Search

Coronary artery segmentation is an essential procedure in the computer-aided diagnosis of coronary artery disease. It aims to identify and segment the regions of interest in the coronary circulation for further processing and diagnosis. Currently, automatic segmentation of coronary arteries is often unreliable because of their small size and poor distribution of contrast medium, as well as the problems that lead to over-segmentation or omission. To improve the performance of convolutional-neural-network (CNN) based coronary artery segmentation, we propose a novel automatic method, DR-LCT-UNet, with two innovative components: the Dense Residual (DR) module and the Local Contextual Transformer (LCT) module. The DR module aims to preserve unobtrusive features through dense residual connections, while the LCT module is an improved Transformer that focuses on local contextual information, so that coronary artery-related information can be better exploited. The LCT and DR modules are effectively integrated into the skip connections and encoder-decoder of the 3D segmentation network, respectively. Experiments on our CorArtTS2020 dataset show that the dice similarity coefficient (DSC), Recall, and Precision of the proposed method reached 85.8%, 86.3% and 85.8%, respectively, outperforming 3D-UNet (taken as the reference among the 6 other chosen comparison methods), by 2.1%, 1.9%, and 2.1%., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Wang, Xu, Wang, Yang, Sun, Yang and Greenwald.)

Objective: The purpose of this study is to establish and evaluate an early biomarker prediction model of massive cerebral infarction caused by anterior circulation occlusion., Methods: One hundred thirty-four patients with acute cerebral infarction from January 2018 to October 2020 were selected to establish the development cohort for the internal test of the nomogram. Ninety-one patients with acute cerebral infarction hospitalized in our hospital from December 2020 to December 2021 were constituted the validation cohort for the external validation. All patients underwent baseline computed tomography (CT) scans within 12 h of onset and early imaging signs (hyperdense middle cerebral artery sign, obscuration of the lentiform nucleus, insular ribbon sign) of acute cerebral infarction were identified on CT by two neurologists. Based on follow-up CT images, patients were then divided into a massive cerebral infarction group and a non-massive cerebral infarction group. The nomogram model was constructed based on logistic regression analysis with R language. The nomogram was subsequently validated in an independent external validation cohort. Accuracy and discrimination of the prediction model were evaluated by a calibration chart, receiver operating characteristic (ROC) curve, and decision curve., Results: The indicators, including insular ribbon sign, reperfusion therapy, National Institutes of Health Stroke Scale (NHISS) score, previous cerebral infarction, and atrial fibrillation, were entered into the prediction model through binary logistic regression analysis. The prediction model showed good predictive ability. The area under the ROC curve of the prediction model was 0.848. The specificity, sensitivity, and Youden index were 0.864, 0.733, and 0.597, respectively. This nomogram to the validation cohort also showed good discrimination (AUC = 0.940, 95% CI 0.894-0.985) and calibration., Conclusion: Demonstrating favorable predictive efficacy and reproducibility, this study successfully established a prediction model of CT imaging signs and clinical data as early biomarkers of massive cerebral infarction caused by anterior circulation occlusion., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Chen, Li, Xu, Zhang, Qi, Yang, Chen, Wang and Duan.)

Objective: To quantitatively evaluate the impaired perfusion status of patients with symptomatic internal carotid artery (ICA) steno-occlusive disease and to explore the risk factors of impaired perfusion with computed tomography perfusion (CTP)., Methods: The clinical and imaging data of 187 patients with ICA steno-occlusive disease were retrospectively analyzed. The ICA stenosis rate was divided into Grades I-IV (70-79%; 80-89%; 90-99%; 100%), and the circle of Willis was classified as four types (types I-IV). According to the literature, the value of cerebral blood flow/cerebral blood volume (CBF/CBV) of 7.55/min was used as cut-off to predict symptomatic patients. All patients were categorized into two groups: those with impaired perfusion [ n = 99 (52.9%)] and those without impaired perfusion [ n = 88 (47.1%)]. Symmetrical bilateral internal watershed areas were selected as the regions of interest (ROIs). Statistical analysis was made on the status of impaired perfusion and the risk factors of impaired perfusion., Results: Univariate analysis revealed that systolic blood pressure (SBP), diastolic blood pressure (DBP), mean arterial pressure (MAP), types of the circle of Willis, and clinical features at admission differed between the two groups (patients with or without impaired perfusion) ( p < 0.05). Multiple logistic stepwise regression analysis showed that MAP [odds ratio (OR) = 0.946, 95% confidential interval (CI) = 0.917-0.974, p < 0.001] and type IV (type I vs. IV: OR = 4.987, 95% CI = 1.955-12.723, p = 0.001) at admission were independently associated with impaired perfusion in the internal watershed areas., Conclusion: MAP and the type of circle of Willis at admission are independent risk factors associated with the impaired perfusion in patients with ICA steno-occlusive disease., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Qiao, Duan, Zhang, Duan, Wang, Pei, Xu, Yang, Qi and Li.)

