Computed Tomography Angiography Volume Research Articles

A Dual-Functional System for the Classification and Diameter Measurement of Aortic Dissections Using CTA Volumes via Deep Learning

Acute aortic dissection is one of the most life-threatening cardiovascular diseases, with a high mortality rate. Its prevalence ranges from 0.2% to 0.8% in humans, resulting in a significant number of deaths due to being missed in manual examinations. More importantly, the aortic diameter—a critical indicator for surgical selection—significantly influences the outcomes of surgeries post-diagnosis. Therefore, it is an urgent yet challenging mission to develop an automatic aortic dissection diagnostic system that can recognize and classify the aortic dissection type and measure the aortic diameter. This paper offers a dual-functional deep learning system called aortic dissections diagnosis-aiding system (DDAsys) that enables both accurate classification of aortic dissection and precise diameter measurement of the aorta. To this end, we created a dataset containing 61 190 computed tomography angiography (CTA) images from 279 patients from the Division of Cardiovascular Surgery at Tongji Hospital, Wuhan, China. The dataset provides a slice-level summary of difficult-to-identify features, which helps to improve the accuracy of both recognition and classification. Our system achieves a recognition F1 score of 0.984, an average classification F1 score of 0.935, and the respective measurement precisions for ascending and descending aortic diameters are 0.994 mm and 0.767 mm root mean square error (RMSE). The high consistency (88.6%) between the recommended surgical treatments and the actual corresponding surgeries verifies the capability of our system to aid clinicians in developing a more prompt, precise, and consistent treatment strategy.

CAR-Net: A Deep Learning-Based Deformation Model for 3D/2D Coronary Artery Registration.

Percutaneous coronary intervention is widely applied for the treatment of coronary artery disease under the guidance of X-ray coronary angiography (XCA) image. However, the projective nature of XCA causes the loss of 3D structural information, which hinders the intervention. This issue can be addressed by the deformable 3D/2D coronary artery registration technique, which fuses the pre-operative computed tomography angiography volume with the intra-operative XCA image. In this study, we propose a deep learning-based neural network for this task. The registration is conducted in a segment-by-segment manner. For each vessel segment pair, the centerlines that preserve topological information are decomposed into an origin tensor and a spherical coordinate shape tensor as network input through independent branches. Features of different modalities are fused and processed for predicting angular deflections, which is a special type of deformation field implying motion and length preservation constraints for vessel segments. The proposed method achieves an average error of 1.13 mm on the clinical dataset, which shows the potential to be applied in clinical practice.

End-to-end artificial intelligence platform for the management of large vessel occlusions: A preliminary study

ObjectivesIn this study, we developed a deep learning pipeline that detects large vessel occlusion (LVO) and predicts functional outcome based on computed tomography angiography (CTA) images to improve the management of the LVO patients. MethodsA series identifier picked out 8650 LVO-protocoled studies from 2015 to 2019 at Rhode Island Hospital with an identified thin axial series that served as the data pool. Data were annotated into 2 classes: 1021 LVOs and 7629 normal. The Inception-V1 I3D architecture was applied for LVO detection. For outcome prediction, 323 patients undergoing thrombectomy were selected. A 3D convolution neural network (CNN) was used for outcome prediction (30-day mRS) with CTA volumes and embedded pre-treatment variables as inputs. ResultFor LVO-detection model, CTAs from 8,650 patients (median age 68 years, interquartile range (IQR): 58-81; 3934 females) were analyzed. The cross-validated AUC for LVO vs. not was 0.74 (95% CI: 0.72-0.75). For the mRS classification model, CTAs from 323 patients (median age 75 years, IQR: 63-84; 164 females) were analyzed. The algorithm achieved a test AUC of 0.82 (95% CI: 0.79-0.84), sensitivity of 89%, and specificity 66%. The two models were then integrated with hospital infrastructure where CTA was collected in real-time and processed by the model. If LVO was detected, interventionists were notified and provided with predicted clinical outcome information. Conclusion3D CNNs based on CTA were effective in selecting LVO and predicting LVO mechanical thrombectomy short-term prognosis. End-to-end AI platform allows users to receive immediate prognosis prediction and facilitates clinical workflow.

