Narrow Results

Quantitative analysis is vital for blood perfusion in ischemic stroke validating and predicting blood trend to refer and remedy on selection, operation and intervention. We leveraged the complex network modeling blood perfusion to pursue the changes and trends of blood flow in ischemic stroke. According to conversion of the flow chart from laser Doppler perfusion images of rats into the correlation matrix, the blood perfusion networks were formed and topology characters were quantitatively analyzed. The results verified the steal phenomenon and the compensatory ability in the vessel injury in accord with clinical indexes by the basic characters and efficiency, especially the interesting local efficiency. In addition, the outcomes exhibited consistently the small-world characters in the brain of rats. This computational model strengthened the new way of blood perfusion and potential predictions for stroke’s assessment, operation and prevention from the basic vascular dynamic indexes and complex networks.

Electrical acupoint stimulation (EAS) has been used to treat motor dysfunction of stroke patients with reportedly effective results. When we operate EAS treatment, we can modulate the intensity and frequency of stimulation. The purpose of this study is to evaluate the effect of different frequencies in treating motor dysfunction of ischemic stroke patients with EAS. The subjects of this study were 62 ischemic stroke patients with motor dysfunction in Kyunghee oriental medical center. They have been hospitalized after 1 week to 1 month from onset. They were treated with 2 Hz or 120 Hz EAS for 2 weeks, and had motor evoked potentials (MEPs) tests before and after 2 weeks of EAS treatment. We measured latency, central motor conduction time (CMCT) and amplitude of MEPs. After 2 weeks of treatment, we compared MEPs data of the affected side between the 2 Hz group and the 120 Hz group. The 2 Hz group showed more significant improvement than the 120 Hz group in latency, CMCT and amplitude (p = 0.008, 0.002, 0.002). In the case of the affected side MEPs data divided by normal side MEPs data, the 2 Hz group also showed higher improvement rate than the 120 Hz group in latency, CMCT and amplitude with significant differences (p = 0.003, 0.000, 0.008). These results suggest that low frequency EAS activates the central motor conduction system better than high frequency EAS, and EAS with low frequency could be more helpful for motor recovery after ischemic stroke than that with high frequency.

Ischemic stroke is one of the most common causes of death and disability that is induced by ischemia reperfusion (IR). Granulocyte adherence has been proven to be a principal cause of IR. Salvianolic acid A (Sal A) is one of the major active components of Danshen, a Chinese herbal medicine used for the treatment of cardiovascular and cerebrovascular diseases, such as ischemic stroke. Some experimental studies have shown the strong cerebral protection effect of Sal A. However, little information is available about the effect of Sal A on granulocyte adherence to brain micro-vascular endothelial cells (BMEC). Therefore, the aim of the present study was to investigate the effect of Sal A on the leukocyte adhesion rate and the intercellular cell adhesion molecule-1 (ICAM-1) expression in BMEC injured by hypoxia/reoxygenation (H/R), using a rheometer, qRT-PCR, and flow cytometry (FCM). The results of the adhesion rate gathered by the rheometer showed that Sal A could remarkably inhibit the adherence of granulocytes on BMEC in the case of H/R injury. Moreover, PCR and FCM results showed that Sal A could decrease the expression of ICAM-1 on BMEC on the gene and protein levels. In conclusion, the study demonstrated that the inhibition of granulocyte adherence is one of the targets of Sal A in the treatment of ischemic stroke. Meanwhile, Sal A inhibits of granulocyte adherence by decreasing the expression of ICAM-1 in BMEC.

