Editorial: Imaging in Acute Stroke-New Options and State of the Art

A deep CT to MRI unpaired translation that preserve ischemic stroke lesions

Stroke is the second-leading cause of death world around. The immediate attention is key to patient prognosis. Ischemic stroke diagnosis typically involves neuroimaging studies (MRI and CT scans) and clinical protocols to characterize lesions and support decisions about treatment to be administered to the patient. Nowadays, multiparametric MRI images are the standard tool to visualize core and penumbra of ischemic stroke, supporting diagnosis and lesion prognosis. Specially, DWI modality (Diffusion Weighted Imaging) allows to quantify the cellular density of the tissue, and therefore allowing to quantify the lesion aggressiveness, and the recognition of micro-circulation properties. Nevertheless, MRI availability at hospitals is not widespread, and acquisition require special conditions requiring considerable time. Contrary, CT scans commonly have major availability but brain structures are poorly delineated, and even worse, ischemic lesions are only visible at advanced stages of the disease. This work introduces a deep generative strategy that allows ischemic stroke lesion translation over synthetic DWI-MRI images. This encoder-decoder architecture, include U-net modules, hierarchically organized, with inter-level connections that preserve brain structures, while codifying an embedding representation. Then a cyclic loss was here implemented to receive CT inputs and decode DWI-MRI images. To avoid mode collapse, this learning is inversely propagated, i.e., from synthetic DWI-MRI images to original CT-scans. Finally, an embedding projection is recovered to show a proper lesion-slice discrimination, regarding control studies. Clinical relevance- To recover synthetic DWI-MRI that preserved ischemic lesion using CT scans as an input and following an unpaired image translation setup.

Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study

In stroke imaging, CT angiography (CTA) is used for detecting arterial occlusions. These images could also provide information on the extent of ischemia. The study aim was to develop and evaluate a convolutional neural network (CNN)-based algorithm for detecting and segmenting acute ischemic lesions from CTA images of patients with suspected middle cerebral artery stroke. These results were compared to volumes reported by widely used CT perfusion-based RAPID software (IschemaView). A 42-layer-deep CNN was trained on 50 CTA volumes with manually delineated targets. The lower bound for predicted lesion size to reliably discern stroke from false positives was estimated. The severity of false positives and false negatives was reviewed visually to assess the clinical applicability and to further guide the method development. The CNN model corresponded to the manual segmentations with voxel-wise sensitivity 0.54 (95% confidence interval: 0.44-0.63), precision 0.69 (0.60-0.76), and Sørensen-Dice coefficient 0.61 (0.52-0.67). Stroke/nonstroke differentiation accuracy 0.88 (0.81-0.94) was achieved when only considering the predicted lesion size (i.e., regardless of location). By visual estimation, 46% of cases showed some false findings, such as CNN highlighting chronic periventricular white matter changes or beam hardening artifacts, but only in 9% the errors were severe, translating to 0.91 accuracy. The CNN model had a moderately strong correlation to RAPID-reported T_max > 10 s volumes (Pearson's r = 0.76 (0.58-0.86)). The results suggest that detecting anterior circulation ischemic strokes from CTA using a CNN-based algorithm can be feasible when accompanied with physiological knowledge to rule out false positives.

Indian College of Radiology and Imaging (ICRI) Consensus Guidelines for the Early Management of Patients with Acute Ischemic Stroke: Imaging and Intervention

The medical science has witnessed significant change in the management of acute stroke patients as a result of recent advances in the field of stroke imaging and endovascular mechanical thrombectomy in addition to intravenous thrombolysis and optimization of stroke services in balance with available resources. Despite initial negative trials, we witnessed the publication of five multicenter randomized clinical trials showing superiority of the endovascular approach over standard medical management in patients with large vessel occlusion. The aim of this study is to provide comprehensive set of evidence-based recommendations regarding imaging and endovascular interventions in acute ischemic stroke patients.

