Robust Segmentation of the Full Cerebral Vasculature in 4D CT of Suspected Stroke Patients

Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis

Background

Artificial intelligence-derived software technologies have been developed that are intended to facilitate the review of computed tomography brain scans in patients with suspected stroke.

Objectives

To evaluate the clinical and cost-effectiveness of using artificial intelligence-derived software to support review of computed tomography brain scans in acute stroke in the National Health Service setting.

Methods

Twenty-five databases were searched to July 2021. The review process included measures to minimise error and bias. Results were summarised by research question, artificial intelligence-derived software technology and study type. The health economic analysis focused on the addition of artificial intelligence-derived software-assisted review of computed tomography angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with an ischaemic stroke. The de novo model (developed in R Shiny, R Foundation for Statistical Computing, Vienna, Austria) consisted of a decision tree (short-term) and a state transition model (long-term) to calculate the mean expected costs and quality-adjusted life-years for people with ischaemic stroke and suspected large-vessel occlusion comparing artificial intelligence-derived software-assisted review to usual care.

Results

A total of 22 studies (30 publications) were included in the review; 18/22 studies concerned artificial intelligence-derived software for the interpretation of computed tomography angiography to detect large-vessel occlusion. No study evaluated an artificial intelligence-derived software technology used as specified in the inclusion criteria for this assessment. For artificial intelligence-derived software technology alone, sensitivity and specificity estimates for proximal anterior circulation large-vessel occlusion were 95.4% (95% confidence interval 92.7% to 97.1%) and 79.4% (95% confidence interval 75.8% to 82.6%) for Rapid (iSchemaView, Menlo Park, CA, USA) computed tomography angiography, 91.2% (95% confidence interval 77.0% to 97.0%) and 85.0 (95% confidence interval 64.0% to 94.8%) for Viz LVO (Viz.ai, Inc., San Fransisco, VA, USA) large-vessel occlusion, 83.8% (95% confidence interval 77.3% to 88.7%) and 95.7% (95% confidence interval 91.0% to 98.0%) for Brainomix (Brainomix Ltd, Oxford, UK) e-computed tomography angiography and 98.1% (95% confidence interval 94.5% to 99.3%) and 98.2% (95% confidence interval 95.5% to 99.3%) for Avicenna CINA (Avicenna AI, La Ciotat, France) large-vessel occlusion, based on one study each. These studies were not considered appropriate to inform cost-effectiveness modelling but formed the basis by which the accuracy of artificial intelligence plus human reader could be elicited by expert opinion. Probabilistic analyses based on the expert elicitation to inform the sensitivity of the diagnostic pathway indicated that the addition of artificial intelligence to detect large-vessel occlusion is potentially more effective (quality-adjusted life-year gain of 0.003), more costly (increased costs of £8.61) and cost-effective for willingness-to-pay thresholds of £3380 per quality-adjusted life-year and higher.

Limitations and conclusions

The available evidence is not suitable to determine the clinical effectiveness of using artificial intelligence-derived software to support the review of computed tomography brain scans in acute stroke. The economic analyses did not provide evidence to prefer the artificial intelligence-derived software strategy over current clinical practice. However, results indicated that if the addition of artificial intelligence-derived software-assisted review for guiding mechanical thrombectomy treatment decisions increased the sensitivity of the diagnostic pathway (i.e. reduced the proportion of undetected large-vessel occlusions), this may be considered cost-effective.

Future work

Large, preferably multicentre, studies are needed (for all artificial intelligence-derived software technologies) that evaluate these technologies as they would be implemented in clinical practice.

Study registration

This study is registered as PROSPERO CRD42021269609.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133836) and is published in full in Health Technology Assessment; Vol. 28, No. 11. See the NIHR Funding and Awards website for further award information.

LVONet: automatic classification model for large vessel occlusion based on the difference information between left and right hemispheres

Objective.Stroke is a highly lethal condition, with intracranial vessel occlusion being one of its primary causes. Intracranial vessel occlusion can typically be categorized into four types, each requiring different intervention measures. Therefore, the automatic and accurate classification of intracranial vessel occlusions holds significant clinical importance for assessing vessel occlusion conditions. However, due to the visual similarities in shape and size among different vessels and variations in the degree of vessel occlusion, the automated classification of intracranial vessel occlusions remains a challenging task. Our study proposes an automatic classification model for large vessel occlusion (LVO) based on the difference information between the left and right hemispheres.Approach.Our approach is as follows. We first introduce a dual-branch attention module to learn long-range dependencies through spatial and channel attention, guiding the model to focus on vessel-specific features. Subsequently, based on the symmetry of vessel distribution, we design a differential information classification module to dynamically learn and fuse the differential information of vessel features between the two hemispheres, enhancing the sensitivity of the classification model to occluded vessels. To optimize the feature differential information among similar vessels, we further propose a novel cooperative learning loss function to minimize changes within classes and similarities between classes.Main results.We evaluate our proposed model on an intracranial LVO data set. Compared to state-of-the-art deep learning models, our model performs optimally, achieving a classification sensitivity of 93.73%, precision of 83.33%, accuracy of 89.91% and Macro-F1 score of 87.13%.Significance.This method can adaptively focus on occluded vessel regions and effectively train in scenarios with high inter-class similarity and intra-class variability, thereby improving the performance of LVO classification.