Stroke is one of the most common causes of death and few pharmacological therapies show benefits in ischemic stroke. In this study, 290 patients aged 40–75 years old with first onset of acute ischemic stroke (more than 24 hours but within 14 days) were treated with standard treatments, and then were randomly allocated into an intervention group (treated with resuscitating acupuncture) and a control group (treated using sham-acupoints). Primary outcome measures included Barthel Index (BI), relapse and death up to six months. For the 290 patients in both groups, one case in the intervention group died, and two cases in the control group died from the disease (p = 0.558). Six patients of the 144 cases in the intervention group had relapse, whereas 34 of 143 patients had relapse in the control group (p < 0.001). The mean values for BI at six months were 70.25 ± 20.37 and 57.43 ± 19.61 for the two groups, respectively (p < 0.01). Acupuncture resulted in a significant difference between the two groups for the National Institute of Health Stroke Scale (NIHSS), not at two weeks (7.03 ± 3.201 vs. 8.13 ± 3.634; p = 0.067), but at four weeks (4.15 ± 2.032 vs. 6.35 ± 3.131, p < 0.01). The Chinese Stroke Scale (CSS) at four weeks showed more improvement in the intervention group than that in the control group (9.40 ± 4.51 vs. 13.09 ± 5.80, p < 0.001). Stroke Specific Quality of Life Scale (SS-QOL) at six months was higher in the intervention group (166.63 ± 45.70) than the control group (143.60 ± 50.24; p < 0.01). The results of this clinical trial showed a clinically relevant decrease of relapse in patients treated with resuscitating acupuncture intervention by the end of six months, compared with needling at the sham-acupoints. The resuscitating acupuncture intervention could also improve self-care ability and quality of life, evaluated with BI, NIHSS, CSS, Oxford Handicap Scale (OHS), and SS-QOL.

This study aimed to determine the efficacy of Integrated Rehabilitation Techniques of Traditional Chinese Medicine (IRT-TCM) on patients with ischemic stroke as an alternative therapy to conventional rehabilitation techniques. Sixty-nine patients with ischemic stroke were randomly assigned to receive either IRT-TCM (intervention group, n = 46) or conventional rehabilitation techniques (control group, n = 23). The IRT-TCM consisted of a sequential combination of acupuncture and massage techniques. The Fugl-Meyer Assessment (FMA), National Institutes of Health Stroke Scale (NIHSS), Barthel index (BI) and modified Rankin Scale (mRS) were measured on day 0 (baseline, before treatment), day 21, and day 90. We observed that the scores in FMA and BI were increased, and NIHSS were decreased in both groups on day 21 and 90, compared with the baseline (day 0). Furthermore, significantly better scores in FMA of lower limbs and NIHSS were found in patients treated with IRT-TCM on day 21 and 90. For mRS, the percentage of patients ranking 0 and 1 in the intervention group presented a striking contrast to the control group on day 90 but with no significant difference. The results indicated that, as a feasible alternative therapy, IRT-TCM is beneficial for patients with ischemic stroke. Further research with larger sample size, long-term observation, and strict blinding are still in need to confirm the efficacy of IRT-TCM.

Ischemic stroke is a clinical acute disease which causes neurological dysfunction and threatens a patient's life. Because the mechanism of pathology is complicated and most patients miss the best therapeutic window time, the effect of the treatment is not satisfied at present. Numerous studies indicated new vessels not only recuperated blood flow in the ischemic boundary zone, but also facilitated endogenous neurogenesis and improved neurological function after ischemic stroke. Therefore, angiogenesis has been an important research field in neurovascular regeneration. Recently, some Chinese medicines, bone marrow stromal cells (BMSCs) and their combination treatment were demonstrated to have beneficial effects in promoting angiogenesis both in vitro and in vivo. In this review, we summarized the effective mechanisms of Chinese medicines and BMSCs, as well as BMSCs in combination with Chinese medicines on angiogenesis post-stroke.

Traditional Chinese herbal products (CHPs) have been described in ancient medicine systems as treatments for various stroke-associated ailments. This study is aimed to investigate the prescription patterns and combinations of CHPs for ischemic stroke in Taiwan. Prescriptions of CHPs for ischemic stroke were obtained from the National Health Insurance Research Database (NHIRD) of Taiwan. Every prescription with a leading diagnosis of ischemic stroke made during 2000–2010 was analyzed. Descriptive statistics were applied to the pattern of co-prescriptions. Multiple logistic regression models were used to assess demographic and risk factors that are correlated with CHP use. The dataset of inpatient claims data contained information on 15,896 subjects who experienced ischemic stroke from 2000 to 2010. There was an average of 5.82 CHPs in a single prescription for subjects with ischemic stroke. Bu-yang-huan-wu-tang (BYHWT) (40.32%) was by far the most frequently prescribed formula CHP for ischemic stroke, and the most commonly used combination of two-formula-CHP was BYHWT with Shu-jin-huo-xue-tang (SJHXT) (4.40%). Dan Shen (16.50%) was the most commonly used single CHP for ischemic stroke, and the most commonly used combination of two single CHPs was Shi Chang Pua with Yuan Zhi (4.79%). We found that BYHWT and Dan Shen were the most frequently prescribed formula and single CHP for ischemic stroke, respectively. These results provide information about individualized therapy and may contribute to further pharmacologic experiments and clinical trials.

