of both tracking and segmentation show that our proposed LIVE-Net exhibits superior performance compared with other state-of-the-art (SOTA) networks. In the CAT08 dataset, the tracked centerlines have an average overlap of 95.2%, overlap until first error of 91.2%, overlap with the clinically relevant vessels of 98.3%, and error distance inside of 0.21 mm. The corresponding tracking overlap metrics in the head and neck CTA dataset are 96.7%, 91.0%, and 99.8%, respectively. In addition, the results of the consistent experiment also show strong clinical correspondence. For the segmentation of bilateral carotid and vertebral arteries, our method can not only achieve better accuracy with an average dice similarity coefficient (DSC) of 90.03%, Intersection over Union (IoU) of 81.97%, and 95% Hausdorff distance (95%HD) of 3.42 mm , but higher efficiency with an average time of 67.25 s , even three times faster compared to some methods applied in full field view. Both the tracking and segmentation results prove the potential clinical utility of our network.

Prior skeleton based online deep reinforcement learning for coronary artery centerline extraction

Coronary centerline extraction is an essential technique for X-ray coronary angiography (XCA) image analysis, which provides qualitative and quantitative guidance for percutaneous coronary intervention (PCI). In this paper, an online deep reinforcement learning method for coronary centerline extraction is proposed based on the prior vascular skeleton. Firstly, with XCA image preprocessing (foreground extraction and vessel segmentation) results, the improved ZhangSuen image thinning algorithm is used to rapidly extract the preliminary vascular skeleton network. On this basis, according to the spatial-temporal and morphological continuity of the angiography image sequence, the connectivity of different branches is determined using k-means clustering, and the vessel segments are then grouped, screened, and reconnected to obtain the aorta and its major branches. Finally, using the previous results as prior information, an online Deep Q-Network (DQN) reinforcement learning method is proposed to optimize each branch simultaneously. It comprehensively considers grayscale intensity and eigenvector continuity to achieve the combination of data-driven and model-driven without pre-training. Experimental results on clinical images and the third-party dataset demonstrate that the proposed method can accurately extract, restructure, and optimize the centerline of XCA images with a higher overall accuracy than the existing state-of-the-art methods.

A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation

Automatic segmentation of coronary arteries provides vital assistance to enable accurate and efficient diagnosis and evaluation of coronary artery disease (CAD). However, the task of coronary artery segmentation (CAS) remains highly challenging due to the large-scale variations exhibited by coronary arteries, their complicated anatomical structures and morphologies, as well as the low contrast between vessels and their background. To comprehensively tackle these challenges, we propose a novel multi-attention, multi-scale 3D deep network for CAS, which we call CAS-Net. Specifically, we first propose an attention-guided feature fusion (AGFF) module to efficiently fuse adjacent hierarchical features in the encoding and decoding stages to capture more effectively latent semantic information. Then, we propose a scale-aware feature enhancement (SAFE) module, aiming to dynamically adjust the receptive fields to extract more expressive features effectively, thereby enhancing the feature representation capability of the network. Furthermore, we employ the multi-scale feature aggregation (MSFA) module to learn a more distinctive semantic representation for refining the vessel maps. In addition, considering that the limited training data annotated with a quality golden standard are also a significant factor restricting the development of CAS, we construct a new dataset containing 119 cases consisting of coronary computed tomographic angiography (CCTA) volumes and annotated coronary arteries. Extensive experiments on our self-collected dataset and three publicly available datasets demonstrate that the proposed method has good segmentation performance and generalization ability, outperforming multiple state-of-the-art algorithms on various metrics. Compared with U-Net3D, the proposed method significantly improves the Dice similarity coefficient (DSC) by at least 4% on each dataset, due to the synergistic effect among the three core modules, AGFF, SAFE, and MSFA. Our implementation is released at https://github.com/Cassie-CV/CAS-Net.

Annotated computed tomography coronary angiogram images and associated data of normal and diseased arteries

Computed Tomography Coronary Angiography (CTCA) is a non-invasive method to evaluate coronary artery anatomy and disease. CTCA is ideal for geometry reconstruction to create virtual models of coronary arteries. To our knowledge there is no public dataset that includes centrelines and segmentation of the full coronary tree. We provide anonymized CTCA images, voxel-wise annotations and associated data in the form of centrelines, calcification scores and meshes of the coronary lumen in 20 normal and 20 diseased cases. Images were obtained along with patient information with informed, written consent as part of the Coronary Atlas. Cases were classified as normal (zero calcium score with no signs of stenosis) or diseased (confirmed coronary artery disease). Manual voxel-wise segmentations by three experts were combined using majority voting to generate the final annotations. Provided data can be used for a variety of research purposes, such as 3D printing patient-specific models, development and validation of segmentation algorithms, education and training of medical personnel and in-silico analyses such as testing of medical devices.