Objective: To explore the biomarkers of cerebral small vessel disease (CSVD) associated with cognitive impairment. Methods: A total of 69 patients with CSVD were enrolled in the study, and baseline clinical and imaging data were reviewed retrospectively. The following neuroimaging biomarkers of CSVD were identified: high-grade white matter hyperintensity (HWMH), cerebral microbleeds (CMB), enlarged perivascular space (PVS), and lacunar infarct (LI). A total score for CSVD was calculated. The deep medullary veins (DMVs) were divided into six segments according to the regional anatomy. The total DMV score (0-18) was derived from the sum of the scores of the six individual segments, the scores of which ranged from 0 to 3, for a semiquantitative assessment of the DMV that was based on segmental continuity and visibility. Results: The DMV score, patient age, and total CSVD score were independently associated with the presence or absence of cognitive impairment in patients with CSVD ( P < 0.05). By integrating patient age and the total CSVD and DMV scores, the area under the curve of the receiver operating characteristic curve (AUROC) for predicting CSVD associated with cognitive impairment was 0.885, and the sensitivity and specificity were 64.71 and 94.23%, respectively. Conclusions: The DMV score may be a novel imaging biomarker for CSVD associated with cognitive impairment. The integration of the DMV score with age and total CSVD score should increase the predictive value of the DMV score for CSVD associated with cognitive impairment., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Xu, Li, Xing, Song, Chen, Duan and Yang.)

Objective: To explore the relation between diffusion-weighted and susceptibility weighted imaging (DWI-SWI) mismatch and collateral circulation or prognosis in patients with occluded M1 segments of middle cerebral artery (MCA). Methods: We enrolled 59 patients with MCA M1-segment occlusion for a retrospective review of baseline clinical and imaging data. As markers of circulatory collaterals, prominent laterality of posterior (PLPCA) and anterior (PLACA) cerebral arteries on magnetic resonance angiography (MRA) studies and a hyperintense vessel sign (HVS) on T2 fluid-attenuated inversion recovery (FLAIR) images were collectively scored. The extent of acute cerebral infarction was then quantified on DWI, using the Alberta Stroke Program Early CT Score (DWI-ASPECTS). Hypointensity vessel sign prominence (PVS) was also evaluated by SWI and similarly scored (SWI-ASPECT) to calculate DWI-SWI mismatch [(DWI-ASPECTS) - (SWI-ASPECTS)], ranging from -10 to 10 points. Results: DWI-SWI mismatch showed significant associations with PLPCA, PLACA, HVS prominence, and collective collateral scores (all, p < 0.05). National Institutes of Health Stroke Scale (NIHSS), DWI-SWI mismatch, and DWI-ASPECTS also differed significantly according to patient prognosis (good vs. poor) after MCA M1-segment occlusion ( p < 0.05). In binary logistic regression analyses, NIHSS and DWI-SWI mismatch emerged as independent prognostic factors ( p < 0.05). Conclusions: Collateral circulation may be an important aspect of DWI-SWI mismatch, which in this study correlated with prognostic outcomes of MCA M1-segment occlusion., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Xu, Tong, Duan, Xing, Song, Pei and Yang.)

Background: This study was conducted to explore the risk factors of anterior circulation intracranial aneurysm rupture based on extracranial carotid artery (ECA) tortuosity. Methods: This retrospective study, conducted from January 1, 2017, to March 1, 2021, collected and reviewed the clinical and imaging data of 308 patients with anterior circulation intracranial aneurysm [133 (43.2%) patients in the ruptured aneurysm group; 175 (56.8%) patients in the unruptured aneurysm group]. Computed tomography angiography (CTA) of the head and neck was used to determine the ECA tortuosity (normal, simple tortuosity, kink, coil) and the morphologic parameters of the aneurysms. The relationship of aneurysm rupture to ECA tortuosity and the morphologic parameters were analyzed. Results: After univariate analysis, kink, angle of flow inflow (FA), aspect ratio (AR), aneurysm length ( L ), the distance from the tortuosity to the aneurysm (distance), and size ratio (SR) were significantly correlated with anterior circulation intracranial aneurysm rupture ( p < 0.05). Spearman correlation analysis showed that ECA tortuosity was correlated with FA and SR ( p < 0.05). Multiple logistic analyses showed that FA [odds ratio (OR), 1.013; 95% CI, 1.002-1.025], SR (OR, 1.521; 95% CI, 1.054-2.195), and kink (OR, 1.823; 95% CI, 1.074-3.096) were independently associated with aneurysm rupture. Conclusion: Study results suggest that FA, SR, and ECA kink were independent risk factors associated with anterior circulation intracranial aneurysm rupture., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Pei, Xu, Liang, Jin, Duan, Yang, Qiao, You and Xing.)