Whole-Brain Volume CT Angiography can Effectively Detect Early Ischemic Cerebrovascular Diseases.

To investigate the role of whole-brain volume computed tomography (CT) perfusion in assessing early ischemic cerebrovascular diseases. Seventy-two patients with early ischemic cerebrovascular diseases who had undergone routine CT scan and 320-row volume CT whole-brain perfusion imaging within 8 h after admission were retrospectively enrolled in this one-center case-sectional study. The perfusion parameters of cerebral blood flow (CBF), cerebral blood volume (CBV), mean transit time (MTT), time to peak (TTP), and dynamic CT angiogram (4D-CTA) were obtained and analyzed. Among 72 patients, 29 cases with 37 cerebral ischemic lesions were found in plain CT scan, whereas 51 cases with 76 lesions were found in whole-brain CT perfusion, with 30.6% more patients being detected. The CBF value was significantly lower in the abnormal than normal corresponding perfusion area in the healthy hemisphere (P<0.05), while the MTT and TTP values were significantly higher in the abnormal than the normal corresponding area (P<0.05). 4D-CTA image suggested that 59 cases had different degrees of stenosis or occlusion, including 11 mild, 18 moderate, 21 severe, and 9 occlusive cases. Four-D-CTA imaging could detect significantly (P<0.05) more patients with abnormal perfusion in severe cerebral vascular stenosis or occlusion than those with no, mild or moderate stenosis (93.33% vs. 16.67%) (P<0.05). The stenosis of intracranial and carotid arteries was positively correlated with MTT and TTP values (P<0.05). Whole-brain volume CT angiography can comprehensively display early cerebral ischemic lesions, cerebral blood perfusion status, and cerebral vascular stenosis, providing valuable information for early detection of ischemic cerebral diseases and appropriate treatment planning.

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

Background and objectiveAccurate 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. MethodsUtilizing 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. ResultsThe 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%. ConclusionsThe proposed segmentation framework effectively segments the coronary tree from the CTA volume, which improves the accuracy of 3D vascular tree segmentation.

Patient-specific 3D-printed coronary models based on coronary computed tomography angiography volumes to investigate flow conditions in coronary artery disease

Background: 3D printed patient-specific coronary models have the ability to enable repeatable benchtop experiments under controlled blood flow conditions. This approach can be applied to CT-derived patient geometries to emulate coronary flow and related parameters such as Fractional Flow Reserve (FFR). Methods: This study uses 3D printing to compare such benchtop FFR results with a non-invasive CT-FFR research software algorithm and catheter based invasive FFR (I-FFR) measurements. Fifty-two patients with a clinical indication for I-FFR underwent a research Coronary CT Angiography (CCTA) prior to catheterization. CT images were used to measure CT-FFR and to generate patient-specific 3D printed models of the aortic root and three main coronary arteries. Each patient-specific model was connected to a programmable pulsatile pump and benchtop FFR (B-FFR) was derived from pressures measured proximal and distal to coronary stenosis using pressure transducers. B-FFR was measured for two coronary outflow rates (‘normal’, 250 ml min−1; and ‘hyperemic’, 500 ml min−1) by adjusting the model’s distal coronary resistance. Results: Pearson correlations and ROC AUC were calculated using invasive I-FFR as reference. The Pearson correlation factor of CT-FFR and B-FFR-500 was 0.75 and 0.71, respectively. Areas under the ROCs for CT-FFR and B-FFR-500 were 0.80 (95%CI: 0.70–0.87) and 0.81 (95%CI: 0.64–0.91) respectively. Conclusion: Benchtop flow simulations with 3D printed models provide the capability to measure pressure changes at any location in the model, for ultimately emulating the FFR at several simulated physiological blood flow conditions. Clinical Trial Registration: https://clinicaltrials.gov/show/NCT03149042

Development of Virtual 3D Stereoscopic Model of the Heart from Computed Tomography Angiography for Anatomy Education