DL-3-n-butylphthalide (NBP) is widely used as a neuroprotective drug for ischemic stroke in China. There is, however, no established evidence on its efficacy and safety for patients with ischemic stroke. We, therefore, conducted a systematic review and meta-analysis. Major databases were searched to identify randomized controlled trials that assessed the efficacy and safety of NBP on ischemic stroke, reporting outcomes among patients treated with NBP alone or combined with standard anti-ischemic stroke drugs vs. standard anti-ischemic stroke drugs. Continuous data were validated, extracted and synthesized of standardized mean differences (SMDs) by random effects models, while dichotomous data were validated, extracted and synthesized of relative risk (RR) by random effects models. Twelve randomized controlled trials involving 1160 patients were identified. Results suggested that NBP monotherapy is not superior to standard anti-ischemic stroke drugs based on the Barthel Index (SMD, 0.25; 95% CI $-$0.14 to 0.63; $P=0.21$) and the National Institutes of Health Stroke Scale (SMD, 0.73; 95% CI $-$0.14 to 1.59; $P=0.10$). In contrast, the combination of NBP and standard anti-ischemic stroke drugs appears to be superior to standard drugs alone, again based on both the Barthel index (SMD, 1.65; 95% CI 1.25 to 2.04; $P<0.01$) and National Institutes of Health Stroke Scale (SMD, 1.40; 95% CI 0.72 to 2.09; $P<0.01$). However, the use of NBP may cause adverse event on the function of the liver (RR, 3.55; 95% CI 1.19 to 10.56; $P<0.05$). The combination use of NBP and standard anti-ischemic stroke drugs is more effective than standard drugs. However, more attention should be payed to the adverse effects on liver function. Our findings provided an established evidence of NBP as a neuroprotective drug, which may improve the current guideline for treatment of ischemic stroke.

Stroke is the leading fatal disease in China. This retrospective study aimed to explore the optimal acupuncture intervention time for long-term efficacy on motor dysfunction in patients suffering from acute ischemic stroke through 1-year of follow-up. Three hundred and nine patients collected at Longhua Hospital from January 2016 to December 2017 were classified into 3 groups based on the acupuncture intervention time, including groups A (within 2 days), B (within 3–7 days) and C (within 8–14 days). All patients had received standard treatment combined with acupuncture therapy. Specifically, acupuncture was performed at the acupoints including LI4 (Hegu), ST40 (Fenglong), DU20 (Baihui), and motor area of the scalp, followed by 2 electroacupuncture protocols based on different muscle tensions once a day for 5 days consecutively. The time-effect relationship was assessed using both the Fugl-Meyer Assessment (FMA) and the modified Barthel index (MBI) on the 90th day and 1st year, respectively. Meanwhile, the modified Rankin scale (mRS), high-sensitivity C-reactive protein (hs-CRP), and fibrinogen (FIB) were also measured during the 1-year follow-up. The favorable outcome rate was 74.4%. One-way univariate analysis of variance (ANOVA) revealed significant differences in FMA and MBI on the 90th day among the 3 groups ($p$ < 0.05), while no significant differences were observed in FMA, MBI or mRS at the 1st year between groups A and B. The levels of hs-CRP and FIB ($p$ < 0.05) were markedly reduced. Binary logistic regression analysis suggested that patients with atrial fibrillation (AF) (odds ratio (OR): 3.156), chronic kidney disease (CKD) (OR: 2.563), diabetes mellitus (DM) (OR: 2.174) or stroke history (OR: 1.883) were more inclined to recover poorly from nerve function deficit ($p$ < 0.05). Earlier acupuncture intervention may have a better long-term effect on motor dysfunction and inflammation during the 1-year follow-up. Moreover, acupuncture within 2 days is probably the optimal treatment time for early recovery on the 90th day.