A dataset of rodent cerebrovasculature from in vivo multiphoton fluorescence microscopy imaging

We present MiniVess, the first annotated dataset of rodent cerebrovasculature, acquired using two-photon fluorescence microscopy. MiniVess consists of 70 3D image volumes with segmented ground truths. Segmentations were created using traditional image processing operations, a U-Net, and manual proofreading. Code for image preprocessing steps and the U-Net are provided. Supervised machine learning methods have been widely used for automated image processing of biomedical images. While much emphasis has been placed on the development of new network architectures and loss functions, there has been an increased emphasis on the need for publicly available annotated, or segmented, datasets. Annotated datasets are necessary during model training and validation. In particular, datasets that are collected from different labs are necessary to test the generalizability of models. We hope this dataset will be helpful in testing the reliability of machine learning tools for analyzing biomedical images.

Artificial Intelligence-Assisted Chest X-ray for the Diagnosis of COVID-19: A Systematic Review and Meta-Analysis

Because it is an accessible and routine image test, medical personnel commonly use a chest X-ray for COVID-19 infections. Artificial intelligence (AI) is now widely applied to improve the precision of routine image tests. Hence, we investigated the clinical merit of the chest X-ray to detect COVID-19 when assisted by AI. We used PubMed, Cochrane Library, MedRxiv, ArXiv, and Embase to search for relevant research published between 1 January 2020 and 30 May 2022. We collected essays that dissected AI-based measures used for patients diagnosed with COVID-19 and excluded research lacking measurements using relevant parameters (i.e., sensitivity, specificity, and area under curve). Two independent researchers summarized the information, and discords were eliminated by consensus. A random effects model was used to calculate the pooled sensitivities and specificities. The sensitivity of the included research studies was enhanced by eliminating research with possible heterogeneity. A summary receiver operating characteristic curve (SROC) was generated to investigate the diagnostic value for detecting COVID-19 patients. Nine studies were recruited in this analysis, including 39,603 subjects. The pooled sensitivity and specificity were estimated as 0.9472 (p = 0.0338, 95% CI 0.9009-0.9959) and 0.9610 (p < 0.0001, 95% CI 0.9428-0.9795), respectively. The area under the SROC was 0.98 (95% CI 0.94-1.00). The heterogeneity of diagnostic odds ratio was presented in the recruited studies (I² = 36.212, p = 0.129). The AI-assisted chest X-ray scan for COVID-19 detection offered excellent diagnostic potential and broader application.

Deep Learning Applications for Acute Stroke Management

Brain imaging is essential to the clinical care of patients with stroke, a leading cause of disability and death worldwide. Whereas advanced neuroimaging techniques offer opportunities for aiding acute stroke management, several factors, including time delays, inter-clinician variability, and lack of systemic conglomeration of clinical information, hinder their maximal utility. Recent advances in deep machine learning (DL) offer new strategies for harnessing computational medical image analysis to inform decision making in acute stroke. We examine the current state of the field for DL models in stroke triage. First, we provide a brief, clinical practice-focused primer on DL. Next, we examine real-world examples of DL applications in pixel-wise labeling, volumetric lesion segmentation, stroke detection, and prediction of tissue fate postintervention. We evaluate recent deployments of deep neural networks and their ability to automatically select relevant clinical features for acute decision making, reduce inter-rater variability, and boost reliability in rapid neuroimaging assessments, and integrate neuroimaging with electronic medical record (EMR) data in order to support clinicians in routine and triage stroke management. Ultimately, we aim to provide a framework for critically evaluating existing automated approaches, thus equipping clinicians with the ability to understand and potentially apply DL approaches in order to address challenges in clinical practice. ANN NEUROL 2022.

Numerical Assessment of the Risk of Abnormal Endothelialization for Diverter Devices: Clinical Data Driven Numerical Study

Numerical modeling is an effective tool for preoperative planning. The present work is devoted to a retrospective analysis of neurosurgical treatments for the occlusion of cerebral aneurysms using flow-diverters and hemodynamic factors affecting stent endothelization. Several different geometric approaches have been considered for virtual flow-diverters deployment. A comparative analysis of hemodynamic parameters as a result of computational modeling has been carried out basing on the four clinical cases: one successful treatment, one with no occlusion and two with in stent stenosis. For the first time, a quantitative assessment of both: the limiting magnitude of shear stresses that are necessary for the occurrence of in stent stenosis (MaxWSS > 1.23) and for conditions in which endothelialization is insufficiently active and occlusion of the cervical part of the aneurysm does not occur (MaxWSS < 1.68)—has been statistacally proven (p < 0.01).