The development of 3D stereoscopic models usually requires the acquisition and conversion of voxel‐based CT or MRI data into 3D models. It has been reported recently that the computed tomography angiography (CTA) was used to create vascular models using volume rendering, and surface rendering. CTA images and volume rendering models have been extensively used for vasculature anatomy, detection and evaluation of intracranial aneurysms and diagnosis of ischemic stroke, however, the CTA data has not been well explored for creating heart stereoscopic virtual models using semi‐auto combined rendering for anatomy educational purpose. In this study, we utilize CTA data to develop a stereoscopic heart model using the semi‐auto combined rendering in addition to the volume and surface rendering methods. These CTA imagings happened to come from an individual with left‐sided superior vena cava (0.3–0.5% population). The heart displays good contrast in the CTA due to its rich blood supply, and large vessels were easily selected during the creation process. The visualization of the heart, associated major arteries, and their relationship can be viewed via the stereoscopic presentation. Future studies will include the measure and comparison of students' learning outcomes of anatomy knowledge using the model versus that of a cadaver heart.This abstract is from the Experimental Biology 2019 Meeting. There is no full text article associated with this abstract published in The FASEB Journal.

Automatic extraction of coronary centerline based on model-mapped and inertia-guided minimum path from CTA images

It has been a challenging but significant research topic to extract the centerlines of the coronary arteries of the cardiac computed tomography angiography volume in clinical applications. A new method is proposed to full-automatically extract and recognize the centerlines of the major branches instead of manual interaction in this paper, which employs a new path tracking algorithm that combines direction features from atlases and inertia features from previous extracted centerline points, referred to as model-mapped and inertia-guided minimum path. This method first registers a pre-constructed coronary model that contains the right coronary artery, the left anterior descending artery, the left circumflex artery coronary artery to the target cardiac computed tomography, to provide initial reference positions and direction information of the coronary artery. After getting the reference regions based on the registration, the two ostia positions are detected automatically by the learning-based method, which is based on the probability boosting tree and 3D Haar features, in the region of interest of the cardiac computed tomography volume. The starting points are then as the ostia in the evolution of minimum path. Meanwhile, to boost the robustness of the evolution, the tracked path of the last step is used to generate the inertia-driven force. Finally, based on a new automatic endpoint detection algorithm, the longest centerline of a particular coronary branch can be extracted with the proposed method. We tested the robustness of our method in the Rotterdam Coronary Artery Algorithm Evaluation framework. The proposed method is fully automatic and obtains the optimal effect among the fully automatic methods in Rotterdam framework.

Gamma Knife Radiosurgery for Arteriovenous Malformations Using a Four-Dimensional Dynamic Volume Computed Tomography Angiography Planning System as an Alternative to Traditional Catheter Angiogram.

BackgroundGamma knife radiosurgery (GKRS) remains a critical intervention in the long-term management of arteriovenous malformations (AVMs). For planning a treatment, identification of the nidus is essential, and it is dependent on high-resolution blood flow imaging, usually in the form of a traditional angiogram. The development of dynamic 320-slice computed tomography (CT) angiography has offered a noninvasive alternative to intra-arterial fluoroscopic imaging, and it is capable of providing equivalent temporal resolution. In this study, we describe the feasibility of using four-dimensional CT angiography (4D-CTA) in GKRS planning for AVM treatment and a comparative analysis with a traditional angiogram.MethodsA retrospective review was performed on AVM patients treated via GKRS with a 4D-CTA prior to the day of treatment, on the day of treatment, or with a day-of-treatment angiogram. Treatment times, along with total times in the Leksell® coordinate frame G, were obtained from the medical records. The frame-on time was calculated by subtracting the treatment time from the total time starting from application to removal, and the statistical analysis was performed across groups using analysis of variance (ANOVA). All treatments were performed on the Perfexion™ model with a dynamic flow imaging procured via a 320-slice CT scanner or traditional angiography platform.ResultsSome 27 patients underwent a total of 29 GKRS procedures for AVM treatment at our institution between September 2011 and January 2017. Mean age at the time of treatment was 35.5 (6-65) years, and male:female ratio was 5:4. Some 12 patients had 4D-CTA performed prior to the day of treatment, eight patients had the same CTA completed after frame placement on the day of treatment, while seven patients underwent traditional angiography. The mean frame-on times of each group were 190, 336, and 426 minutes, respectively (p < 0.0001). No procedures were aborted based on the image quality.Conclusions4D-CTA is an effective tool in identifying the AVM nidus for GKRS planning. These studies can be performed prior to the day of treatment, allowing for a significant reduction in frame-on time and eliminating the risk of angiogram complication on the day of GKRS.