Ischemic stroke is one of the major diseases with high morbidity, mortality, and disability rate all over the world. Chinese herb-derived active components would provide valuable candidate compounds for ischemic stroke therapy. Paeoniflorin (PF) is an active ingredient from Paeoniae Radix which possesses neurovascular effect after ischemia. However, so far, few studies are reported on the efficacy and mechanism of PF from angiogenesis aspects. Results from our in vitro studies showed that the ability for proliferation, migration, and tube formation in bone marrow-derived endothelial progenitor cells (BM-EPCs) was promoted by coculturing with PF (100 $\mu$M). Furthermore, to investigate the angiogenic effects of PF in vivo, we constructed an ischemic stroke model in rats and found that PF could reduce cerebral infarction, alleviate pathological injury, and increase the secretion of pro-angiogenic factors and cerebral vascular density after intraperitonially administration of 40 mg ⋅ kg${}^{-1}$ ⋅ day${}^{-1}$ for 14 days. Up-regulating the expression of VEGF/VEGF-R₂ might be the mechanism of PF’s angiogenic action. In conclusion, the present study provides evidence that PF is an active monomer of Traditional Chinese Medicine which shows angiogenic actions on endothelial progenitor cells and in ischemic stroke rat model.

Currently, therapies for ischemic stroke are limited. Ginkgolides, unique Folium Ginkgo components, have potential benefits for ischemic stroke patients, but there is little evidence that ginkgolides improve neurological function in these patients. Clinical studies have confirmed the neurological improvement efficacy of diterpene ginkgolides meglumine injection (DGMI), an extract of Ginkgo biloba containing ginkgolides A (GA), B (GB), and K (GK), in ischemic stroke patients. In the present study, we performed transcriptome analyses using RNA-seq and explored the potential mechanism of ginkgolides in seven in vitro cell models that mimic pathological stroke processes. Transcriptome analyses revealed that the ginkgolides had potential antiplatelet properties and neuroprotective activities in the nervous system. Specifically, human umbilical vein endothelial cells (HUVEC-T1 cells) showed the strongest response to DGMI and U251 human glioma cells ranked next. The results of pathway enrichment analysis via gene set enrichment analysis (GSEA) showed that the neuroprotective activities of DGMI and its monomers in the U251 cell model were related to their regulation of the sphingolipid and neurotrophin signaling pathways. We next verified these in vitro findings in an in vivo cuprizone (CPZ, bis(cyclohexanone)oxaldihydrazone)-induced model. GB and GK protected against demyelination in the corpus callosum (CC) and promoted oligodendrocyte regeneration in CPZ-fed mice. Moreover, GB and GK antagonized platelet-activating factor (PAF) receptor (PAFR) expression in astrocytes, inhibited PAF-induced inflammatory responses, and promoted brain-derived neurotrophic factor (BDNF) and ciliary neurotrophic factor (CNTF) secretion, supporting remyelination. These findings are critical for developing therapies that promote remyelination and prevent stroke progression.

Ischemic stroke is a serious health hazard that lacks effective treatment strategies. This study aims to investigate baicalin’s effect on tight junctions and immune cell infiltration after ischemic stroke injury. Rat brain microvascular endothelial cells (BMECs) were treated with OGD/R to establish an in vitro model. Caspase-3, Bax, Bcl-2, zonula occludens-1 (ZO-1), occludin, claudin-5, tumor necrosis factor (TNF)-$\alpha$, interleukin (IL)-6, inducible nitric oxide synthase (iNOS), Toll-like receptor (TLR) 2, TLR4, and nuclear factor-kappa B (NF-$\kappa$B) expressions were detected using qRT-PCR and western blotting. ZO-1, TNF-$\alpha$, iNOS, IL6, CD31, and ZO-1 expressions were examined using immunofluorescence. A tube formation assay was performed to measure angiogenesis. An ischemia-reperfusion model in rats was established by middle cerebral artery occlusion. The infarct volume was observed using 2,3,5-triphenyltetrazolium chloride staining. TNF-$\alpha$, iNOS, and IL6 levels in the serum were tested using ELISA. Flow cytometry was performed to examine immune cell inflammatory infiltration. Baicalin had no significant effect on the proliferation of normal BMECs. Baicalin inhibited apoptosis, protected against tight junction injury, and alleviated the inflammatory response in OGD/R-induced BMECs and IR rats, with the highest dose (25$\mu$g/mL) exerting a superior effect. Baicalin decreased the neurological function score, infarct volume, and brain water content, relieved brain morphological changes, and inhibited immune cell infiltration in vivo. In conclusion, baicalin could reduce BMECs apoptosis, protect tight junctions, and resist immune cell infiltration, thereby alleviating ischemic stroke. Our findings potentially provide a novel treatment strategy for ischemic stroke.