3D volume segmentation and reconstruction. Supervised image classification and automated quantification of superparamagnetic iron oxide nanoparticles in histology slides for safety assessment

This article presents an automated image-processing workflow for quantitative assessment of SPION accumulation in tissue sections stained with Prussian blue for iron detection. We utilized supervised machine learning with manually labeled features used for training the classifier. Performance of the classifier was validated by 10-fold cross-validation of obtained data and by measuring Dice and Jaccard Similarity Coefficients between manually segmented image and automated segmentation. The proposed approach provides time and cost-effective solution for quantitative imaging analysis of SPION in tissue with a precision similar to that obtained via thresholding method for stain quantification. Furthermore, we exploited the classifiers to generate segmented 3D volumes from histological slides. This enabled visualization of particles which were obscured in original 3D histology stacks. Our approach offers a powerful tool for preclinical assessment of the precise tissue-specific SPION biodistribution, which could affect both their toxicity and their efficacy as nanocarriers for medicines.

A minimally interactive method for labeling respiratory phases in free-breathing thoracic dynamic MRI for constructing 4D images

OBJECTIVE

Determination of end-expiration (EE) and end-inspiration (EI) time points in the respiratory cycle in free-breathing slice image acquisitions of the thorax is one key step needed for 4D image construction via dynamic magnetic resonance imaging. The purpose of this paper is to realize the automation of the labeling process.

METHODS

The diaphragm is used as a surrogate for tracking respiratory motion and determining the state of breathing. Regions of interest (ROIs) containing the hemi-diaphragms are set by human interaction to compute the optical flow matrix between two adjacent 2D time slices. Subsequently, our approach examines the diaphragm speed and direction and by considering the change in the optical flow matrix, the EE or EI points are detected.

RESULTS AND CONCLUSION

The labeling accuracy for the lateral aspect of the left lung and the lateral aspect of the right lung (0.630.71) is significantly lower (P < 0.05) than the accuracy for other positions (0.420.44), but the error in almost all scenarios is less than 1 time point. By comparing between automatic and manual labeling in 12 scenarios, we found out that 9 scenarios showed no significant difference (P > 0.05) between two methods. Overall, our method is found to be highly agreeable with manual labeling and greatly shortens the labeling time, requiring less than 8 minutes/ study compared to 4 hours/ study for manual labeling.

SIGNIFICANCE

Our method achieves automatic labeling of EE and EI points without the need for use of patient internal or external markers.

Deep learning-based Hounsfield unit value measurement method for bolus tracking images in cerebral computed tomography angiography

BACKGROUND

Patient movement during bolus tracking (BT) impairs the accuracy of Hounsfield unit (HU) measurements. This study assesses the accuracy of measuring HU values in the internal carotid artery (ICA) using an original deep learning (DL)-based method as compared with using the conventional region of interest (ROI) setting method.

METHOD

A total of 722 BT images of 127 patients who underwent cerebral computed tomography angiography were selected retrospectively and divided into groups for training data, validation data, and test data. To segment the ICA using our proposed method, DL was performed using a convolutional neural network. The HU values in the ICA were obtained using our DL-based method and the ROI setting method. The ROI setting was performed with and without correcting for patient body movement (corrected ROI and settled ROI). We compared the proposed DL-based method with settled ROI to evaluate HU value differences from the corrected ROI, based on whether or not patients experienced involuntary movement during BT image acquisition.

RESULTS

Differences in HU values from the corrected ROI in the settled ROI and the proposed method were 23.8 ± 12.7 HU and 9.0 ± 6.4 HU in patients with body movement and 1.1 ± 1.6 HU and 3.9 ± 4.7 HU in patients without body movement, respectively. There were significant differences in both comparisons (P < 0.01).

CONCLUSION

DL-based method can improve the accuracy of HU value measurements for ICA in BT images with patient involuntary movement.

An evaluation of performance measures for arterial brain vessel segmentation

BACKGROUND

Arterial brain vessel segmentation allows utilising clinically relevant information contained within the cerebral vascular tree. Currently, however, no standardised performance measure is available to evaluate the quality of cerebral vessel segmentations. Thus, we developed a performance measure selection framework based on manual visual scoring of simulated segmentation variations to find the most suitable measure for cerebral vessel segmentation.

METHODS

To simulate segmentation variations, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation. In 10 patients, we generated a set of approximately 300 simulated segmentation variations for each ground truth image. Each segmentation was visually scored based on a predefined scoring system and segmentations were ranked based on 22 performance measures common in the literature. The correlation of visual scores with performance measure rankings was calculated using the Spearman correlation coefficient.

RESULTS

The distance-based performance measures balanced average Hausdorff distance (rank = 1) and average Hausdorff distance (rank = 2) provided the segmentation rankings with the highest average correlation with manual rankings. They were followed by overlap-based measures such as Dice coefficient (rank = 7), a standard performance measure in medical image segmentation.

CONCLUSIONS

Average Hausdorff distance-based measures should be used as a standard performance measure in evaluating cerebral vessel segmentation quality. They can identify more relevant segmentation errors, especially in high-quality segmentations. Our findings have the potential to accelerate the validation and development of novel vessel segmentation approaches.