Automated Quantification of Non-Calcified Coronary Plaques in Cardiac CT Angiographic Imagery

The high mortality rate associated with coronary heart disease (CHD) has driven intensive research in cardiac image analysis. The advent of computed tomography angiography (CTA) has turned non-invasive diagnosis of cardiovascular anomalies into reality as calcified coronary plaques can be easily identified due to high intensity values. However, detection and quantification of the non-calcified plaques in CTA is still a challenging problem because of their lower intensity values, which are often similar to the nearby blood and muscle tissues. In this work, we propose Bayesian posterior based model for precise quantification of the non-calcified plaques in CTA imagery. The only indicator of non-calcified plaques in CTA is relatively lower intensity. Hence, we exploited intensity variations to discriminate voxels into lumen and plaque classes. Based on the normal coronary segments, we computed the vessel-wall thickness in first step. In the subsequent step, we removed vessel wall from the segmented tree and employed Gaussian Mixture Model to compute optimal distribution parameters. In the final step, distribution parameters were employed in Bayesian posterior model to classify voxels into lumen or plaque. A total of 18 CTA volumes were analyzed in this work using two different approaches. According to the experimental results, mean Jaccard overlap is around 88% with respect to the manual expert. In terms of sensitivity, specificity and accuracy, the proposed method achieves 84.13%, 79.15% and 82.02% success, respectively. Conclusion: According to the experimental results, it is shown that the proposed plaque quantification method achieves accuracy equivalent to human experts.

Clinical Impact of Flat Panel Volume CT Angiography in Evaluating the Accurate Intraoperative Deployment of Flow-Diverter Stents.

The deployment of flow-diverter stents may be difficult to analyse on regular DSA. The purpose of our study was to investigate the clinical impact of stent-dedicated flat panel volume CT angiography to evaluate intraoperatively the satisfactory deployment of flow-diverter stents. From January 2009 to April 2015, 83 consecutive patients (mean age, 51 years; 62 women) were treated in our institution with flow-diverter stents. Eighty-seven aneurysms (82 unruptured, 5 ruptured; 77 anterior, 10 posterior circulation) were treated in these 83 patients (4 patients had 2 aneurysms, both treated by means of flow-diverter stents). One patient was treated for a traumatic carotid cavernous fistula. In 80% of the cases (68/85) a flat panel volume CT angiography was performed in the angiographic suite just after the flow-diverter stent deployment. Stent visualization was assessed by 2 independent reviewers. The clinical impact of stent malapposition was evaluated. Flow-diverter stent visualization was satisfactory in 73.5% of the cases. In 2 cases (2.9%) the flat panel volume CT angiography prompted the operator to perform an additional intrastent angioplasty for a condition that was previously underestimated. Four patients (4.7%) experienced acute thromboembolic complications; 3 others had delayed thromboembolic complications. Only 1 of these patients had thromboembolic complications (acute or delayed) related to stent misdeployment, which was easily managed intraoperatively with no clinical consequence. Flat panel volume CT angiography is an interesting tool to depict flow-diverter stent misdeployment and may encourage the operator to perform intrastent angioplasty (2.9% of the cases in our experience) to reduce the risks of thromboembolic complications.