The brain metabolic changes caused by the interruption of blood supply are the initial factors of brain injury in ischemic stroke. Electroacupuncture (EA) pretreatment has been shown to protect against ischemic stroke, but whether its neuroprotective mechanism involves metabolic regulation remains unclear. Based on our finding that EA pretreatment significantly alleviated ischemic brain injury in mice by reducing neuronal injury and death, we performed a gas chromatography-time of flight mass spectrometry (GC-TOF/MS) to investigate the metabolic changes in the ischemic brain and whether EA pretreatment influenced these changes. First, we found that some glycolytic metabolites in the normal brain tissues were reduced by EA pretreatment, which may lay the foundation of neuroprotection for EA pretreatment against ischemic stroke. Then, 6h of cerebral ischemia-induced brain metabolic changes, especially the enhanced glycolysis, were partially reversed by EA pretreatment, which was manifested by the brain levels of 11 of 35 up-regulated metabolites and 18 of 27 down-regulated metabolites caused by cerebral ischemia significantly decreasing and increasing, respectively, due to EA pretreatment. A further pathway analysis showed that these 11 and 18 markedly changed metabolites were mainly involved in starch and sucrose metabolism, purine metabolism, aspartate metabolism, and the citric acid cycle. Additionally, we found that EA pretreatment raised the levels of neuroprotective metabolites in both normal and ischemic brain tissues. In conclusion, our study revealed that EA pretreatment may attenuate the ischemic brain injury by inhibiting glycolysis and increasing the levels of some neuroprotective metabolites.

Berberine has been demonstrated to alleviate cerebral ischemia/reperfusion injury, but its neuroprotective mechanism has yet to be understood. Studies have indicated that ischemic neuronal damage was frequently driven by autophagic/lysosomal dysfunction, which could be restored by boosting transcription factor EB (TFEB) nuclear translocation. Therefore, this study investigated the pharmacological effects of berberine on TFEB-regulated autophagic/lysosomal signaling in neurons after cerebral stroke. A rat model of ischemic stroke and a neuronal ischemia model in HT22 cells were prepared using middle cerebral artery occlusion (MCAO) and oxygen-glucose deprivation (OGD), respectively. Berberine was pre-administered at a dose of 100mg/kg/d for three days in rats and 90$\mu$M in HT22 neurons for 12h. 24h after MCAO and 2h after OGD, the penumbral tissues and OGD neurons were obtained to detect nuclear and cytoplasmic TFEB, and the key proteins in the autophagic/lysosomal pathway were examined using western blot and immunofluorescence, respectively. Meanwhile, neuron survival, infarct volume, and neurological deficits were assessed to evaluate the therapeutic efficacy. The results showed that berberine prominently facilitated TFEB nuclear translocation, as indicated by increased nuclear expression in penumbral neurons as well as in OGD HT22 cells. Consequently, both autophagic activity and lysosomal capacity were simultaneously augmented to alleviate the ischemic injury. However, berberine-conferred neuroprotection could be greatly counteracted by lysosomal inhibitor Bafilomycin A1 (Baf-A1). Meanwhile, autophagy inhibitor 3-Methyladenine (3-MA) also slightly neutralized the pharmacological effect of berberine on ameliorating autophagic/lysosomal dysfunction. Our study suggests that berberine-induced neuroprotection against ischemic stroke is elicited by enhancing autophagic flux via facilitation of TFEB nuclear translocation in neurons.

