Artificial intelligence software for assessing brain ischemic penumbra/core infarction on computed tomography perfusion:A real-world accuracy study

BACKGROUND With the increasingly extensive application of artificial intelligence(AI)in medical systems,the accuracy of AI in medical diagnosis in the real world deserves attention and objective evaluation.AIM To investigate the accuracy of AI diagnostic software(Shukun)in assessing ischemic penumbra/core infarction in acute ischemic stroke patients due to large vessel occlusion.METHODS From November 2021 to March 2022,consecutive acute stroke patients with large vessel occlusion who underwent mechanical thrombectomy(MT)post-Shukun AI penumbra assessment were included.Computed tomography angiography(CTA)and perfusion exams were analyzed by AI,reviewed by senior neurointerventional experts.In the case of divergences among the three experts,discussions were held to reach a final conclusion.When the results of AI were inconsistent with the neurointerventional experts’diagnosis,the diagnosis by AI was considered inaccurate.RESULTS A total of 22 patients were included in the study.The vascular recanalization rate was 90.9%,and 63.6%of patients had modified Rankin scale scores of 0-2 at the 3-month follow-up.The computed tomography(CT)perfusion diagnosis by Shukun(AI)was confirmed to be invalid in 3 patients(inaccuracy rate:13.6%).CONCLUSION AI(Shukun)has limits in assessing ischemic penumbra.Integrating clinical and imaging data(CT,CTA,and even magnetic resonance imaging)is crucial for MT decision-making.

Endovascular treatment vs drug therapy alone in patients with mild ischemic stroke and large infarct cores

BACKGROUND Treatment decision making is strictly associated with the outcomes in patients with ischemic stroke who show a large core infarct.Medical care alone may result in suboptimal treatment efficacy,and endovascular treatment may be accompanied by safety issues.Whether endovascular treatment is superior to medical care is not well investigated in the clinical studies.AIM To investigate the efficacy of endovascular treatment and drug therapy alone in mild ischemic stroke patients with large infarct cores.METHODS Fifty patients with mild ischemic stroke and 50 patients with acute ischemic stroke caused by anterior large vessel occlusion were selected at the First Affiliated Hospital of Hebei North University between January 2021 and December 2021.Patients were divided into an endovascular therapy group and a drug therapy group according to different treatment methods.In the endovascular therapy group,there were 28 patients with minor stroke and 22 patients with large infarct cores.The drug therapy group had 22 patients with minor stroke and 28 patients with large infarct cores.The National Institutes of Health Stroke Scale(NIHSS) scores were collected and compared between the two groups immediately after the operation and 24 h and 7 d after the operation.The modified Rankin scale(m RS) and/or activity of daily living were assessed at hospital discharge.RESULTS There was no significant difference in NIHSS scores between the two groups before the operation(P > 0.05).NIHSS scores were lower in the endovascular therapy group than in the drug therapy group at 24 h and 7 d after the operation and at hospital discharge(all P < 0.05).The incidence of early neurologic deterioration was significantly lower in the endovascular therapy group than in the drug therapy group(P < 0.05).At hospital discharge,the m RS score was lower in the endovascular treatment group than in the drug therapy group,and the activity of daily living score was better in the endovascular treatment group than in the drug therapy group(all P < 0.05).During a follow-up of 3 mo,17 patients(34.0%) had good prognosis(m RS ≤ 2),33 patients(66.0%) had poor prognosis(m RS > 2),and 11 patients(22.0%) died.In the medical treatment group,16 patients(m RS ≤ 2) had good prognosis(32.0%),34 patients(m RS > 2) had poor prognosis(68.0%),and 14 patients(28.0%) died.There was no significant difference in prognosis and mortality between the two groups(P > 0.05).CONCLUSION Endovascular therapy can improve NIHSS score and m RS score in patients with mild ischemic stroke and large infarct cores.It is suitable for clinical application.

Apparent diffusion coefficient evaluation for secondary changes in the cerebellum of rats after middle cerebral artery occlusion

Supratentorial cerebral infarction can cause functional inhibition of remote regions such as the cerebellum, which may be relevant to diaschisis. This phenomenon is often analyzed using positron emission tomography and single photon emission CT. However, these methods are expensive and radioactive. Thus, the present study quantified the changes of infarction core and remote regions after unilateral middle cerebral artery occlusion using apparent diffusion coefficient values. Diffu- sion-weighted imaging showed that the area of infarction core gradually increased to involve the cerebral cortex with increasing infarction time. Diffusion weighted imaging signals were initially in- creased and then stabilized by 24 hours. With increasing infarction time, the apparent diffusion co- efficient value in the infarction core and remote bilateral cerebellum both gradually decreased, and then slightly increased 3-24 hours after infarction. Apparent diffusion coefficient values at remote regions （cerebellum） varied along with the change of supratentorial infarction core, suggesting that the phenomenon of diaschisis existed at the remote regions. Thus, apparent diffusion coefficient values and diffusion weighted imaging can be used to detect early diaschisis.

Computed tomography perfusion and computed tomography angiography for prediction of clinical outcomes in ischemic stroke patients after thrombolysis

Cerebral blood perfusion and cerebrovascular lesions are important factors that can affect the therapeutic efficacy of thrombolysis.At present,the majority of studies focus on assessing the accuracy of lesion location using imaging methods before treatment,with less attention to predictions of outcomes after thrombolysis.Thus,in the present study,we assessed the efficacy of combined computed tomography（CT） perfusion and CT angiography in predicting clinical outcomes after thrombolysis in ischemic stroke patients.The study included 52 patients who received both CT perfusion and CT angiography.Patients were grouped based on the following criteria to compare clinical outcomes：（1） thrombolytic and non-thrombolytic patients,（2） thrombolytic patients with CT angiography showing the presence or absence of a vascular stenosis,（3） thrombolytic patients with CT perfusion showing the presence or absence of hemodynamic mismatch,and（4） different CT angiography and CT perfusion results.Short-term outcome was assessed by the 24-hour National Institution of Health Stroke Scale score change.Long-term outcome was assessed by the 3-month modified Rankin Scale score.Of 52 ischemic stroke patients,29 were treated with thrombolysis and exhibited improved short-term outcomes compared with those without thrombolysis treatment（23 patients）.Patients with both vascular stenosis and blood flow mismatch（13 patients） exhibited the best short-term outcome,while there was no correlation of long-term outcome with CT angiography or CT perfusion findings.These data suggest that combined CT perfusion and CT angiography are useful for predicting short-term outcome,but not long-term outcome,after thrombolysis.