Framework for detection and localization of coronary non-calcified plaques in cardiac CTA using mean radial profiles

Background and objectiveThe high mortality rate associated with coronary heart disease (CHD) has driven intensive research in cardiac imaging and image analysis. The advent of computed tomography angiography (CTA) has turned non-invasive diagnosis of cardiovascular anomalies into reality as calcified coronary plaques can be easily identified due to their high intensity values. However, the detection of non-calcified plaques in CTA is still a challenging problem because of lower intensity values, which are often similar to the nearby blood and muscle tissues. In this work, we propose the use of mean radial profiles for the detection of non-calcified plaques in CTA imagery. MethodsAccordingly, we computed radial profiles by averaging the image intensity in concentric rings around the vessel centreline in a first stage. In the subsequent stage, an SVM classifier is applied to identify the abnormal coronary segments. For occluded segments, we further propose a derivative-based method to localize the position and length of the plaque inside the segment. ResultsA total of 32 CTA volumes were analysed and a detection accuracy of 88.4% with respect to the manual expert was achieved. The plaque localization accuracy was computed using the Dice similarity coefficient and a mean of 83.2% was achieved. ConclusionThe consistent performance for multi-vendor, multi-institution data demonstrates the reproducibility of our method across different CTA datasets with a good agreement with manual expert annotations.

A hybrid energy model for region based curve evolution – Application to CTA coronary segmentation

Background and ObjectiveState-of-the-art medical imaging techniques have enabled non-invasive imaging of the internal organs. However, high volumes of imaging data make manual interpretation and delineation of abnormalities cumbersome for clinicians. These challenges have driven intensive research into efficient medical image segmentation. In this work, we propose a hybrid region-based energy formulation for effective segmentation in computed tomography angiography (CTA) imagery. MethodsThe proposed hybrid energy couples an intensity-based local term with an efficient discontinuity-based global model of the image for optimal segmentation. The segmentation is achieved using a level set formulation due to the computational robustness. After validating the statistical significance of the hybrid energy, we applied the proposed model to solve an important clinical problem of 3D coronary segmentation. An improved seed detection method is used to initialize the level set evolution. Moreover, we employed an auto-correction feature that captures the emerging peripheries during the curve evolution for completeness of the coronary tree. ResultsWe evaluated the segmentation accuracy of the proposed energy model against the existing techniques in two stages. Qualitative and quantitative results demonstrate the effectiveness of the proposed framework with a consistent mean sensitivity and specificity measures of 80% across the CTA data. Moreover, a high degree of agreement with respect to the inter-observer differences justifies the generalization of the proposed method. ConclusionsThe proposed method is effective to segment the coronary tree from the CTA volume based on hybrid image based energy, which can improve the clinicians ability to detect arterial abnormalities.

Automatic Fuzzy-based Hybrid Approach for Segmentation and Centerline Extraction of Main Coronary Arteries

Coronary arteries segmentation and centerlines extraction is an important step in Coronary Artery Disease diagnosis. The main purpose of the fully automated presented approaches is helping the clinical non-invasive diagnosis process to be done in fast way with accurate result. In this paper, a hybrid scheme is proposed to segment the coronary arteries and to extract the centerlines from Computed Tomography Angiography volumes. The proposed automatic hybrid segmentation approach combines the Hough transform with a fuzzy-based region growing algorithm. First, a circular Hough transform is used to detect initially the aorta circle. Then, the well-known Fuzzy c-mean algorithm is employed to detect the seed points for the region growing algorithm resulting in 3D binary volume. Finally, the centerlines of the segmented arteries are extracted based on the segmented 3D binary volume using a skeletonization based method. Using a benchmark database provided by the Rotterdam Coronary Artery Algorithm Evaluation Framework, the proposed algorithm is tested and evaluated. A comparative study shows that the proposed hybrid scheme is able to achieve a higher accuracy, in comparison to the most related and recent published work, at reasonable computational cost.