Machine learning (ML) can be used for deep mining and analysis of multidimensional medical data. At present, it has been widely used in medical diagnosis and prognosis prediction. This paper aims to make the existing research no longer focus on identifying key risk factors of stroke, and predict stroke risk more accurately. We collected the data of 3,962 cerebral apoplexy patients from 2019 to 2020, according to gender (male: 2,613; female: 1,349) and age (16–40 years old; 41–54 years old; 55–69 years old; 70 years old and above) layered. After data preprocessing, a stroke risk prediction model was built using principal component analysis (PCA) and extreme learning institutions (ELM). The prediction accuracy of PCA-ELM was as high as 97%. In this model, total cholesterol and high density lipoprotein are taken as 10 important factors that affect the incidence of stroke. This method can timely and efficiently mine the factors influencing the incidence of cerebral apoplexy from the data, and can predict the incidence of cerebral apoplexy. It has high value in practical application. This paper has great reference value in the research of brain death.

This study proposes the inverse problem algorithm (IPA) with five risk factors applied to the semi-quantitative analysis of carotid stenosis 272 patients with suspected ischemic stroke. The IPA is known to provide a substantiated machine learning-based prediction of the expected outcomes by solving an inverse matrix of variable coefficients. In case of carotid stenosis prediction, such risk factors as patient’s age, mean arterial pressure (MAP), glucose AC, low-density lipoprotein-cholesterol (LDL-C), and C-Reactive protein (CRP) were assessed for the main group of 217 patients. Their results were processed by the STATISTICA program with a customized loss function ($\mathrm{\Phi }$), yielding the first-order nonlinear semi-empirical formula with 16 terms. The loss function was calculated via the total mismatch between the theoretical predictions and true carotid stenosis cases (%) for all 217 patients. Thus, the carotid stenosis (%) compromised solution array [$16\times 1=16$] was optimized using $217\times 16=3488$ individual data points via the proposed algorithm. The results showed a complete regression with loss function $\mathrm{\Phi }$=2.3543, variance $s^2$=87.46%, and correlation coefficient $r^2=0.9352$. The reference group of 55 more patients with the same preliminary diagnosis and symptoms was selected to validate the method predictive feasibility, which was found quite satisfactory. The decreasing order of three dominant risk factors was as follows: CRP, glucose AC, and MAP, whereas age and LDL-C weakly influenced the program computation results. The IPA showed a strong convergence by its default characteristic. The reduction of the number of variables in computation deteriorated the prediction accuracy, exhibiting the algorithm’s high sensitivity to the number of variables.

This study processed the recent in vivo survey results for over a thousand patients and optimized their neck and head CT angiography triggered timing (CTA-TT) via the inverse problem algorithm, which ensured the maximal ratio of both left and right arterial to upper sinuses (LRA/US). These results are instrumental in examining the ischemic stroke syndromes along the neck and head. These 1001 patients were randomly categorized into test surveyed (802 patients) and verification group (199 patients), then a six factors semi-empirical formula was constructed by the STATISTICA program. The six factors were assigned a patient’s biological data and preset of the CTA facility; namely Age, mean arterial pressure (MAP), heart rate (HR), contrast media dose (CMD), Pre (injected pressure of CMD), and body surface area (BSA). Each factor was normalized into dimensionless values and incorporated into the dataset matrix $V[802\times 22]$ to analyze the coefficient matrix $M[22\times 1]$. The derived semi-empirical formula closely correlated with experimental data, according to the loss function $\mathrm{\Phi }=4.4084$, correlation coefficient $r^2=0.9468$, and variance of 0.8965. The formula verification for 199 more patients (verification group) yielded a correlation coefficient $r^2=0.8965$. Thus, it can be used for the CTA-TT estimation of patients without their preliminary tests, avoiding unnecessary irradiation. The estimated LRA/US was $2.19\pm 0.30$ for the verification group in this study. A simplified three-factor formula, featuring only age, MAP, and BSA, was also proposed.