Continuous extraction of coronary artery centerline from cardiac CTA images using a regression-based method

Coronary artery centerline extraction in cardiac computed tomography angiography (CTA) is an effectively non-invasive method to diagnose and evaluate coronary artery disease (CAD). The traditional method of manual centerline extraction is time-consuming and tedious. In this study, we propose a deep learning algorithm that continuously extracts coronary artery centerlines from CTA images using a regression method. In the proposed method, a CNN module is trained to extract the features of CTA images, and then the branch classifier and direction predictor are designed to predict the most possible direction and lumen radius at the given centerline point. Besides, a new loss function is developed for associating the direction vector with the lumen radius. The whole process starts from a point manually placed at the coronary artery ostia, and terminates until tracking the vessel endpoint. The network was trained using a training set consisting of 12 CTA images and the evaluation was performed using a testing set consisting of 6 CTA images. The extracted centerlines had an average overlap (OV) of 89.19%, overlap until first error (OF) of 82.30%, and overlap with clinically relevant vessel (OT) of 91.42% with manually annotated reference. Our proposed method can efficiently deal with multi-branch problems and accurately detect distal coronary arteries, thereby providing potential help in assisting CAD diagnosis.

A novel end-to-end deep learning solution for coronary artery segmentation from CCTA

PURPOSE

Coronary computed tomographic angiography (CCTA) plays a vital role in the diagnosis of cardiovascular diseases, among which automatic coronary artery segmentation (CAS) serves as one of the most challenging tasks. To computationally assist the task, this paper proposes a novel end-to-end deep learning-based (DL) solution for automatic CAS.

METHODS

Inspired by the Di-Vnet network, a fully automatic multistage DL solution is proposed. The new solution aims to preserve the integrity of blood vessels in terms of both their shape details and continuity. The solution is developed using 338 CCTA cases, among which 133 cases (33865 axial images) have their ground-truth cardiac masks pre-annotated and 205 cases (53365 axial images) have their ground-truth coronary artery (CA) masks pre-annotated. The solution's accuracy is measured using dice similarity coefficient (DSC), 95th percentile Hausdorff Distance (95% HD), Recall, and Precision scores for CAS.

RESULTS

The proposed solution attains 90.29% in DSC, 2.11 mm in 95% HD, 97.02% in Recall, and 92.17% in Precision, respectively, which consumes 0.112 s per image and 30 s per case on average. Such performance of our method is superior to other state-of-the-art segmentation methods.

CONCLUSIONS

The novel DL solution is able to automatically learn to perform CAS in an end-to-end fashion, attaining a high accuracy, efficiency and robustness simultaneously.

Automated Coronary Optical Coherence Tomography Feature Extraction with Application to Three-Dimensional Reconstruction

Coronary optical coherence tomography (OCT) is an intravascular, near-infrared light-based imaging modality capable of reaching axial resolutions of 10–20 µm. This resolution allows for accurate determination of high-risk plaque features, such as thin cap fibroatheroma; however, visualization of morphological features alone still provides unreliable positive predictive capability for plaque progression or future major adverse cardiovascular events (MACE). Biomechanical simulation could assist in this prediction, but this requires extracting morphological features from intravascular imaging to construct accurate three-dimensional (3D) simulations of patients’ arteries. Extracting these features is a laborious process, often carried out manually by trained experts. To address this challenge, numerous techniques have emerged to automate these processes while simultaneously overcoming difficulties associated with OCT imaging, such as its limited penetration depth. This systematic review summarizes advances in automated segmentation techniques from the past five years (2016–2021) with a focus on their application to the 3D reconstruction of vessels and their subsequent simulation. We discuss four categories based on the feature being processed, namely: coronary lumen; artery layers; plaque characteristics and subtypes; and stents. Areas for future innovation are also discussed as well as their potential for future translation.