Malignant cerebral edema (MCE) after an ischemic stroke results in a poor outcome or death. Early prediction of MCE helps to identify subjects that could benefit from a surgical decompressive craniectomy. Net water uptake (NWU) in an ischemic lesion is a predictor of MCE; however, CT perfusion and lesion segmentation are required. This paper proposes a new Image Patch-based Net Water Uptake (IP-NWU) procedure that only uses non-enhanced admission CT and does not need lesion segmentation. IP-NWU is calculated by comparing the density of ischemic and contralateral normal patches selected from the middle cerebral artery (MCA) area using standard reference images. We also compared IP-NWU with the Segmented Region-based NWU (SR-NWU) procedure in which segmented ischemic regions from follow-up CT images are overlaid onto admission images. Furthermore, IP-NWU and its combination with imaging features are used to construct predictive models of MCE with a radiomics approach. In total, 116 patients with an MCA infarction (39 with MCE and 77 without MCE) were included in the study. IP-NWU was significantly higher for patients with MCE than those without MCE ( p < 0.05). IP-NWU can predict MCE with an AUC of 0.86. There was no significant difference between IP-NWU and SR-NWU, nor between their predictive efficacy for MCE. The inter-reader and interoperation agreement of IP-NWU was exceptional according to the Intraclass Correlation Coefficient (ICC) analysis (inter-reader: ICC = 0.92; interoperation: ICC = 0.95). By combining IP-NWU with imaging features through a random forest classifier, the radiomics model achieved the highest AUC (0.96). In summary, IP-NWU and radiomics models that combine IP-NWU with imaging features can precisely predict MCE using only admission non-enhanced CT images scanned within 24 h from onset., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2020 Fu, Qi, Tao, Xu, Kang, Yao, Yang, Duan and Chen.)

Objective: To assess the suitability of deep medullary vein visibility in susceptibility weighted imaging-magnetic resonance imaging studies as a method for the diagnosis and evaluation of cerebral small vessel disease progression., Methods: A total of 92 patients with CSVD were enrolled and baseline clinical and imaging data were reviewed retrospectively. Neuroimaging biomarkers of CSVD including high-grade white matter hyperintensity (HWMH), cerebral microbleed (CMB), enlarged perivascular space (PVS), and lacunar infarct (LI) were identified and CSVD burden was calculated. Cases were grouped accordingly as mild, moderate, or severe. The DMV was divided into six segments according to the regional anatomy. The total DMV score (0-18) was calculated as the sum of the six individual segmental scores, which ranged from 0 to 3, for a semi-quantitative assessment of the DMV based on segmental continuity and visibility., Results: The DMV score was independently associated with the presence of HWMH, PVS, and LI ( P < 0.05), but not with presence and absence of CMB ( P > 0.05). Correlation between the DMV score and the CSVD burden was significant ( P < 0.05) [OR 95% C.I., 1.227 (1.096-1.388)]., Conclusion: The DMV score was associated with the presence and severity of CSVD., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2020 Xu, Li, Wang, Xing, Pei, Yang and Duan.)

Objective: To explore the relationships of asymmetric deep medullary veins (ADMV) to asymmetric cortical veins (ACV), leptomeningeal collaterals and prognosis in patients with occlusion of a large cerebral artery. Methods: Clinical and imaging data of 56 patients with occlusion of a large cerebral artery were collected and reviewed. We assessed the time delayed between stroke onset and MR imaging (within 24 h of stroke onset), extension of cerebral infarction using the Alberta stroke program early CT score based on diffusion-weighted imaging (ASPECTs). ADMV and ACV were assessed using susceptibility-weighted imaging. The presence of ADMV (ACV) was defined as deep medullary veins (cortical veins) of the affected hemisphere that were greater in number and diameter than in the contralateral hemisphere. To evaluate leptomeningeal collaterals, the hyperintense vessel sign (HVS) was detected using T2 weighted fluid attenuated inversion recovery images. At 90 days, a modified Rankin scale score (mRS) was assessed to evaluate the clinical outcome. Results: Of 56 patients, 27 presented with ADMV. Those patients who presented with and without ADMV differed significantly in HVS and ACV ( P < 0.05) but not in time delayed between stroke onset and MR imaging, age, gender, stroke risk factors, baseline NIHSS score, or modified Rankin scale score at 3 months ( P > 0.05). Logistic regression analysis found that the presence of ADMV was independently related to HVS and ACV (ACV: OR 95% C.I., 1.287-4.368; HVS: OR 95% C.I., 1.132-4.887). Conclusions: The presence of ADMV on SWI was associated with prominent ACV and good leptomeningeal collateral flow but was not related to prognosis in patients with occlusion of a large cerebral artery., (Copyright © 2019 Xu, Duan, Yang, Huang, Pei and Li.)