Stroke is a group of diseases that damage brain tissue caused by sudden local cerebral blood circulation disorder. If not diagnosed and treated in time, the patient will lose a large number of neurons and even die. Among the examination methods, using magnetic resonance scans is more accurate than CT images, but it also has other risk factors. In response to these existing problems, this paper attempts to use a stroke classification model based on pre-trained CNN networks, which can help doctors detect MRI images of ischemic stroke and reduce time delays. This paper uses two real datasets. Dataset 1 includes 1112 cases of ischemic stroke and 1202 normal MRI images, while dataset 2 includes 1008 cases of ischemic stroke and 1002 normal MRI images. After data processing and noise reduction, two processed datasets, which contain 4448 cases, 4808 cases and 4032 cases, 4008 cases of ischemic stroke and normal MRI images, respectively, were obtained. Features are obtained by extracting the last pooling layer and the last fully connected layer of the pre-trained CNN network ResNet50 and DenseNet201. After combining the features, the iterative mRMR feature selection method is used to select image features. A support vector machine classifier with 10-fold cross-validation is used to classify the data. Finally, IMV is applied to the prediction vectors to get the voting results, and the best results are selected from the results. The evaluation indicators of the final experimental results in dataset 1 yielded 94.74%, 93.56%, 96.22%, and 94.87% results for accuracy, recall, precision, and F1 score, respectively. The evaluation indicators in dataset 2 yielded 92.24%, 92.21%, 92.26%, and 92.23% results for accuracy, recall, precision, and F1 score, respectively. These results clearly demonstrate that ischemic stroke can be successfully classified based on MRI and confirm the success of the hybrid feature engineering approach.

Neuroimaging investigation is an essential parameter to detect infarct lesion in stroke patients. Precise detection of brain lesions is an important task related to impaired behavior. In this paper, we aimed to develop an automatic method to segment and classify infarct lesion in diffusion-weighted imaging (DWI) of brain MRI. The method includes hybrid fuzzy $c$-means (HFCM) clustering in which the structure of $c$-means clustering is modified with rough sets and fuzzy sets to improve the segmentation performance with self-adjusted intensity thresholds. Quantitative evaluation was carried out on 128 MRI slices of brain image collected from ischemic stroke patients at the Department of Radiology, IMS and SUM Hospital, Bhubaneswar. The informative statistical features have been extracted using gray-level co-occurrence matrix (GLCM) and used to classify the types of stroke infarct according to the Oxfordshire Community Stroke Project (OCSP) classification. The parameters such as accuracy, Dice similarity index (DSI) and Jaccard index (JI) were utilized to evaluate the effectiveness of the proposed method in detecting the stroke lesions. The segmentation method achieved the average accuracy, DSI and JI of 96.8%, 95.8% and 92.2%, respectively, in support vector machine (SVM) classifier. The obtained results are higher in terms of random forest (RF) classification. With a high Dice coefficient of 0.958 and other evaluated parameters, the proposed method outperforms earlier published results.

Cerebral edema is a severe complication of acute ischemic stroke with high mortality but limited treatment. Although parameters such as brain water content and intracranial pressure may represent the global assessment of edema, optical properties can appear heterogeneously throughout the cerebral tissue relative to the site of injury. In this study, we have monitored the edema formation and progression in both permanent and transient middle cerebral artery occlusion models in rats. Edema was reflected by the decrease of optical attenuation coefficient (OAC) value in OCT system. By utilizing swept-source optical coherence tomography (SS-OCT), we found that in photochemically induced permanent focal stroke model, both the edema size and edema index, steadily developed until the end of monitor (7h). Comparatively, when transient ischemia was introduced with endothelin-1 (ET-1), the edema was detected as early as 15min, and began to recover after 30min until monitor was finished (3h). Despite the majority of the edema being recovered to some extent, the condition of a small region within the edema kept deteriorating, presumably due to the reperfusion damage which might result in serious clinical outcomes. Our study has compared the edema characteristics from two different acute ischemic stroke situations. This work not only confirms the capability of OCT to temporal and spatial monitor of edema but is also able to locate focal conditions at some areas that might highly determine the prognosis and treatment decisions.