Automatic construction of coronary artery tree structure based on vessel blood flow tracking

We sought to propose an innovative vessel blood flow tracking (VBFT) method to extract coronary artery tree (CAT) and to assess the effectiveness of this VBFT versus the single-frame method. Construction of a CAT from a segmented artery is the basis of artificial intelligence-aided angiographic diagnosis. However, construction of a CAT using a single frame remains challenging, due to bifurcations and overlaps in two-dimensional angiograms. Overall, 13,222 angiograms, including 28,539 vessels, were retrospectively collected from 3275 patients and were then annotated. Coronary arteries were automatically segmented by a previously established deep neural networks (DNNs), and the skeleton lines were then extracted from segmentation images to construct CAT using the single-frame method and the VBFT method. Additionally, 1322 angiograms with 2201 vessels were used to test these two methods. Compared to the single-frame method, the VBFT method can significantly improve the accuracy of CAT as (84.3% vs. 72.3%; p < 0.001). Overlap (OV) was higher in the VBFT group than that in the Single-Frame group (91.1% vs. 87.5%; p < 0.001). The VBFT method significantly reduced the incidence of the lack of branching (7.30% vs. 13.9%, p < 0.001), insufficient length (6.70% vs. 11.0%, p < 0.001), and redundant branches (1.60% vs. 3.10%, p < 0.001). The VBFT method improved the extraction of a CAT structure, which will facilitate the development of artificial intelligence-aided angiographic diagnosis. Cardiologists can efficiently diagnose CAD using this method.

Voxel-Wise Adversarial FiboNet for 3D Cerebrovascular Segmentation on Magnetic Resonance Angiography Images

Cerebrovascular segmentation is important in various clinical applications, such as surgical planning and computer-aided diagnosis. In order to achieve high segmentation performance, three challenging problems should be taken into consideration: (1) large variations in vascular anatomies and voxel intensities; (2) severe class imbalance between foreground and background voxels; (3) image noise with different magnitudes. Limited accuracy was achieved without considering these challenges in deep learning-based methods for cerebrovascular segmentation. To overcome the limitations, we propose an end-to-end adversarial model called FiboNet-VANGAN. Specifically, our contributions can be summarized as follows: (1) to relieve the first problem mentioned above, a discriminator is proposed to regularize for voxel-wise distribution consistency between the segmentation results and the ground truth; (2) to mitigate the problem of class imbalance, we propose to use the addition of cross-entropy and Dice coefficient as the loss function of the generator. Focal loss is utilized as the loss function of the discriminator; (3) a new feature connection is proposed, based on which a generator called FiboNet is built. By incorporating Dice coefficient in the training of FiboNet, noise robustness can be improved by a large margin. We evaluate our method on a healthy magnetic resonance angiography (MRA) dataset to validate its effectiveness. A brain atrophy MRA dataset is also collected to test the performance of each method on abnormal cases. Results show that the three problems in cerebrovascular segmentation mentioned above can be alleviated and high segmentation accuracy can be achieved on both datasets using our method.

Examinee-Examiner Network: Weakly Supervised Accurate Coronary Lumen Segmentation Using Centerline Constraint

Accurate coronary lumen segmentation on coronary-computed tomography angiography (CCTA) images is crucial for quantification of coronary stenosis and the subsequent computation of fractional flow reserve. Many factors including difficulty in labeling coronary lumens, various morphologies in stenotic lesions, thin structures and small volume ratio with respect to the imaging field complicate the task. In this work, we fused the continuity topological information of centerlines which are easily accessible, and proposed a novel weakly supervised model, Examinee-Examiner Network (EE-Net), to overcome the challenges in automatic coronary lumen segmentation. First, the EE-Net was proposed to address the fracture in segmentation caused by stenoses by combining the semantic features of lumens and the geometric constraints of continuous topology obtained from the centerlines. Then, a Centerline Gaussian Mask Module was proposed to deal with the insensitiveness of the network to the centerlines. Subsequently, a weakly supervised learning strategy, Examinee-Examiner Learning, was proposed to handle the weakly supervised situation with few lumen labels by using our EE-Net to guide and constrain the segmentation with customized prior conditions. Finally, a general network layer, Drop Output Layer, was proposed to adapt to the class imbalance by dropping well-segmented regions and weights the classes dynamically. Extensive experiments on two different data sets demonstrated that our EE-Net has good continuity and generalization ability on coronary lumen segmentation task compared with several widely used CNNs such as 3D-UNet. The results revealed our EE-Net with great potential for achieving accurate coronary lumen segmentation in patients with coronary artery disease. Code at http://github.com/qiyaolei/Examinee-Examiner-Network.

