Automatic Ischemic Core Estimation Based on Noncontrast-Enhanced Computed Tomography.

BACKGROUND: Evaluating the extent of ischemic change is an important step in deciding whether to use thrombolysis or mechanical thrombectomy, but the current standard method, Alberta Stroke Program Early CT Score, is semiquantitative and has low consistency among raters. We aim to create and test a fully automated machine learning-based ischemic core segmentation model using only noncontrast-enhanced computed tomography images. METHODS: In this multicenter retrospective study, patients with anterior circulation acute ischemic stroke who received both computed tomography (CT) and magnetic resonance imaging before thrombolysis or recanalization treatment between 2013 and 2019 were included. On CT, the ischemic core was manually delineated using the diffusion-weighted image and apparent diffusion coefficient maps. A deep learning-based ischemic core segmentation model (DL model) was developed using data from 3 institutions (n=272), and the model performance was validated using data from 3 institutions (n=106 Results: The median time ).between CT and magnetic resonance imaging in the validation cohort was 18 min. The DL model calculated ischemic core volume was significantly correlated with the reference standard (intraclass correlation coefficient, 0.90, P<0.01). Both the early time window (≤4.5 hours from onset; intraclass correlation coefficient, 0.90, P<0.01) and the late time window (>4.5 hours from onset; intraclass correlation coefficient, 0.93, P<0.01) had significant correlations. The median difference in ivolume between the model and the reference standard was 4.7 mL (interquartile range, 0.8-12.4 mL). The DL model performed well in distinguishing large ischemic cores (>70 mL), with a sensitivity of 84.2%, specificity of 97.7%, and area under the curve of 0.91. CONCLUSIONS: The deep learning-based ischemic core segmentation model, which was based on noncontrast-enhanced CT, demonstrated high accuracy in assessing ischemic core volume in patients with anterior circulation acute ischemic stroke.

Alberta Stroke Program Early CT Score Calculation Using the Deep Learning-Based Brain Hemisphere Comparison Algorithm.

OBJECTIVES: The Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a promising tool for the evaluation of stroke expansion to determine suitability for reperfusion therapy. The aim of this study was to validate deep learning-based ASPECTS calculation software that utilizes a three-dimensional fully convolutional network-based brain hemisphere comparison algorithm (3D-BHCA). MATERIALS AND METHODS: We retrospectively collected head non-contrast computed tomography (CT) data from 71 patients with acute ischemic stroke and 80 non-stroke patients. The results for ASPECTS on CT assessed by 5 stroke neurologists and by the 3D-BHCA model were compared with the ground truth by means of region-based and score-based analyses. RESULTS: In total, 151 patients and 3020 (151 × 20) ASPECTS regions were investigated. Median time from onset to CT was 195 min in the stroke patients. In region-based analysis, the sensitivity (0.80), specificity (0.97), and accuracy (0.96) of the 3D-BHCA model were superior to those of stroke neurologists. The sensitivity (0.98), specificity (0.92), and accuracy (0.97) of dichotomized ASPECTS > 5 analysis and the intraclass correlation coefficient (0.90) in total score-based analysis of the 3D-BHCA model were superior to those of stroke neurologists overall. When patients with stroke were stratified by onset-to-CT time, the 3D-BHCA model exhibited the highest performance to calculate ASPECTS, even in the earliest time period. CONCLUSIONS: The automated ASPECTS calculation software we developed using a deep learning-based algorithm was superior or equal to stroke neurologists in performing ASPECTS calculation in patients with acute stroke and non-stroke patients.

Zero-shot fMRI decoding with three-dimensional registration based on diffusion tensor imaging.

Functional magnetic resonance imaging (fMRI) acquisitions include a great deal of individual variability. This individuality often generates obstacles to the efficient use of databanks from multiple subjects. Although recent studies have suggested that inter-regional connectivity reflects individuality, conventional three-dimensional (3D) registration methods that calibrate inter-subject variability are based on anatomical information about the gray matter shape (e.g., T1-weighted). Here, we present a new registration method focusing more on the white matter structure, which is directly related to the connectivity in the brain, and apply it to subject-transfer brain decoding. Our registration method based on diffusion tensor imaging (DTI) transferred functional maps of each individual to a common anatomical space, where a decoding analysis of multi-voxel patterns was performed. The decoder trained on functional maps from other individuals in the common space showed a transfer decoding accuracy comparable to that of an individual decoder trained on single-subject functional maps. The DTI-based registration allowed more precise transformation of gray matter boundaries than a well-established T1-based method. These results suggest that the DTI-based registration is a promising tool for standardization of the brain functions, and moreover, will allow us to perform 'zero-shot' learning of decoders which is profitable in brain machine interface scenes.