Differentiation of Brain Tumor Microvasculature From Normal Vessels Using Optical Coherence Angiography

BACKGROUND AND OBJECTIVES

Despite rapid advances and discoveries in medical imaging, monitoring therapeutic efficacy for malignant gliomas and monitoring tumor vasculature remains problematic. The purpose of this study is to utilize optical coherence angiography for vasculature characterization inside and surrounding brain tumors in a murine xenograft brain tumor model. Features included in our analysis include fractional blood volume, vessel tortuosity, diameter, orientation, and directionality.

STUDY DESIGN/MATERIALS AND METHODS

In this study, five tumorous mice models at 4 weeks of age were imaged. Human glioblastoma cells were injected into the brain and allowed to grow for 4 weeks and then imaged using optical coherence tomography.

RESULTS

Results suggest that blood vessels outside the tumor contain a greater fractional blood volume as compared with vessels inside the tumor. Vessels inside the tumor are more tortuous as compared with those outside the tumor. Results indicate that vessels near the tumor margin are directed inward towards the tumor while normal vessels show a more random orientation.

CONCLUSION

Quantification of vascular microenvironments in brain gliomas can provide functional vascular parameters to aid various diagnostic and therapeutic studies. © 2021 Wiley Periodicals LLC.

Systematic review protocol to assess artificial intelligence diagnostic accuracy performance in detecting acute ischaemic stroke and large-vessel occlusions on CT and MR medical imaging

INTRODUCTION

The use of artificial intelligence (AI) to support the diagnosis of acute ischaemic stroke (AIS) could improve patient outcomes and facilitate accurate tissue and vessel assessment. However, the evidence in published AI studies is inadequate and difficult to interpret which reduces the accountability of the diagnostic results in clinical settings. This study protocol describes a rigorous systematic review of the accuracy of AI in the diagnosis of AIS and detection of large-vessel occlusions (LVOs).

METHODS AND ANALYSIS

We will perform a systematic review and meta-analysis of the performance of AI models for diagnosing AIS and detecting LVOs. We will adhere to the Preferred Reporting Items for Systematic Reviews and Meta-analyses Protocols guidelines. Literature searches will be conducted in eight databases. For data screening and extraction, two reviewers will use a modified Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies checklist. We will assess the included studies using the Quality Assessment of Diagnostic Accuracy Studies guidelines. We will conduct a meta-analysis if sufficient data are available. We will use hierarchical summary receiver operating characteristic curves to estimate the summary operating points, including the pooled sensitivity and specificity, with 95% CIs, if pooling is appropriate. Furthermore, if sufficient data are available, we will use Grading of Recommendations, Assessment, Development and Evaluations profiler software to summarise the main findings of the systematic review, as a summary of results.

ETHICS AND DISSEMINATION

There are no ethical considerations associated with this study protocol, as the systematic review focuses on the examination of secondary data. The systematic review results will be used to report on the accuracy, completeness and standard procedures of the included studies. We will disseminate our findings by publishing our analysis in a peer-reviewed journal and, if required, we will communicate with the stakeholders of the studies and bibliographic databases.

PROSPERO REGISTRATION NUMBER

CRD42020179652.

Automatic segmentation, feature extraction and comparison of healthy and stroke cerebral vasculature

Accurate segmentation of cerebral vasculature and a quantitative assessment of its morphology is critical to various diagnostic and therapeutic purposes and is pertinent to studying brain health and disease. However, this is still a challenging task due to the complexity of the vascular imaging data. We propose an automated method for cerebral vascular segmentation without the need of any manual intervention as well as a method to skeletonize the binary segmented map to extract vascular geometric features and characterize vessel structure. We combine a Hessian-based probabilistic vessel-enhancing filtering with an active-contour-based technique to segment magnetic resonance and computed tomography angiograms (MRA and CTA) and subsequently extract the vessel centerlines and diameters to calculate the geometrical properties of the vasculature. Our method was validated using a 3D phantom of the Circle-of-Willis region, demonstrating 84% mean Dice similarity coefficient (DSC) and 85% mean Pearson's correlation coefficient (PCC) with minimal modified Hausdorff distance (MHD) error (3 surface pixels at most), and showed superior performance compared to existing segmentation algorithms upon quantitative comparison using DSC, PCC and MHD. We subsequently applied our algorithm to a dataset of 40 subjects, including 1) MRA scans of healthy subjects (n = 10, age = 30 ± 9), 2) MRA scans of stroke patients (n = 10, age = 51 ± 15), 3) CTA scans of healthy subjects (n = 10, age = 62 ± 12), and 4) CTA scans of stroke patients (n = 10, age = 68 ± 11), and obtained a quantitative comparison between the stroke and normal vasculature for both imaging modalities. The vascular network in stroke patients compared to age-adjusted healthy subjects was found to have a significantly (p < 0.05) higher tortuosity (3.24 ± 0.88 rad/cm vs. 7.17 ± 1.61 rad/cm for MRA, and 4.36 ± 1.32 rad/cm vs. 7.80 ± 0.92 rad/cm for CTA), higher fractal dimension (1.36 ± 0.28 vs. 1.71 ± 0.14 for MRA, and 1.56 ± 0.05 vs. 1.69 ± 0.20 for CTA), lower total length (3.46 ± 0.99 m vs. 2.20 ± 0.67 m for CTA), lower total volume (61.80 ± 18.79 ml vs. 34.43 ± 22.9 ml for CTA), lower average diameter (2.4 ± 0.21 mm vs. 2.18 ± 0.07 mm for CTA), and lower average branch length (4.81 ± 1.97 mm vs. 8.68 ± 2.03 mm for MRA), respectively. We additionally studied the change in vascular features with respect to aging and imaging modality. While we observed differences between features as a result of aging, statistical analysis did not show any significant differences, whereas we found that the number of branches were significantly different (p < 0.05) between the two imaging modalities (201 ± 73 for MRA vs. 189 ± 69 for CTA). Our segmentation and feature extraction algorithm can be applied on any imaging modality and can be used in the future to automatically obtain the 3D segmented vasculature for diagnosis and treatment planning as well as to study morphological changes due to stroke and other cerebrovascular diseases (CVD) in the clinic.