Coronary Artery Extraction from CT Coronary Angiography with Augmentation on Partially Labelled Data

Coronary artery disease (CAD) is an important cause of morbidity and mortality. CT coronary angiography is considered as first-line of investigation in patients suspected of having CAD. Coronary artery centerline extraction is a challenging prerequisite for coronary artery stenosis evaluation. These challenges include the small and complex structure, variation of plaques and imaging noise. Deep learning methods often require adequate annotated data to build a good model. This work aims to adopt a dataset that has partial annotation to augment the data to train a Coronary Neural Network (CorNN) to track the coronary artery centerline. We combined a small training dataset with densely labelled centerline and radius, augmented with a larger dataset with only the centerline sparsely labelled to train networks to track centerlines from 3D computed tomography coronary angiography. The vessel orientation estimation is patch based, with or without additional radius prediction. The patch data are carefully positioned and sampled, which are tagged with the orientations computed based on the centerlines. Our experiment results show that, with the augmentation of the new data, although partially annotated, nearly 10% or more improvement has been achieved for the coronary artery extraction by the proposed approach.

Improved Centerline Extraction in Fully Automated Coronary Ostium Localization and Centerline Extraction Framework using Deep Learning

Coronary artery extraction in cardiac CT angiography (CCTA) image volume is a necessary step for any quantitative assessment of stenoses and atherosclerotic plaque. In this work, we propose a fully automated workflow that depends on convolutional networks to extract the centerlines of the coronary arteries from CCTA image volumes, starting from identifying the ostium points and then tracking the vessel till its end based on its radius and direction. First, a regression U-Net is employed to identify the ostium points in the image volume, then these points are fed to an orientation and radius predictor CNN model to track and extract each artery till its end point. Our results show that an average of 96% of the ostium points were identified and located within less than 5mm from their true location. The coronary arteries centerlines extraction was performed with high accuracy and lower number of training parameters making it suitable for real clinical applications and continuous learning.

AI-Based Quantification of Planned Radiation Therapy Dose to Cardiac Structures and Coronary Arteries in Patients With Breast Cancer

PURPOSE

The purpose of this work is to develop and evaluate an automatic deep learning method for segmentation of cardiac chambers and large arteries, and localization of the 3 main coronary arteries in radiation therapy planning on computed tomography (CT). In addition, a second purpose is to determine the planned radiation therapy dose to cardiac structures for breast cancer therapy.

METHODS AND MATERIALS

Eighteen contrast-enhanced cardiac scans acquired with a dual-layer-detector CT scanner were included for method development. Manual reference annotations of cardiac chambers, large arteries, and coronary artery locations were made in the contrast scans and transferred to virtual noncontrast images, mimicking noncontrast-enhanced CT. In addition, 31 noncontrast-enhanced radiation therapy treatment planning CTs with corresponding dose-distribution maps of breast cancer cases were included for evaluation. For reference, cardiac chambers and large vessels were manually annotated in two 2-dimensional (2D) slices per scan (26 scans, totaling 52 slices) and in 3-dimensional (3D) scan volumes in 5 scans. Coronary artery locations were annotated on 3D imaging. The method uses an ensemble of convolutional neural networks with 2 output branches that perform 2 distinct tasks: (1) segmentation of the cardiac chambers and large arteries and (2) localization of coronary arteries. Training was performed using reference annotations and virtual noncontrast cardiac scans. Automatic segmentation of the cardiac chambers and large vessels and the coronary artery locations was evaluated in radiation therapy planning CT with Dice score (DSC) and average symmetrical surface distance (ASSD). The correlation between dosimetric parameters derived from the automatic and reference segmentations was evaluated with R².

RESULTS

For cardiac chambers and large arteries, median DSC was 0.76 to 0.88, and the median ASSD was 0.17 to 0.27 cm in 2D slice evaluation. 3D evaluation found a DSC of 0.87 to 0.93 and an ASSD of 0.07 to 0.10 cm. Median DSC of the coronary artery locations ranged from 0.80 to 0.91. R² values of dosimetric parameters were 0.77 to 1.00 for the cardiac chambers and large vessels, and 0.76 to 0.95 for the coronary arteries.

CONCLUSIONS

The developed and evaluated method can automatically obtain accurate estimates of planned radiation dose and dosimetric parameters for the cardiac chambers, large arteries, and coronary arteries.

