A Fast-Processing Pipeline for Three-dimensional Visualization of Acute Ischemic Stroke lesion topography

BackgroundThe aim of this study was to assess reperfusion and clinical outcome of treatment with the self-expanding retrievable Separator 3D in revascularization of acute ischemic stroke. The three-dimensional (3D) device secures thrombus with direct aspiration and supports debulking of the clot.MethodsAt two centers, 129 consecutive stroke patients with National Institutes of Health Stroke Scale (NIHSS) scores ≥5 were treated with mechanical thrombectomy using the Separator 3D as a component of the Penumbra System within 8 h of symptom onset; modified Treatment in Cerebral Infarction (mTICI) revascularization scores, NIHSS score on admission and discharge, mortality rates, and modified Rankin Scale (mRS) outcomes at 90 days were evaluated.ResultsA total of 129 vessels in 129 patients were treated. Occlusions were located in the middle cerebral artery (MCA, 48%), internal carotid artery (ICA, 33%), cervical ICA–MCA (3%), and vertebrobasilar arteries (16%). Intravenous thrombolytic therapy with recombinant tissue plasminogen activator was given to 78% of patients. Median NIHSS was 15 prior to treatment. Reperfusion to mTICI 2b or 3 was successful in 96/129 (74%) target arterial lesions, with more than half of cases (51%) achieving mTICI 3. The mean time from arterial puncture to revascularization was 65 min. At 90 days, the symptomatic intracranial hemorrhage rate was 4%, all cause mortality was 32%, and 43/99 patients (43%) achieved functional independence with an mRS score of ≤2.ConclusionsThe results suggest that the Separator 3D enables safe and effective revascularization of occluded large arteries in acute stroke intervention, leading to a high rate of functional independence at 90 days.

Download Full-text

Deep Learning-Based Acute Ischemic Stroke Lesion Segmentation Method on Multimodal MR Images Using a Few Fully Labeled Subjects

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/3628179 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Bin Zhao ◽

Zhiyang Liu ◽

Guohua Liu ◽

Chen Cao ◽

Song Jin ◽

...

Keyword(s):

Ischemic Stroke ◽

Acute Ischemic Stroke ◽

Segmentation Method ◽

Lesion Segmentation ◽

Resonance Imaging ◽

Mr Images ◽

Dice Coefficient ◽

Automatic Methods ◽

Stroke Lesion ◽

Magnetic Resonance Imaging Mri

Acute ischemic stroke (AIS) has been a common threat to human health and may lead to severe outcomes without proper and prompt treatment. To precisely diagnose AIS, it is of paramount importance to quantitatively evaluate the AIS lesions. By adopting a convolutional neural network (CNN), many automatic methods for ischemic stroke lesion segmentation on magnetic resonance imaging (MRI) have been proposed. However, most CNN-based methods should be trained on a large amount of fully labeled subjects, and the label annotation is a labor-intensive and time-consuming task. Therefore, in this paper, we propose to use a mixture of many weakly labeled and a few fully labeled subjects to relieve the thirst of fully labeled subjects. In particular, a multifeature map fusion network (MFMF-Network) with two branches is proposed, where hundreds of weakly labeled subjects are used to train the classification branch, and several fully labeled subjects are adopted to tune the segmentation branch. By training on 398 weakly labeled and 5 fully labeled subjects, the proposed method is able to achieve a mean dice coefficient of 0.699 ± 0.128 on a test set with 179 subjects. The lesion-wise and subject-wise metrics are also evaluated, where a lesion-wise F1 score of 0.886 and a subject-wise detection rate of 1 are achieved.

Download Full-text