CT perfusion imaging is commonly used for infarct core quantification in acute ischemic stroke patients. The outcomes and perfusion maps of CT perfusion software, however, show many discrepancies between vendors. We aim to perform infarct core segmentation directly from CT perfusion source data using machine learning, excluding the need to use the perfusion maps from standard CT perfusion software. To this end, we present a symmetry-aware spatio-temporal segmentation model that encodes the micro-perfusion dynamics in the brain, while decoding a static segmentation map for infarct core assessment. Our proposed spatio-temporal PerfU-Net employs an attention module on the skip-connections to match the dimensions of the encoder and decoder. We train and evaluate the method on 94 and 62 scans, respectively, using the Ischemic Stroke Lesion Segmentation (ISLES) 2018 challenge data. We achieve state-of-the-art results compared to methods that only use CT perfusion source imaging with a Dice score of 0.46. We are almost on par with methods that use perfusion maps from third party software, whilst it is known that there is a large variation in these perfusion maps from various vendors. Moreover, we achieve improved performance compared to simple perfusion map analysis, which is used in clinical practice.

CT perfusion imaging is important in the imaging workup of acute ischemic stroke for evaluating affected cerebral tissue. CT perfusion analysis software produces cerebral perfusion maps from commonly noisy spatio-temporal CT perfusion data. High levels of noise can influence the results of CT perfusion analysis, necessitating software tuning. This work proposes a novel approach for CT perfusion analysis that uses physics-informed learning, an optimization framework that is robust to noise. In particular, we propose SPPINN: Spatio-temporal Perfusion Physics-Informed Neural Network and research spatio-temporal physics-informed learning. SPPINN learns implicit neural representations of contrast attenuation in CT perfusion scans using the spatio-temporal coordinates of the data and employs these representations to estimate a continuous representation of the cerebral perfusion parameters. We validate the approach on simulated data to quantify perfusion parameter estimation performance. Furthermore, we apply the method to in-house patient data and the public Ischemic Stroke Lesion Segmentation 2018 benchmark data to assess the correspondence between the perfusion maps and reference standard infarct core segmentations. Our method achieves accurate perfusion parameter estimates even with high noise levels and differentiates healthy tissue from infarcted tissue. Moreover, SPPINN perfusion maps accurately correspond with reference standard infarct core segmentations. Hence, we show that using spatio-temporal physics-informed learning for cerebral perfusion estimation is accurate, even in noisy CT perfusion data. The code for this work is available at https://github.com/lucasdevries/SPPINN.

Objectives: This study aims to: (1) develop and evaluate a quantitative assessment of collateral status in the downstream area of an occluded intracranial artery in acute ischemic stroke and compare this method to middle cerebral artery (MCA)-based assessment; (2) determine the agreement between the automated occlusion-downstream area collateral score (ODACS) and expert raters’ assessments, and compare this to inter-rater agreement. Methods: Patients from MR CLEAN-NO IV and MR CLEAN Registry with a proximal M1, distal M1, or M2 occlusion were included. Using the hypoperfused area from CT perfusion (CTP) as a proxy for the occlusion-downstream territory and automated vessel segmentations from CT angiography (CTA), ODACS is calculated as the vessel volume ratio between downstream ipsilateral and its contralateral regions. ODACS was compared to a whole MCA-territory approach and evaluated against visual scoring by two expert raters that visually estimated ODACS using CTA and CTP, and their inter-rater agreement. Results: The study included 204 patients with a proximal M1 (52%), distal M1 (32%), or M2 (16%) occlusion. ODACS yielded lower collateral scores than MCA-based scoring for all occlusion locations, with larger differences in more distal occlusions. For M2 occlusions, 58% of patients shifted from good (> 50%) to poor (≤ 50%) collateral filling of the occluded territory using ODACS. Moderate (weighted Cohen’s kappa κ = 0.45) inter-rater agreement and fair (κ = 0.35) to moderate (κ = 0.51) ODACS-rater agreement were observed. Conclusions: ODACS yields lower collateral scores compared to MCA-based scoring and is comparable to scores from expert raters. Key Points: Question CT angiography-based collateral assessment in the MCA territory is inadequate to assess the collateral status in patients with distal vessel occlusions. Findings Our automated ODACS revealed lower collateral scores than traditional whole-territory assessment, especially in distal vessel occlusions. Clinical relevance The more precise evaluation of affected brain territories through automated occlusion-downstream area assessments prevents an overestimation of collateral status in distal occlusions, which could lead to improved patient selection and treatment decisions in acute stroke care. Graphical

Background/Objectives: Computer-aided vessel occlusion detection for acute ischemic stroke is typically developed on early-phase CT angiography (CTA). In late-phase CTA, enhanced venous contrast can mimic arterial occlusions and lead to incorrect occlusion detections. To counteract this, we propose a constraint-based post-processing framework that leverages anatomical and temporal vascular information from CT perfusion (CTP) scans. Methods: Vascular anatomy and relative contrast-arrival times were encoded as time–vessel maps. Three complementary constraints worked on these maps to remove incorrect detections based on distance-to-vessel truncation points, contrast-arrival time, and spatial priors. Constraints were fixed on a 32-case late-phase development subset and applied to an external held-out cohort of late-phase CTA (N = 354). To enable application without CTP, an auxiliary CTA-to-time–vessel map generator was designed to estimate maps directly from CTA. Results: In the external cohort, the framework reduced incorrect occlusions per scan from 3.9 (95% CI 3.6–4.2) to 2.1 (95% CI 1.9–2.3), preserving occlusion-level sensitivity at 80% (95% CI 69–91). The patient-level AUROC was 83 for the baseline versus 88 with post-processing. Improvements were also observed in detectors exposed to late-phase CTA, where post-processing reduced incorrect occlusions per scan from 2.8 to 1.9. As only 51 occlusion-positive cases were present in the external cohort, confidence intervals were wide. Consequently, these estimates should be interpreted with caution. Conclusions: Anatomically and temporally informed post-processing reduced incorrect occlusion detections in late-phase CTA without measurable loss of sensitivity, potentially improving robustness against CTA phase changes in external institutions.