Deep Reinforcement Learning with Explicit Spatio-Sequential Encoding Network for Coronary Ostia Identification in CT Images

Accurate identification of the coronary ostia from 3D coronary computed tomography angiography (CCTA) is a essential prerequisite step for automatically tracking and segmenting three main coronary arteries. In this paper, we propose a novel deep reinforcement learning (DRL) framework to localize the two coronary ostia from 3D CCTA. An optimal action policy is determined using a fully explicit spatial-sequential encoding policy network applying 2.5D Markovian states with three past histories. The proposed network is trained using a dueling DRL framework on the CAT08 dataset. The experiment results show that our method is more efficient and accurate than the other methods. blueFloating-point operations (FLOPs) are calculated to measure computational efficiency. The result shows that there are 2.5M FLOPs on the proposed method, which is about 10 times smaller value than 3D box-based methods. In terms of accuracy, the proposed method shows that 2.22 ± 1.12 mm and 1.94 ± 0.83 errors on the left and right coronary ostia, respectively. The proposed method can be applied to the tasks to identify other target objects by changing the target locations in the ground truth data. Further, the proposed method can be utilized as a pre-processing method for coronary artery tracking methods.

Deep Recursive Bayesian Tracking for Fully Automatic Centerline Extraction of Coronary Arteries in CT Images

Extraction of coronary arteries in coronary computed tomography (CT) angiography is a prerequisite for the quantification of coronary lesions. In this study, we propose a tracking method combining a deep convolutional neural network (DNN) and particle filtering method to identify the trajectories from the coronary ostium to each distal end from 3D CT images. The particle filter, as a non-linear approximator, is an appropriate tracking framework for such thin and elongated structures; however, the robust 'vesselness' measurement is essential for extracting coronary centerlines. Importantly, we employed the DNN to robustly measure the vesselness using patch images, and we integrated softmax values to the likelihood function in our particle filtering framework. Tangent patches represent cross-sections of coronary arteries of circular shapes. Thus, 2D tangent patches are assumed to include enough features of coronary arteries, and the use of 2D patches significantly reduces computational complexity. Because coronary vasculature has multiple bifurcations, we also modeled a method to detect branching sites by clustering the particle locations. The proposed method is compared with three commercial workstations and two conventional methods from the academic literature.

Automatic Aortic Dissection Centerline Extraction Via Morphology-Guided CRN Tracker

Aortic dissection (AD) centerline extraction has important clinical value in the quantitative diagnosis and treatment of AD disease. However, AD centerline extraction is a difficult task and quantitative evaluation is rarely studied. In this work, we propose a fully automatic algorithm to extract AD centerline based on a convolutional regression network (CRN) and the morphological properties of AD. To this end, we first design a topological model to describe the complex topology of AD. With this model, CRNs are trained to estimate the position, tangential vector, and scale of the centerline. The tracking accuracy is further improved by centerline continuity and a gradient-based penalty function. In addition, seed points are extracted on the basis of random regression and line clustering to ensure automated vessel tracking. The proposed method has been evaluated on an AD database and a public aortic database, and achieved high overlapping ratios of 0.9610 and 1.0000, respectively. The tracked centerline is very close to the ground truth and shows good stability, with low average distance errors of 1.4720 mm and 1.8748 mm, respectively.

Accuracy of registration techniques and vascular imaging modalities in fusion imaging for aortic endovascular interventions: a phantom study

Background

This study aimed to assess the error of different registration techniques and imaging modalities for fusion imaging of the aorta in a standardized setting using a anthropomorphic body phantom.

Materials and methods

A phantom with the 3D printed vasculature of a patient suffering from an infrarenal aortic aneurysm was constructed. Pulsatile flow was generated via an external pump. CTA/MRA of the phantom was performed, and a virtual 3D vascular model was computed. Subsequently, fusion imaging was performed employing 3D-3D and 2D-3D registration techniques. Accuracy of the registration was evaluated from 7 right/left anterior oblique c-arm angulations using the agreement of centerlines and landmarks between the phantom vessels and the virtual 3D virtual vascular model. Differences between imaging modalities were assessed in a head-to-head comparison based on centerline deviation. Statistics included the comparison of means ± standard deviations, student’s t-test, Bland-Altman analysis, and intraclass correlation coefficient for intra- and inter-reader analysis.

