Automatic radiomic feature extraction using deep learning for angiographic parametric imaging of intracranial aneurysms.

BACKGROUND: Angiographic parametric imaging (API) is an imaging method that uses digital subtraction angiography (DSA) to characterize contrast media dynamics throughout the vasculature. This requires manual placement of a region of interest over a lesion (eg, an aneurysm sac) by an operator. OBJECTIVE: The purpose of our work was to determine if a convolutional neural network (CNN) was able to identify and segment the intracranial aneurysm (IA) sac in a DSA and extract API radiomic features with minimal errors compared with human user results. METHODS: Three hundred and fifty angiographic images of IAs were retrospectively collected. The IAs and surrounding vasculature were manually contoured and the masks put to a CNN tasked with semantic segmentation. The CNN segmentations were assessed for accuracy using the Dice similarity coefficient (DSC) and Jaccard index (JI). Area under the receiver operating characteristic curve (AUROC) was computed. API features based on the CNN segmentation were compared with the human user results. RESULTS: The mean JI was 0.823 (95% CI 0.783 to 0.863) for the IA and 0.737 (95% CI 0.682 to 0.792) for the vasculature. The mean DSC was 0.903 (95% CI 0.867 to 0.937) for the IA and 0.849 (95% CI 0.811 to 0.887) for the vasculature. The mean AUROC was 0.791 (95% CI 0.740 to 0.817) for the IA and 0.715 (95% CI 0.678 to 0.733) for the vasculature. All five API features measured inside the predicted masks were within 18% of those measured inside manually contoured masks. CONCLUSIONS: CNN segmentation of IAs and surrounding vasculature from DSA images is non-inferior to manual contours of aneurysms and can be used in parametric imaging procedures.

9.4T Magnetic Resonance Imaging of the Mouse Circle of Willis Enables Serial Characterization of Flow-Induced Vascular Remodeling by Computational Fluid Dynamics.

BACKGROUND: The neurovasculature dynamically responds to changes in cerebral blood flow by vascular remodeling processes. Serial imaging studies in mouse models could help characterize pathologic and physiologic flow-induced remodeling of the Circle of Willis (CoW). METHOD: We induced flow-driven pathologic cerebral vascular remodeling in the CoW of mice (n=3) by ligation of the left Common Carotid Artery (CCA), and the right external carotid and pterygopalatine arteries, increasing blood flow through the basilar and the right internal carotid arteries. One additional mouse was used as a wild-type control. Magnetic Resonance Imaging (MRI) at 9.4 Tesla (T) was used to serially image the mouse CoW over three months, and to obtain threedimensional images for use in Computational Fluid Dynamic (CFD) simulations. Terminal vascular corrosion casting and scanning electron microscope imaging were used to identify regions of macroscopic and microscopic arterial damage. RESULTS: We demonstrated the feasibility of detecting and serially measuring pathologic cerebral vascular changes in the mouse CoW, specifically in the anterior vasculature. These changes were characterized by bulging and increased vessel tortuosity on the anterior cerebral artery and aneurysm- like remodeling at the right olfactory artery origin. The resolution of the 9.4T system further allowed us to perform CFD simulations in the anterior CoW, which showed a correlation between elevated wall shear stress and pathological vascular changes. CONCLUSION: In the future, serial high-resolution MRI could be useful for characterizing the flow environments corresponding to other pathologic remodeling processes in the mouse CoW, such as aneurysm formation, subarachnoid hemorrhage, and ischemia.