30 September 2018 in IEEE Access
The patient with ischemic stroke can benefit most from the earliest possible definitive diagnosis. While a quantitative evaluation of the stroke lesions on the magnetic resonance images (MRIs) is effective in clinical diagnosis, manually segmenting the stroke lesions is commonly used, which is, however, a tedious and time-consuming task. Therefore, how to segment the stroke lesions in a fully automated manner has recently extracted extensive attentions. Considering that the clinically acquired MRIs usually have thick slices, we propose a 2D-slice-based segmentation method. In particular, we use multi-spectral MRIs, i.e., diffusion weighted image, apparent diffusion coefficient, and T2-weighted image, as input, and propose a residual-structured fully convolutional network (Res-FCN). The proposed Res-FCN is trained and evaluated on a large data set with 212 clinically acquired MRIs, which achieves a mean dice coefficient of 0.645 with a mean number of false negative lesions of 1.515 per subject. The proposed Res-FCN is further evaluated on a public data set, i.e., ISLES2015-SISS, which presents a very competitive result among all 2D-slice-based segmentation methods.
1 October 2017 in Radiology
The differences in structural damage and reorganization between capsular and pontine stroke emphasize the importance of lesion location–specific studies of patients with stroke. Purpose To investigate whether patients with capsular stroke (CS) and patients with pontine stroke (PS) involving the motor pathway have different types of structural damage and reorganization. Mat...
1 January 2017 in NeuroImage: Clinical
This study aimed to investigate the effects of lesion side and degree of motor recovery on gray matter volume (GMV) difference relative to healthy controls in right-handed subcortical stroke. Structural MRI data were collected in 97 patients with chronic subcortical ischemic stroke and 79 healthy controls. Voxel-wise GMV analysis was used to investigate the effects of lesion side and degree of motor recovery on GMV difference in right-handed chronic subcortical stroke patients. Compared with healthy controls, right-lesion patients demonstrated GMV increase (P < 0.05, voxel-wise false discovery rate correction) in the bilateral paracentral lobule (PCL) and supplementary motor area (SMA) and the right middle occipital gyrus (MOG); while left-lesion patients did not exhibit GMV difference under the same threshold. Patients with complete and partial motor recovery showed similar degree of GMV increase in right-lesion patients. However, the motor recovery was correlated with the GMV increase in the bilateral SMA in right-lesion patients. These findings suggest that there exists a lesion-side effect on GMV difference relative to healthy controls in right-handed patients with chronic subcortical stroke. The GMV increase in the SMA may facilitate motor recovery in subcortical stroke patients.
20 January 2022 in American Journal of Neuroradiology
BACKGROUND AND PURPOSE: Intracranial atherosclerotic plaque features are potential factors associated with recurrent stroke, but previous studies only focused on a single lesion, and few studies investigated them with perfusion impairment. This study aimed to investigate the association among whole-brain plaque features, perfusion deficit, and stroke recurrence. MATERIALS AND METHODS: Patients with ischemic stroke due to intracranial atherosclerosis were retrospectively collected and categorized into first-time and recurrent-stroke groups. Patients underwent high-resolution vessel wall imaging and DSC-PWI. Intracranial plaque number, culprit plaque features (such as plaque volume/burden, degree of stenosis, enhancement ratio), and perfusion deficit variables were recorded. Logistic regression analyses were performed to determine the independent factors associated with recurrent stroke. RESULTS: One hundred seventy-five patients (mean age, 59 [SD, 12] years; 115 men) were included. Compared with the first-time stroke group (n = 100), the recurrent-stroke group (n = 75) had a larger culprit volume (P = .006) and showed more intracranial plaques (P < .001) and more enhanced plaques (P = .003). After we adjusted for other factors, culprit plaque volume (OR, 1.16 per 10-mm3 increase; 95% CI, 1.03–1.30; P = .015) and total plaque number (OR, 1.31; 95% CI, 1.13–1.52; P < .001) were independently associated with recurrent stroke. Combining these factors increased the area under the curve to 0.71. CONCLUSIONS: Large culprit plaque and more intracranial plaques were independently associated with recurrent stroke. Performing whole-brain vessel wall imaging may help identify patients with a higher risk of recurrent stroke.
27 February 2020 in American Journal of Neuroradiology
BACKGROUND AND PURPOSE: Not all tandem occlusions diagnosed on traditional vascular imaging modalities, such as MRA, represent actual complete ICA occlusion. This study aimed to explore the utility of high-resolution vessel wall imaging in identifying true ICA tandem occlusions and screening patients for their suitability for endovascular recanalization. MATERIALS AND METHODS: Patients with no signal in the ICA on MRA were retrospectively reviewed. Two neuroradiologists independently reviewed their high-resolution vessel wall images to assess whether there were true tandem occlusions and categorized all cases into intracranial ICA occlusion, extracranial ICA occlusion, tandem occlusion, or near-occlusion. DSA classified patient images into the same 4 categories, which were used as the comparison with high-resolution vessel wall imaging. The suitability for recanalization of occluded vessels was evaluated on high-resolution vessel wall imaging compared with DSA. RESULTS: Forty-five patients with no ICA signal on MRA who had available high-resolution vessel wall imaging and DSA images were included. Among the 34 patients (34/45, 75.6%) with tandem occlusions on DSA, 18 cases also showed tandem occlusions on high-resolution vessel wall imaging. The remaining 16 patients, intracranial ICA, extracranial ICA occlusions and near-occlusions were found in 2, 6, and 8 patients, respectively, on the basis of high-resolution vessel wall imaging. A total of 20 cases (20/45, 44.4%) were considered suitable for recanalization on the basis of both DSA and high-resolution vessel wall imaging. Among the 25 patients deemed unsuitable for recanalization by DSA, 11 were deemed suitable for recanalization by high-resolution vessel wall imaging. CONCLUSIONS: High-resolution vessel wall imaging could allow identification of true ICA tandem occlusion in patients with an absence of signal on MRA. Findings on high-resolution vessel wall imaging can be used to screen more suitable candidates for recanalization therapy.
1 March 2019 in International Journal of Pediatric Otorhinolaryngology