Results

3D-3D registration was superior to 2D-3D registration, with the highest mean centerline deviation being 1.67 ± 0.24 mm compared to 4.47 ± 0.92 mm. The highest absolute deviation was 3.25 mm for 3D-3D and 6.25 mm for 2D-3D registration. Differences for all angulations between registration techniques reached statistical significance. A decrease in registration accuracy was observed for c-arm angulations beyond 30° right anterior oblique/left anterior oblique. All landmarks (100%) were correctly positioned using 3D-3D registration compared to 81% using 2D-3D registration. Differences in accuracy between CT and MRI were acceptably small. Intra- and inter-reader reliability was excellent.

Conclusion

In the realm of registration techniques, the 3D-3D method proved more accurate than did the 2D-3D method. Based on our data, the use of 2D-3D registration for interventions with high registration quality requirements (e.g., fenestrated aortic repair procedures) cannot be fully recommended. Regarding imaging modalities, CTA and MRA can be used equivalently.

Coronary Centerline Extraction from CCTA Using 3D-UNet

The mesh-type coronary model, obtained from three-dimensional reconstruction using the sequence of images produced by computed tomography (CT), can be used to obtain useful diagnostic information, such as extracting the projection of the lumen (planar development along an artery). In this paper, we have focused on automated coronary centerline extraction from cardiac computed tomography angiography (CCTA) proposing a 3D version of U-Net architecture, trained with a novel loss function and with augmented patches. We have obtained promising results for accuracy (between 90–95%) and overlap (between 90–94%) with various network training configurations on the data from the Rotterdam Coronary Artery Centerline Extraction benchmark. We have also demonstrated the ability of the proposed network to learn despite the huge class imbalance and sparse annotation present in the training data.

Artificial Intelligence to Assist in Exclusion of Coronary Atherosclerosis During CCTA Evaluation of Chest Pain in the Emergency Department: Preparing an Application for Real-world Use

Coronary computed tomography angiography (CCTA) evaluation of chest pain patients in an emergency department (ED) is considered appropriate. While a "negative" CCTA interpretation supports direct patient discharge from an ED, labor-intensive analyses are required, with accuracy in jeopardy from distractions. We describe the development of an artificial intelligence (AI) algorithm and workflow for assisting qualified interpreting physicians in CCTA screening for total absence of coronary atherosclerosis. The two-phase approach consisted of (1) phase 1-development and preliminary testing of an algorithm for vessel-centerline extraction classification in a balanced study population (n = 500 with 50% disease prevalence) derived by retrospective random case selection, and (2) phase 2-simulated clinical Trialing of developed algorithm on a per-case (entire coronary artery tree) basis in a more "real-world" study population (n = 100 with 28% disease prevalence) from an ED chest pain series. This allowed pre-deployment evaluation of the AI-based CCTA screening application which provides vessel-by-vessel graphic display of algorithm inference results integrated into a clinically capable viewer. Algorithm performance evaluation used area under the receiver operating characteristic curve (AUC-ROC); confusion matrices reflected ground truth vs AI determinations. The vessel-based algorithm demonstrated strong performance with AUC-ROC = 0.96. In both phase 1 and phase 2, independent of disease prevalence differences, negative predictive values at the case level were very high at 95%. The rate of completion of the algorithm workflow process (96% with inference results in 55-80 s) in phase 2 depended on adequate image quality. There is potential for this AI application to assist in CCTA interpretation to help extricate atherosclerosis from chest pain presentations.

Machine Learning Quantitation of Cardiovascular and Cerebrovascular Disease: A Systematic Review of Clinical Applications

Research into machine learning (ML) for clinical vascular analysis, such as those useful for stroke and coronary artery disease, varies greatly between imaging modalities and vascular regions. Limited accessibility to large diverse patient imaging datasets, as well as a lack of transparency in specific methods, are obstacles to further development. This paper reviews the current status of quantitative vascular ML, identifying advantages and disadvantages common to all imaging modalities. Literature from the past 8 years was systematically collected from MEDLINE^® and Scopus database searches in January 2021. Papers satisfying all search criteria, including a minimum of 50 patients, were further analysed and extracted of relevant data, for a total of 47 publications. Current ML image segmentation, disease risk prediction, and pathology quantitation methods have shown sensitivities and specificities over 70%, compared to expert manual analysis or invasive quantitation. Despite this, inconsistencies in methodology and the reporting of results have prevented inter-model comparison, impeding the identification of approaches with the greatest potential. The clinical potential of this technology has been well demonstrated in Computed Tomography of coronary artery disease, but remains practically limited in other modalities and body regions, particularly due to a lack of routine invasive reference measurements and patient datasets.

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.