Portable, bedside, low-field magnetic resonance imaging for evaluation of intracerebral hemorrhage

Radiological examination of the brain is a critical determinant of stroke care pathways. Accessible neuroimaging is essential to detect the presence of intracerebral hemorrhage (ICH). Conventional magnetic resonance imaging (MRI) operates at high magnetic field strength (1.5-3 T), which requires an access-controlled environment, rendering MRI often inaccessible. We demonstrate the use of a low-field MRI (0.064 T) for ICH evaluation. Patients were imaged using conventional neuroimaging (non-contrast computerized tomography (CT) or 1.5/3 T MRI) and portable MRI (pMRI) at Yale New Haven Hospital from July 2018 to November 2020. Two board-certified neuroradiologists evaluated a total of 144 pMRI examinations (56 ICH, 48 acute ischemic stroke, 40 healthy controls) and one ICH imaging core lab researcher reviewed the cases of disagreement. Raters correctly detected ICH in 45 of 56 cases (80.4% sensitivity, 95%CI: [0.68-0.90]). Blood-negative cases were correctly identified in 85 of 88 cases (96.6% specificity, 95%CI: [0.90-0.99]). Manually segmented hematoma volumes and ABC/2 estimated volumes on pMRI correlate with conventional imaging volumes (ICC = 0.955, p = 1.69e-30 and ICC = 0.875, p = 1.66e-8, respectively). Hematoma volumes measured on pMRI correlate with NIH stroke scale (NIHSS) and clinical outcome (mRS) at discharge for manual and ABC/2 volumes. Low-field pMRI may be useful in bringing advanced MRI technology to resource-limited settings.

Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study

There is little evidence on the applicability of deep learning (DL) in the segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n = 2986) and B (n = 3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets, and six neuroradiologists created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B. The models subsequently fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist’s performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that the inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learning; thereby, their clinical applicability and generalizability could be improved.

Emerging stroke systems of care in Germany

In order to reduce intrahospital times for stroke patients, we have implemented various strategies throughout the last 4 years. Swift restoration of cerebral perfusion is essential for the outcomes of patients with acute ischemic stroke. Endovascular treatment (EVT) has become the standard of care to accomplish this in patients with acute stroke due to large vessel occlusion (LVO). To achieve reperfusion of ischemic brain regions as fast as possible, all in-hospital time delays have to be avoided. Therefore management of patients with acute ischemic stroke was optimized with an interdisciplinary standard operating procedure (SOP). Stroke neurologists, diagnostic as well as interventional neuroradiologists, and anesthesiologists streamlined all necessary processes from patient admission and diagnosis to EVT of eligible patients. In a second step we established a one-stop management of stroke patients, meaning that imaging was acquired with the same angiography suite use for treatment of patients with LVO. In the last section of this chapter we discuss the latest trials on stroke therapy and their implications for our current triage systems and imaging patterns.

Unusual presentation of basilar artery thrombosis

Strokes in the territory of the posterior cerebral artery (PCA) may rarely cause acute confusion or delirium, especially when bilateral or the dominant PCA are involved. Delirium as the only initial presentation of basilar artery thrombosis (with no brainstem or long tract findings) is an extremely rare occurrence. In this article, the clinical presentation of our case was an acute confusion with septic shock-like features (tachycardia, hypotension, and leukocytosis) for a few days without any focal deficit. These symptoms pointed more toward a non-focal neurological cause, especially meningoencephalitis. This case highlights the importance of detailed history and thorough evaluation of high-risk patients who present with an acute devastating neurological syndrome. In addition, knowledge of the atypical presentation of stroke should be acquired, and the limitation of an unenhanced computed tomography scan of the brain without vascular imaging should be known. Investigating patients with a sudden acute confusion should be directed toward the evaluation of the etiology in a stepwise manner. However, the pace of investigations should be fast to establish the diagnosis and optimize the outcome.