-
1دورية أكاديمية
المؤلفون: Werdiger, Freda, Parsons, Mark W., Visser, Milanka, Levi, Christopher, Spratt, Neil, Kleinig, Tim, Lin, Longting, Bivard, Andrew
المصدر: Frontiers in Neurology ; volume 14 ; ISSN 1664-2295
مصطلحات موضوعية: Neurology (clinical), Neurology
الوصف: Introduction Computed tomography perfusion (CTP) imaging is widely used in cases of suspected acute ischemic stroke to positively identify ischemia and assess suitability for treatment through identification of reversible and irreversible tissue injury. Traditionally, this has been done via setting single perfusion thresholds on two or four CTP parameter maps. We present an alternative model for the estimation of tissue fate using multiple perfusion measures simultaneously. Methods We used machine learning (ML) models based on four different algorithms, combining four CTP measures (cerebral blood flow, cerebral blood volume, mean transit time and delay time) plus 3D-neighborhood (patch) analysis to predict the acute ischemic core and perfusion lesion volumes. The model was developed using 86 patient images, and then tested further on 22 images. Results XGBoost was the highest-performing algorithm. With standard threshold-based core and penumbra measures as the reference, the model demonstrated moderate agreement in segmenting core and penumbra on test images. Dice similarity coefficients for core and penumbra were 0.38 ± 0.26 and 0.50 ± 0.21, respectively, demonstrating moderate agreement. Skull-related image artefacts contributed to lower accuracy. Discussion Further development may enable us to move beyond the current overly simplistic core and penumbra definitions using single thresholds where a single error or artefact may lead to substantial error.
-
2دورية أكاديمية
المؤلفون: Chen, Cuiping, Yang, Jianhong, Han, Qing, Wu, Yuefei, Li, Jichuan, Xu, Tianqi, Sun, Jie, Gao, Xiang, Huang, Yi, Parsons, Mark W., Lin, Longting
المصدر: Frontiers in Neurology ; volume 14 ; ISSN 1664-2295
مصطلحات موضوعية: Neurology (clinical), Neurology
الوصف: Objective The study aimed to explore the association between midline shift (MLS) and net water uptake (NWU) within the ischemic penumbra in acute ischemic stroke patients. Methods This was a retrospective cohort study that examined patients with anterior circulation stroke. Net water uptake within the acute ischemic core and penumbra was calculated using data from admission multimodal CT scans. The primary outcome was severe cerebral edema measured by the presence of MLS on 24 to 48 h follow-up CT scans. The presence of a significant MLS was defined by a deviation of the septum pellucidum from the midline on follow-up CT scans of at least 3 mm or greater due to the mass effect of ischemic edema. The net water uptake was compared between patients with and without MLS, followed by logistic regression analyses and receiver operating characteristics (ROCs) to assess the predictive power of net water uptake in MLS. Results A total of 133 patients were analyzed: 50 patients (37.6%) with MLS and 83 patients (62.4%) without. Compared to patients without MLS, patients with MLS had higher net water uptake within the core [6.8 (3.2–10.4) vs. 4.9 (2.2–8.1), P = 0.048] and higher net water uptake within the ischemic penumbra [2.9 (1.8–4.3) vs. 0.2 (−2.5–2.7), P < 0.001]. Penumbral net water uptake had higher predictive performance than net water uptake of the core in MLS [area under the curve: 0.708 vs. 0.603, p < 0.001]. Moreover, the penumbral net water uptake predicted MLS in the multivariate regression model, adjusting for age, sex, admission National Institutes of Health Stroke Scale (NIHSS), diabetes mellitus, atrial fibrillation, ischemic core volume, and poor collateral vessel status (OR = 1.165; 95% CI = 1.002–1.356; P = 0.047). No significant prediction was found for the net water uptake of the core in the multivariate regression model. Conclusion Net water uptake measured acutely within the ischemic penumbra could predict severe cerebral edema at 24–48 h.