Automated coronary artery tree segmentation in coronary CTA using a multiobjective clustering and toroidal model-guided tracking method

BACKGROUND AND OBJECTIVE

Accurate coronary artery tree segmentation can now be developed to assist radiologists in detecting coronary artery disease. In clinical medicine, the noise, low contrast, and uneven intensity of medical images along with complex shapes and vessel bifurcation structures make coronary artery segmentation challenging. In this work, we propose a multiobjective clustering and toroidal model-guided tracking method that can accurately extract coronary arteries from computed tomography angiography (CTA) imagery.

METHODS

Utilizing integrated noise reduction, candidate region detection, geometric feature extraction, and coronary artery tracking techniques, a new segmentation framework for 3D coronary artery trees is presented. The candidate regions are extracted using a multiobjective clustering method, and the coronary arteries are tracked by a toroidal model-guided tracking method.

RESULTS

The qualitative and quantitative results demonstrate the effectiveness of the presented framework, which achieves better performance than the compared segmentation methods in three widely used evaluation indices: the Dice similarity coefficient (DSC), Jaccard index and Recall across the CTA data. The proposed method can accurately identify the coronary artery tree with a mean DSC of 84%, a Jaccard index of 74%, and a Recall of 93%.

CONCLUSIONS

The proposed segmentation framework effectively segments the coronary tree from the CTA volume, which improves the accuracy of 3D vascular tree segmentation.

Bayesian Estimation of Geometric Morphometric Landmarks for Simultaneous Localization of Multiple Anatomies in Cardiac CT Images

We propose a robust method to simultaneously localize multiple objects in cardiac computed tomography angiography (CTA) images. The relative prior distributions of the multiple objects in the three-dimensional (3D) space can be obtained through integrating the geometric morphological relationship of each target object to some reference objects. In cardiac CTA images, the cross-sections of ascending and descending aorta can play the role of the reference objects. We employed the maximum a posteriori (MAP) estimator that utilizes anatomic prior knowledge to address this problem of localizing multiple objects. We propose a new feature for each pixel using the relative distances, which can define any objects that have unclear boundaries. Our experimental results targeting four pulmonary veins (PVs) and the left atrial appendage (LAA) in cardiac CTA images demonstrate the robustness of the proposed method. The method could also be extended to localize other multiple objects in different applications.

CF Distance: A New Domain Discrepancy Metric and Application to Explicit Domain Adaptation for Cross-Modality Cardiac Image Segmentation

Domain adaptation has great values in unpaired cross-modality image segmentation, where the training images with gold standard segmentation are not available from the target image domain. The aim is to reduce the distribution discrepancy between the source and target domains. Hence, an effective measurement for this discrepancy is critical. In this work, we propose a new metric based on characteristic functions of distributions. This metric, referred to as CF distance, enables explicit domain adaptation, in contrast to the implicit manners minimizing domain discrepancy via adversarial training. Based on this CF distance, we propose an unsupervised domain adaptation framework for cross-modality cardiac segmentation, which consists of image reconstruction and prior distribution matching. We validated the method on two tasks, i.e., the CT-MR cross-modality segmentation and the multi-sequence cardiac MR segmentation. Results showed that the proposed explicit metric was effective in domain adaptation, and the segmentation method delivered promising and superior performance, compared to other state-of-the-art techniques. The data and source code of this work has been released via https://zmiclab.github.io/projects.html.

Neural Network Vessel Lumen Regression for Automated Lumen Cross-Section Segmentation in Cardiovascular Image-Based Modeling

PURPOSE

We accelerate a pathline-based cardiovascular model building method by training machine learning models to directly predict vessel lumen surface points from computed tomography (CT) and magnetic resonance (MR) medical image data.

METHODS

We formulate vessel lumen detection as a regression task using a polar coordiantes representation.

RESULTS

Neural networks trained with our regression formulation allow predictions to be made with significantly higher accuracy than existing methods that identify the vessel lumen through binary pixel classification. The regression formulation enables machine learning models to be trained end-to-end for vessel lumen detection without post-processing steps that reduce accuracy.

CONCLUSION

By employing our models in a pathline-based cardiovascular model building pipeline we substantially reduce the manual segmentation effort required to build accurate cardiovascular models, and reduce the overall time required to perform patient-specific cardiovascular simulations. While our method is applied here for cardiovascular model building it is generally applicable to segmentation of tree-like and tubular structures from image data.