Accuracy of 320-detector volume CT angiography in the diagnosis of intracranial aneurysms

Objective To assess the accuracy of 320-detector volume CTA (VCTA) in the diagnosis of intracranial aneurysms. Methods A total of 462 patients suspected with intracranial aneurysm in the Department of Interventional Radiology, the Third Affiliated Hospital of Soochow University from February 2011 to October 2014 were performed 320-detector VCTA and digital subtraction angiographic (DSA) examinations. Results In 462 patients, 313 patients with intracranial aneurysm were diagnosed by 3D-DSA and a total of 381 intracranial aneurysms were detected. Ten intracranial aneurysms were missed by non-subtracted VCTA and one aneurysm was misdiagnosed. The sensitivity, specificity, and accuracy of non-subtracted VCTA diagnosed 0.05). Conclusions The accuracy of subtracted 320-detector VCTA in the diagnosis of <3 mm intracranial aneurysms is higher. It can be used as the preferred imaging examination for diagnosis of intracranial aneurysms. The non-subtracted 320-detector VCTA relatively easily misses the diagnosis of intracranial aneurysms near the skull. Key words: Intracranial aneurysm; 320-detector volume CT angiography; Angiography, digital subtraction

GW26-e3907 Diagnostic accuracy of 320-slice dynamic volume computed tomography angiography for evaluation of coronary stent patency and restenosis

GW26-e3907 Diagnostic accuracy of 320-slice dynamic volume computed tomography angiography for evaluation of coronary stent patency and restenosis

GW26-e2505 The contrast of radiation dose with three scan modes in 320-slice dynamic volume computed tomography angiography compared with selective coronary angiography

GW26-e2505 The contrast of radiation dose with three scan modes in 320-slice dynamic volume computed tomography angiography compared with selective coronary angiography

GW26-e3541 Diagnostic accuracy of 320-slice dynamic volume computed tomography angiography for detection of coronary artery stenosis in patients with atrial fibrillation

To evaluate the diagnostic accuracy of 320-slice dynamic volume CT angiography (CTA) in assessment of coronary artery stenosis in patients with atrial fibrillation (AF) compared with selective coronary angiography (SCA). Seventy-two patients (49males, 63.9±12.5 years) with persistent AF were

CT angiography of the lower extremity and coronary arteries using 256-section CT: a preliminary study

To investigate the possible use of a 256-section computed tomography (CT) prospective electrocardiography (ECG)-gated wide volume scanning protocol for combined angiography of the lower extremity and coronary arteries, after a single injection of contrast medium, in patients with lower extremity peripheral arterial disease (PAD). Thirty-four patients with suspected PAD underwent CT angiography (CTA) with a prospective ECG-gated protocol that covered the level of the tracheal bifurcation to the foot sole. Digital subtraction angiography (DSA) of the lower extremity arteries was performed on patients requiring therapeutic intervention. Image quality and stenosis of the coronary and lower extremity arteries were assessed. A total of 93.1% of the coronary segments were adequate for diagnosis. 17 (50%) patients showed coronary artery stenosis ≥50%. A total of 95.8% of the lower extremity arterial segments were adequate for diagnosis. Twenty-eight patients with severe lower extremity arterial stenosis or occlusion underwent DSA. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of CTA for the detection of significant lower arterial stenosis (≥50%) was 94.8%, 97.2%, 95.3%, 96.9%, and 96.3%, respectively. Using the prospective ECG-gated wide volume CTA protocol, images of the coronary and lower extremity arteries suitable for diagnosis can be acquired simultaneously after a single injection of contrast agent. In addition to accurately diagnosing PAD, combined angiography may be used to screen for coronary heart disease in patients with PAD.

Urgent endovascular repair for ruptured aortic aneurysm using computed tomography image fusion

Abdominal aortic aneurysm rupture remains a cardiovascular catastrophe with strikingly high morbidity and mortality rates. Endovascular aneurysm repair management has recently emerged as a valuable treatment modality for ruptured abdominal aortic aneurysm, but better outcomes have to be reached. Image fusion may potentially improve perioperative outcomes in selected patients, guiding navigation and device implantation and limiting contrast dosage during interventions. We report an 83-year-old man presenting with an 80-mm infrarenal aortic aneurysm rupture suitable for endovascular aneurysm repair. Endovascular navigation and stent graft deployment were achieved using computed tomography image fusion for the first reported case in English.