Noncontrast Computed Tomography versus Computed Tomography Angiography Source Images for Predicting Final Infarct Size in Anterior Circulation Acute Ischemic Stroke: a Prospective Cohort Study.

BACKGROUND: There has been a recent debate regarding the superiority of computed tomography angiography source images (CTASIs) over noncontrast computed tomography (NCCT) to predict the final infarct size in acute ischemic stroke (AIS). We hypothesized that the parenchymal abnormality on CTASI in faster scanners would overestimate ischemic core. METHODS: This prospective study assessed the correlation of Alberta Stroke Program Early CT Score (ASPECTS) on NCCT, CTASI, and computed tomography perfusion (CTP) with final infarct size in patients within 8 hours of AIS. Follow-up with NCCT or diffusion-weighted magnetic resonance imaging (MRI) was performed at 24 hours. Correlations of NCCT and CTASI with final infarct size and with CTP parameters were assessed. Subgroup analysis was performed in patients who underwent intravenous thrombolysis or mechanical thrombectomy. Inter-rater reliability was tested using Spearman's rank correlation. A P value less than .05 was considered statistically significant. RESULTS: A total of 105 patients were included in the final analysis. NCCT had a stronger correlation with the final infarct size than did CTASI (Spearman's ρ = .85 versus .78, P = .13). We found an overestimation of the final infarct size by CTASI in 47.6% of the cases, whereas NCCT underestimated infarct size in 60% of the patients. NCCT correlated most strongly with CBV (ρ = .93), whereas CTASI correlated most strongly with CBF (ρ = .87). Subgroup analysis showed less correlation of CTASI with final infarct size in the group that received thrombolysis versus the group that did not (ρ = .70 versus .88, P = .01). CONCLUSION: In a 256-slice scanner, the CTASI parenchymal abnormality includes ischemic penumbra and thus overestimates final infarct size-this could result in inappropriate exclusion of patients from thrombolysis or thrombectomy.

Conjoined Pathways: Unraveling the Coexistence of Developmental Venous Anomaly With Arteriovenous Malformation.

Developmental venous anomalies (DVAs) are intracranial vascular malformations typically characterized by their benign nature, often obviating the need for radiological follow-up. These anomalies arise from variations in the standard drainage pattern. While previously deemed congenital, there has been ongoing debate about a developmental component contributing to their etiology. They frequently coexist with other cerebral venous malformations (CVM); however, their association with arteriovenous malformations (AVM) is exceedingly rare. Such mixed malformations pose a therapeutic challenge, necessitating meticulous consideration for appropriate treatment. We present a noteworthy case involving a patient with arteriovenous malformation along with dual developmental venous anomalies, one of which served as the draining vein for the AVM.

Computed tomographic and digital subtraction angiography evaluation of ophthalmic-ethmoidal artery dural arteriovenous fistula.

Ophthalmic-ethmoidal dural arteriovenous fistula (DAVFs) is a rare type of dural arteriovenous fistulas and usually presenting with spontaneous subarachnoid hemorrhage, subdural hemorrhage or ocular symptoms. We present a case of a 59-year old gentleman presenting with acute headache, vomiting and generalized weakness. CT study of the brain revealed a large left frontal hematoma and abnormal aneurysmal sac with dilated cortical vein, communicating with the superior sagittal sinus. Conventional angiography confirmed diagnosis of ruptured ophthalmic-ethmoidal DAVF, resulting in a frontal intra-axial hemorrhage. Anterior fossa DAVFs are extremely rare, difficult to diagnose and treat. CT angiography is initial method of diagnosis, but digital substruction angiography remains the gold standard of confirming dural fistulas.

A lightweight asymmetric U-Net framework for acute ischemic stroke lesion segmentation in CT and CTP images.

BACKGROUND AND OBJECTIVES: This paper has introduced a patch-based, residual, asymmetric, encoder-decoder CNN that solves two major problems in acute ischemic stroke lesion segmentation from CT and CT perfusion data using deep neural networks. First, the class imbalance is encountered since the lesion core size covers less than 5% of the volume of the entire brain. Second, deeper neural networks face the drawback of vanishing gradients, and this degrades the learning ability of the network. METHODS: The neural network architecture has been designed for better convergence and faster inference time without compromising performance to address these difficulties. It uses a training strategy combining Focal Tversky and Binary cross-entropy loss functions to overcome the class imbalance issue. The model comprises only four resolution steps with a total of 11 convolutional layers. A base filter of 8, used for the residual connection with two convolutional blocks at the encoder side, is doubled after each resolution step. Simultaneously, the decoder consists of residual blocks with one convolutional layer and a constant number of 8 filters in each resolution step. This proposition allows for a lighter build with fewer trainable parameters as well as aids in avoiding overfitting by allowing the decoder to decode only necessary information. RESULTS: The presented method has been evaluated through submission on the publicly accessible platform of the Ischemic Stroke Lesion Segmentation (ISLES) 2018 medical image segmentation challenge achieving the second-highest testing dice similarity coefficient (DSC). The experimental results demonstrate that the proposed model achieves comparable performance to other submitted strategies in terms of DSC Precision, Recall, and Absolute Volume Difference (AVD). CONCLUSIONS: Through the proposed approach, the two major research gaps are coherently addressed while achieving high challenge scores by solving the mentioned problems. Our model can serve as a tool for clinicians and radiologists to hasten decision-making and detect strokes efficiently.

CSNet: A new DeepNet framework for ischemic stroke lesion segmentation.

BACKGROUND AND OBJECTIVES: Acute stroke lesion segmentation is of paramount importance as it can aid medical personnel to render a quicker diagnosis and administer consequent treatment. Automation of this task is technically exacting due to the variegated appearance of lesions and their dynamic development, medical discrepancies, unavailability of datasets, and the requirement of several MRI modalities for imaging. In this paper, we propose a composite deep learning model primarily based on the self-similar fractal networks and the U-Net model for performing acute stroke diagnosis tasks automatically to assist as well as expedite the decision-making process of medical practitioners. METHODS: We put forth a new deep learning architecture, the Classifier-Segmenter network (CSNet), involving a hybrid training strategy with a self-similar (fractal) U-Net model, explicitly designed to perform the task of segmentation. In fractal networks, the underlying design strategy is based on the repetitive generation of self-similar fractals in place of residual connections. The U-Net model exploits both spatial as well as semantic information along with parameter sharing for a faster and efficient training process. In this new architecture, we exploit the benefits of both by combining them into one hybrid training scheme and developing the concept of a cascaded architecture, which further enhances the model's accuracy by removing redundant parts from the Segmenter's input. Lastly, a voting mechanism has been employed to further enhance the overall segmentation accuracy. RESULTS: The performance of the proposed architecture has been scrutinized against the existing state-of-the-art deep learning architectures applied to various biomedical image processing tasks by submission on the publicly accessible web platform provided by the MICCAI Ischemic Stroke Lesion Segmentation (ISLES) challenge. The experimental results demonstrate the superiority of the proposed method when compared to similar submitted strategies, both qualitatively and quantitatively in terms of some of the well known evaluation metrics, such as Accuracy, Dice-Coefficient, Recall, and Precision. CONCLUSIONS: We believe that our method may find use as a handy tool for doctors to identify the location and extent of irreversibly damaged brain tissue, which is said to be a critical part of the decision-making process in case of an acute stroke.