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

Introduction: Surgical resection of brain tumors is often limited by adjacent critical structures such as blood vessels. Current intraoperative navigations systems are limited; most are based on two-dimensional (2D) guidance systems that require manual segmentation of any regions of interest (ROI; eloquent structures to avoid or tumor to resect). They additionally require time- and labor-intensive processing for any reconstruction steps. We aimed to develop a deep learning model for real-time fully automated segmentation of the intracranial vessels on preoperative non-angiogram imaging sequences. Methods: We identified 48 pediatric patients (10-months to 22-years old) with high resolution (0.5-1 mm axial thickness) isovolumetric, pre-operative T2 magnetic resonance images (MRIs). Twenty-eight patients had anatomically normal brains, and 20 patients had tumors or other lesions near the skull base. Manually segmented intracranial vessels (internal carotid, middle cerebral, anterior cerebral, posterior cerebral, and basilar arteries) served as ground truth labels. Patients were divided into 80/5/15% training/validation/testing sets. A modified 2-D Unet convolutional neural network (CNN) architecture implemented with 5 layers was trained to maximize the Dice coefficient, a measure of the correct overlap between the predicted vessels and ground truth labels. Results: The model was able to delineate the intracranial vessels in a held-out test set of normal and tumor MRIs with an overall Dice coefficient of 0.75. While manual segmentation took 1-2 h per patient, model prediction took, on average, 8.3 s per patient. Conclusions: We present a deep learning model that can rapidly and automatically identify the intracranial vessels on pre-operative MRIs in patients with normal vascular anatomy and in patients with intracranial lesions. The methodology developed can be translated to other critical brain structures. This study will serve as a foundation for automated high-resolution ROI segmentation for three-dimensional (3D) modeling and integration into an augmented reality navigation platform.

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network

The computed tomography angiography (CTA) postprocessing manually recognized by technologists is extremely labor intensive and error prone. We propose an artificial intelligence reconstruction system supported by an optimized physiological anatomical-based 3D convolutional neural network that can automatically achieve CTA reconstruction in healthcare services. This system is trained and tested with 18,766 head and neck CTA scans from 5 tertiary hospitals in China collected between June 2017 and November 2018. The overall reconstruction accuracy of the independent testing dataset is 0.931. It is clinically applicable due to its consistency with manually processed images, which achieves a qualification rate of 92.1%. This system reduces the time consumed from 14.22 ± 3.64 min to 4.94 ± 0.36 min, the number of clicks from 115.87 ± 25.9 to 4 and the labor force from 3 to 1 technologist after five months application. Thus, the system facilitates clinical workflows and provides an opportunity for clinical technologists to improve humanistic patient care.

Manual postprocessing of computed tomography angiography (CTA) images is extremely labor intensive and error prone. Here, the authors propose an artificial intelligence reconstruction system that can automatically achieve CTA reconstruction in healthcare services.

Cerebral Artery and Vein Segmentation in Four-dimensional CT Angiography Using Convolutional Neural Networks

Purpose

To implement and test a deep learning approach for the segmentation of the arterial and venous cerebral vasculature with four-dimensional (4D) CT angiography.

Materials and Methods

Patients who had undergone 4D CT angiography for the suspicion of acute ischemic stroke were retrospectively identified. A total of 390 patients evaluated in 2014 (n = 113) or 2018 (n = 277) were included in this study, with each patient having undergone one 4D CT angiographic scan. One hundred patients from 2014 were randomly selected, and the arteries and veins on their CT scans were manually annotated by five experienced observers. The weighted temporal average and weighted temporal variance from 4D CT angiography were used as input for a three-dimensional Dense-U-Net. The network was trained with the fully annotated cerebral vessel artery-vein maps from 60 patients. Forty patients were used for quantitative evaluation. The relative absolute volume difference and the Dice similarity coefficient are reported. The neural network segmentations from 277 patients who underwent scanning in 2018 were qualitatively evaluated by an experienced neuroradiologist using a five-point scale.

