Automated classification of cerebral arteries in MRA images and its application to maximum intensity projection

Automated in-depth cerebral arterial labelling using cerebrovascular vasculature reframing and deep neural networks

Identifying the cerebral arterial branches is essential for undertaking a computational approach to cerebrovascular imaging. However, the complexity and inter-individual differences involved in this process have not been thoroughly studied. We used machine learning to examine the anatomical profile of the cerebral arterial tree. The method is less sensitive to inter-subject and cohort-wise anatomical variations and exhibits robust performance with an unprecedented in-depth vessel range. We applied machine learning algorithms to disease-free healthy control subjects (n = 42), patients with stroke with intracranial atherosclerosis (ICAS) (n = 46), and patients with stroke mixed with the existing controls (n = 69). We trained and tested 70% and 30% of each study cohort, respectively, incorporating spatial coordinates and geometric vessel feature vectors. Cerebral arterial images were analyzed based on the 'segmentation-stacking' method using magnetic resonance angiography. We precisely classified the cerebral arteries across the exhaustive scope of vessel components using advanced geometric characterization, redefinition of vessel unit conception, and post-processing algorithms. We verified that the neural network ensemble, with multiple joint models as the combined predictor, classified all vessel component types independent of inter-subject variations in cerebral arterial anatomy. The validity of the categorization performance of the model was tested, considering the control, ICAS, and control-blended stroke cohorts, using the area under the receiver operating characteristic (ROC) curve and precision-recall curve. The classification accuracy rarely fell outside each image's 90-99% scope, independent of cohort-dependent cerebrovascular structural variations. The classification ensemble was calibrated with high overall area rates under the ROC curve of 0.99-1.00 [0.97-1.00] in the test set across various study cohorts. Identifying an all-inclusive range of vessel components across controls, ICAS, and stroke patients, the accuracy rates of the prediction were: internal carotid arteries, 91-100%; middle cerebral arteries, 82-98%; anterior cerebral arteries, 88-100%; posterior cerebral arteries, 87-100%; and collections of superior, anterior inferior, and posterior inferior cerebellar arteries, 90-99% in the chunk-level classification. Using a voting algorithm on the queued classified vessel factors and anatomically post-processing the automatically classified results intensified quantitative prediction performance. We employed stochastic clustering and deep neural network ensembles. Ma-chine intelligence-assisted prediction of vessel structure allowed us to personalize quantitative predictions of various types of cerebral arterial structures, contributing to precise and efficient decisions regarding the cerebrovascular disease.

Quantitative Analysis of the Cerebral Vasculature on Magnetic Resonance Angiography

The arterial connections in the Circle of Willis are a central source of collateral blood flow and play an important role in pathologies such as stroke and mental illness. Analysis of the Circle of Willis and its variants can shed light on optimal methods of diagnosis, treatment planning, surgery, and quantification of outcomes. We developed an automated, standardized, objective, and high-throughput approach for categorizing and quantifying the Circle of Willis vascular anatomy using magnetic resonance angiography images. This automated algorithm for processing of MRA images isolates and automatically identifies key features of the cerebral vasculature such as branching of the internal intracranial internal carotid artery and the basilar artery. Subsequently, physical features of the segments of the anterior cerebral artery were acquired on a sample and intra-patient comparisons were made. We demonstrate the feasibility of using our approach to automatically classify important structures of the Circle of Willis and extract biomarkers from cerebrovasculature. Automated image analysis can provide clinically-relevant vascular features such as aplastic arteries, stenosis, aneurysms, and vessel caliper for endovascular procedures. The developed algorithm could facilitate clinical studies by supporting high-throughput automated analysis of the cerebral vasculature.

Automatic labeling of cerebral arteries in magnetic resonance angiography

OBJECTIVES

In order to introduce 4D flow magnetic resonance imaging (MRI) as a standard clinical instrument for studying the cerebrovascular system, new and faster postprocessing tools are necessary. The objective of this study was to construct and evaluate a method for automatic identification of individual cerebral arteries in a 4D flow MRI angiogram.

MATERIALS AND METHODS

Forty-six elderly individuals were investigated with 4D flow MRI. Fourteen main cerebral arteries were manually labeled and used to create a probabilistic atlas. An automatic atlas-based artery identification method (AAIM) was developed based on vascular-branch extraction and the atlas was used for identification. The method was evaluated by comparing automatic with manual identification in 4D flow MRI angiograms from 67 additional elderly individuals.

RESULTS

Overall accuracy was 93%, and internal carotid artery and middle cerebral artery labeling was 100% accurate. Smaller and more distal arteries had lower accuracy; for posterior communicating arteries and vertebral arteries, accuracy was 70 and 89%, respectively.

CONCLUSION

The AAIM enabled fast and fully automatic labeling of the main cerebral arteries. AAIM functionality provides the basis for creating an automatic and powerful method to analyze arterial cerebral blood flow in clinical routine.

Anatomical labeling of the Circle of Willis using maximum a posteriori probability estimation

Anatomical labeling of the cerebral arteries forming the Circle of Willis (CoW) enables inter-subject comparison, which is required for geometric characterization and discovering risk factors associated with cerebrovascular pathologies. We present a method for automated anatomical labeling of the CoW by detecting its main bifurcations. The CoW is modeled as rooted attributed relational graph, with bifurcations as its vertices, whose attributes are characterized as points on a Riemannian manifold. The method is first trained on a set of pre-labeled examples, where it learns the variability of local bifurcation features as well as the variability in the topology. Then, the labeling of the target vasculature is obtained as maximum a posteriori probability (MAP) estimate where the likelihood of labeling individual bifurcations is regularized by the prior structural knowledge of the graph they span. The method was evaluated by cross-validation on 50 subjects, imaged with magnetic resonance angiography, and showed a mean detection accuracy of 95%. In addition, besides providing the MAP, the method can rank the labelings. The proposed method naturally handles anatomical structural variability and is demonstrated to be suitable for labeling arterial segments of the CoW.