An improved matrix-based endovascular guidewire position simulation using fusiform ternary tree

In this paper, a new matrix-based method is proposed to real-time determine, the guidewire position inside an arterial system. The guidewire path is obtained by the optimal path method, particularly, the fusiform ternary tree method according to the principle of minimum output value of root node. An adaptive sampling strategy, and an optimization strategy based on the proximal end and distal end of the guidewire are proposed to change the guidewire position for obtaining an ideal guidewire path. Compared to the existing methods, the proposed method can achieve 74%, 64%, and 70% improvements in accuracy for phantoms 1, 2, and 3, respectively, investigated in this work.

Deep Learning Analysis of Coronary Arteries in Cardiac CT Angiography for Detection of Patients Requiring Invasive Coronary Angiography

In patients with obstructive coronary artery disease, the functional significance of a coronary artery stenosis needs to be determined to guide treatment. This is typically established through fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA). We present a method for automatic and non-invasive detection of patients requiring ICA, employing deep unsupervised analysis of complete coronary arteries in cardiac CT angiography (CCTA) images. We retrospectively collected CCTA scans of 187 patients, 137 of them underwent invasive FFR measurement in 192 different coronary arteries. These FFR measurements served as a reference standard for the functional significance of the coronary stenosis. The centerlines of the coronary arteries were extracted and used to reconstruct straightened multi-planar reformatted (MPR) volumes. To automatically identify arteries with functionally significant stenosis that require ICA, each MPR volume was encoded into a fixed number of encodings using two disjoint 3D and 1D convolutional autoencoders performing spatial and sequential encodings, respectively. Thereafter, these encodings were employed to classify arteries using a support vector machine classifier. The detection of coronary arteries requiring invasive evaluation, evaluated using repeated cross-validation experiments, resulted in an area under the receiver operating characteristic curve of 0.81 ± 0.02 on the artery-level, and 0.87 ± 0.02 on the patient-level. The results demonstrate the feasibility of automatic non-invasive detection of patients that require ICA and possibly subsequent coronary artery intervention. This could potentially reduce the number of patients that unnecessarily undergo ICA.

Deep Learning for Cardiac Image Segmentation: A Review

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound and major anatomical structures of interest (ventricles, atria, and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

Data Representations for Segmentation of Vascular Structures Using Convolutional Neural Networks with U-Net Architecture

Convolutional neural networks (CNNs) produce promising results when applied to a wide range of medical imaging tasks including the segmentation of tissue structures. However, segmentation is particularly challenging when the target structures are small with respect to the complete image data and exhibit substantial curvature as in the case of coronary arteries in computed tomography angiography (CTA). Therefore, we evaluated the impact of data representation of tubular structures on the segmentation performance of CNNs with U-Net architecture in terms of the resulting Dice coefficients and Hausdorff distances. For this purpose, we considered 2D and 3D input data in cross-sectional and Cartesian representations. We found that the data representation can have a substantial impact on segmentation results with Dice coefficients ranging from 60% to 82% reaching values similar to those of human expert annotations used for training and Hausdorff distances ranging from 1.38 mm to 5.90 mm. Our results indicate that a 3D cross-sectional data representation is preferable for segmentation of thin tubular structures.

Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey

Cardiac computed tomography (CT) allows rapid visualization of the heart and coronary arteries with high spatial resolution. However, analysis of cardiac CT scans for manifestation of coronary artery disease is time-consuming and challenging. Machine learning (ML) approaches have the potential to address these challenges with high accuracy and consistent performance. In this mini review, we present a survey of the literature on ML-based analysis of coronary artery disease in cardiac CT. We summarize ML methods for detection and characterization of atherosclerotic plaque as well as anatomically and functionally significant coronary artery stenosis.

TeTrIS: Template Transformer Networks for Image Segmentation With Shape Priors

In this paper, we introduce and compare different approaches for incorporating shape prior information into neural network-based image segmentation. Specifically, we introduce the concept of template transformer networks, where a shape template is deformed to match the underlying structure of interest through an end-to-end trained spatial transformer network. This has the advantage of explicitly enforcing shape priors, and this is free of discretization artifacts by providing a soft partial volume segmentation. We also introduce a simple yet effective way of incorporating priors in the state-of-the-art pixel-wise binary classification methods such as fully convolutional networks and U-net. Here, the template shape is given as an additional input channel, incorporating this information significantly reduces false positives. We report results on synthetic data and sub-voxel segmentation of coronary lumen structures in cardiac computed tomography showing the benefit of incorporating priors in neural network-based image segmentation.