Results

The average time for processing arterial and venous cerebral vasculature with the network was less than 90 seconds. The mean Dice similarity coefficient in the test set was 0.80 ± 0.04 (standard deviation) for the arteries and 0.88 ± 0.03 for the veins. The mean relative absolute volume difference was 7.3% ± 5.7 for the arteries and 8.5% ± 4.8 for the veins. Most of the segmentations (n = 273, 99.3%) were rated as very good to perfect.

Conclusion

The proposed convolutional neural network enables accurate artery and vein segmentation with 4D CT angiography with a processing time of less than 90 seconds.© RSNA, 2020.

Automatic collateral circulation scoring in ischemic stroke using 4D CT angiography with low-rank and sparse matrix decomposition

PURPOSE

Sufficient collateral blood supply is crucial for favorable outcomes with endovascular treatment. The current practice of collateral scoring relies on visual inspection and thus can suffer from inter and intra-rater inconsistency. We present a robust and automatic method to score cerebral collateral blood supply to aid ischemic stroke treatment decision making. The developed method is based on 4D dynamic CT angiography (CTA) and the ASPECTS scoring protocol.

METHODS

The proposed method, ACCESS (Automatic Collateral Circulation Evaluation in iSchemic Stroke), estimates a target patient's unfilled cerebrovasculature in contrast-enhanced CTA using the lack of contrast agent due to clotting. To do so, the fast robust matrix completion algorithm with in-face extended Frank-Wolfe optimization is applied on a cohort of healthy subjects and a target patient, to model the patient's unfilled vessels and the estimated full vasculature as sparse and low-rank components, respectively. The collateral score is computed as the ratio of the unfilled vessels to the full vasculature, mimicking existing clinical protocols.

RESULTS

ACCESS was tested with 46 stroke patients and obtained an overall accuracy of 84.78%. The optimal threshold selection was evaluated using a receiver operating characteristics curve with the leave-one-out approach, and a mean area under the curve of 85.39% was obtained.

CONCLUSION

ACCESS automates collateral scoring to mitigate the shortcomings of the standard clinical practice. It is a robust approach, which resembles how radiologists score clinical scans, and can be used to help radiologists in clinical decisions of stroke treatment.

Multiscale modeling of human cerebrovasculature: A hybrid approach using image-based geometry and a mathematical algorithm

The cerebral vasculature has a complex and hierarchical network, ranging from vessels of a few millimeters to superficial cortical vessels with diameters of a few hundred micrometers, and to the microvasculature (arteriole/venule) and capillary beds in the cortex. In standard imaging techniques, it is difficult to segment all vessels in the network, especially in the case of the human brain. This study proposes a hybrid modeling approach that determines these networks by explicitly segmenting the large vessels from medical images and employing a novel vascular generation algorithm. The framework enables vasculatures to be generated at coarse and fine scales for individual arteries and veins with vascular subregions, following the personalized anatomy of the brain and macroscale vasculatures. In this study, the vascular structures of superficial cortical (pial) vessels before they penetrate the cortex are modeled as a mesoscale vasculature. The validity of the present approach is demonstrated through comparisons with partially observed data from existing measurements of the vessel distributions on the brain surface, pathway fractal features, and vascular territories of the major cerebral arteries. Additionally, this validation provides some biological insights: (i) vascular pathways may form to ensure a reasonable supply of blood to the local surface area; (ii) fractal features of vascular pathways are not sensitive to overall and local brain geometries; and (iii) whole pathways connecting the upstream and downstream entire-scale cerebral circulation are highly dependent on the local curvature of the cerebral sulci.

Cerebral autoregulation in the complex vascular networks of the brain is an amazing achievement. We believe that numerical analysis of the cerebral blood circulation using an anatomically precise vascular model provides a powerful tool for evaluating the direct relationships between local- and global-scale blood flows. However, there is a lack of information about the overall vascular pathways in the human brain, preventing a monolithic model of the human cerebrovasculature from being established. This paper presents a multiscale model of human cerebrovasculature based on a hybrid approach that uses image-based geometries and a newly developed mathematical algorithm. One important argument of this paper is the validity of the cerebrovasculature represented in the model, which reflects anatomical features of major cerebral vasculatures and brain shape, and has strong similarities with available data for human superficial cortical vessels. Investigations of the reconstructed model allow us to derive some biological insights and associated hypotheses for the cerebral vasculature. The authors believe the present cerebrovascular model can be applied to numerical simulations of the entire-scale cerebral blood flow.

Automatic Collateral Scoring From 3D CTA Images

The collateral score is an important biomarker in decision making for endovascular treatment (EVT) of patients with ischemic stroke. The existing collateral grading systems are based on visual inspection and prone to subjective interpretation and interobserver variation. The purpose of our work is the development of an automatic collateral scoring method. In this work, we present a method that is inspired by human collateral scoring. Firstly, we define an anatomical region by atlas-based registration and extract vessel structures using a deep convolutional neural network. From this, high-level features based on the ratios of vessel length and volume of the occluded and the contralateral side are defined. Multi-class classification models are used to map the feature space to a four-grade collateral score and a quantitative score. The dataset used for training, validation and testing is from a registry of images acquired in clinical routine at multiple medical centers. The model performance is tested on 269 subjects, achieving an accuracy of 0.8. The dichotomized collateral score accuracy is 0.9. The error is comparable to the interobserver variation, the results are comparable to the performance of two radiologists with 10 to 30 years of experience.

Statistical modeling and knowledge-based segmentation of cerebral artery based on TOF-MRA and MR-T1

BACKGROUND AND OBJECTIVE

For cerebrovascular segmentation from time-of-flight (TOF) magnetic resonance angiography (MRA), the focused issues are segmentation accuracy, vascular network coverage ratio, and cerebral artery and vein (CA/CV) separation. Therefore, cerebral artery segmentation is a challenging work, while a complete solution is lacking so far.

METHODS

The preprocessing of skull-stripping and Hessian-based feature extraction is first implemented to acquire an indirect prior knowledge of vascular distribution and shape. Then, a novel intensity- and shape-based Markov statistical modeling is proposed for complete cerebrovascular segmentation, where our low-level process employs a Gaussian mixture model to fit the intensity histogram of the skull-stripped TOF-MRA data, while our high-level process employs the vascular shape prior to construct the energy function. To regularize the individual data processes, Markov regularization parameter is automatically estimated by using a machine-learning algorithm. Further, cerebral artery and vein (CA/CV) separation is explored with a series of morphological logic operations, which are based on a direct priori knowledge on the relationship of arteriovenous topology and brain tissues in between TOF-MRA and MR-T1.

RESULTS

We employed 109 sets of public datasets from MIDAS for qualitative and quantitative assessment. The Dice similarity coefficient, false negative rate (FNR), and false positive rate (FPR) of 0.933, 0.158, and 0.091% on average, as well as CA/CV separation results with the agreement, FNR, and FPR of 0.976, 0.041, and 0.022 on average. For clinical visual assessment, our methods can segment various sizes of the vessel in different contrast region, especially performs better on vessels of small size in low contrast region.

CONCLUSION

Our methods obtained satisfying results in visual and quantitative evaluation. The proposed method is capable of accurate cerebrovascular segmentation and efficient CA/CV separation. Further, it can stimulate valuable clinical applications on the computer-assisted cerebrovascular intervention according to the neurosurgeon's recommendation.

Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures

Delineation of curvilinear structures in images is an important basic step of several image processing applications, such as segmentation of roads or rivers in aerial images, vessels or staining membranes in medical images, and cracks in pavements and roads, among others. Existing methods suffer from insufficient robustness to noise. In this paper, we propose a novel operator for the detection of curvilinear structures in images, which we demonstrate to be robust to various types of noise and effective in several applications. We call it RUSTICO, which stands for RobUST Inhibition-augmented Curvilinear Operator. It is inspired by the push-pull inhibition in visual cortex and takes as input the responses of two trainable B-COSFIRE filters of opposite polarity. The output of RUSTICO consists of a magnitude map and an orientation map. We carried out experiments on a data set of synthetic stimuli with noise drawn from different distributions, as well as on several benchmark data sets of retinal fundus images, crack pavements, and aerial images and a new data set of rose bushes used for automatic gardening. We evaluated the performance of RUSTICO by a metric that considers the structural properties of line networks (connectivity, area, and length) and demonstrated that RUSTICO outperforms many existing methods with high statistical significance. RUSTICO exhibits high robustness to noise and texture.

Self-adaptive weighted level set evolution based on local intensity difference for parotid ducts segmentation

BACKGROUND

Parotid ducts (PDs) play an important role in the diagnosis and treatment of parotid lesions. Segmentation of PDs from Cone beam computed tomography (CBCT) images has a significant impact to the pathological analysis of the parotid gland. Although level set methods (LSMs) have achieved considerable success in medical imaging segmentation, it is still a challenging task for existing LSMs to precisely and self-adaptively segment PDs from parotid duct (PD) images with both noise, intensity inhomogeneity, and vague boundary. In this paper, we propose a novel Self-adaptive Weighted level set method via Local intensity Difference (SWLD) to comprehensively solve the above issues.

METHOD

Firstly, a new adaptive weighted operator based on local intensity variance difference has been proposed to overcome the limitations of previous LSMs that are sensitive to parameters, which achieves the aim of automatic segmentation. Secondly, we introduce local intensity mean difference into the energy function to improve the curve evolution efficiency. Thirdly, we eliminate the effects of intensity inhomogeneity, noise, and boundary blur in the parotid image through a local similarity factor with two different neighborhood sizes.

RESULTS

Using the same dataset, segmentation of PDs is performed using the proposed SWLD algorithm and existing LSM algorithms. The mean Dice score for the proposed algorithm is 91.3%, and the corresponding mean Hausdorff distance (HD) is 1.746.

CONCLUSION

Experimental results demonstrate that the proposed algorithm is superior to many existing level set segmentation algorithms, and it can accurately and automatically segment the PDs even in complex gradient boundaries.

Color-Mapping of 4D-CTA for the Detection of Cranial Arteriovenous Shunts

BACKGROUND AND PURPOSE

4D CT angiography is increasingly used in clinical practice for the assessment of different neurovascular disorders. Optimized processing of 4D-CTA is crucial for diagnostic interpretation because of the large amount of data that is generated. A color-mapping method for 4D-CTA is presented for improved and enhanced visualization of the cerebral vasculature hemodynamics. This method was applied to detect cranial AVFs.

MATERIALS AND METHODS

All patients who underwent both 4D-CTA and DSA in our hospital from 2011 to 2018 for the clinical suspicion of a cranial AVF or carotid cavernous fistula were retrospectively collected. Temporal information in the cerebral vasculature was visualized using a patient-specific color scale. All color-maps were evaluated by 3 observers for the presence or absence of an AVF or carotid cavernous fistula. The presence or absence of cortical venous reflux was evaluated as a secondary outcome measure.

RESULTS

In total, 31 patients were included, 21 patients with and 10 without an AVF. Arterialization of venous structures in AVFs was accurately visualized using color-mapping. There was high sensitivity (86%-100%) and moderate-to-high specificity (70%-100%) for the detection of AVFs on color-mapping 4D-CTA, even without the availability of dynamic subtraction rendering. The diagnostic performance of the 3 observers in the detection of cortical venous reflux was variable (sensitivity, 43%-88%; specificity, 60%-80%).

CONCLUSIONS

Arterialization of venous structures can be visualized using color-mapping of 4D-CTA and proves to be accurate for the detection of cranial AVFs. This finding makes color-mapping a promising visualization technique for assessing temporal hemodynamics in 4D-CTA.

Semi-automated 3D segmentation of human skeletal muscle using Focused Ion Beam-Scanning Electron Microscopic images

Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) is an imaging approach that enables analysis of the 3D architecture of cells and tissues at resolutions that are 1-2 orders of magnitude higher than that possible with light microscopy. The slow speeds of data collection and manual segmentation are two critical problems that limit the more extensive use of FIB-SEM technology. Here, we present an easily accessible robust method that enables rapid, large-scale acquisition of data from tissue specimens, combined with an approach for semi-automated data segmentation using the open-source machine learning Weka segmentation software, which dramatically increases the speed of image analysis. We demonstrate the feasibility of these methods through the 3D analysis of human muscle tissue by showing that our process results in an improvement in speed of up to three orders of magnitude as compared to manual approaches for data segmentation. All programs and scripts we use are open source and are immediately available for use by others.

A U-Net Deep Learning Framework for High Performance Vessel Segmentation in Patients With Cerebrovascular Disease

Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based vessel segmentation algorithms need to be hand-crafted and are insufficiently validated. A specialized deep learning method-the U-net-is a promising alternative. Using labeled data from 66 patients with cerebrovascular disease, the U-net framework was optimized and evaluated with three metrics: Dice coefficient, 95% Hausdorff distance (95HD) and average Hausdorff distance (AVD). The model performance was compared with the traditional segmentation method of graph-cuts. Training and reconstruction was performed using 2D patches. A full and a reduced architecture with less parameters were trained. We performed both quantitative and qualitative analyses. The U-net models yielded high performance for both the full and the reduced architecture: A Dice value of ~0.88, a 95HD of ~47 voxels and an AVD of ~0.4 voxels. The visual analysis revealed excellent performance in large vessels and sufficient performance in small vessels. Pathologies like cortical laminar necrosis and a rete mirabile led to limited segmentation performance in few patients. The U-net outperfomed the traditional graph-cuts method (Dice ~0.76, 95HD ~59, AVD ~1.97). Our work highly encourages the development of clinically applicable segmentation tools based on deep learning. Future works should focus on improved segmentation of small vessels and methodologies to deal with specific pathologies.

Circle of Willis Collateral Flow in Carotid Artery Occlusion Is Depicted by 4D-CTA

BACKGROUND

In case of carotid artery occlusion, the risk and extent of ischemic cerebral damage are highly dependent on the pathways of collateral flow including the anatomy of the circle of Willis. In this report, cases are presented to illustrate that 4-dimensional computed tomography angiography (4D-CTA) can be considered as a noninvasive alternative to digital subtraction angiography for the evaluation of circle of Willis collateral flow.

CASE DESCRIPTION

Five patients with unilateral internal carotid artery (ICA) occlusion underwent 4D-CTA for the evaluation of intracranial hemodynamics. Next to a visual evaluation of 4D-CTA, temporal information was visualized using a normalized color scale on the cerebral vasculature, which enabled quantification of the contrast bolus arrival time. In these patients, 4D-CTA demonstrated dominant middle cerebral artery blood supply on the side of ICA occlusion originating from either the contralateral ICA or posterior circulation via the communicating arteries.

CONCLUSIONS

Temporal dynamics of collateral flow in the circle of Willis can be depicted with 4D-CTA in patients with a unilateral carotid artery occlusion.