期刊文献+

MRI人工智能脑分割软件测量脑梗死患者脑区体积与NIHSS评分的相关分析

Correlation between brain area volume measured by magnetic resonance artificial intelligence brain segmentation software and NIHSS score in patients with cerebral infarction
下载PDF
导出
摘要 目的探讨MRI人工智能脑分割软件测量脑梗死患者脑区体积与美国国立卫生研究院卒中量表(NIHSS)评分的相关性。方法选取我院诊断为脑梗死患者83例,根据入院NIHSS评分分为轻度组18例(0~4分)、中度组45例(5~15分)和重度组20例(6~42分)。入院行MRI扫描头颅和人工智能脑分割软件测量各脑区体积,包括全脑、颞叶、枕叶、额叶、顶叶、小脑以及脑室。根据T2WI序列计算梗死总体积。结果三组患者性别、年龄、体质指数、收缩压和舒张压、空腹血糖和总胆固醇水平比较,差异无统计学意义(P>0.05)。三组全脑、枕叶、顶叶、小脑以及脑室体积比较,差异无统计学意义(P>0.05)。但是中、重度组颞叶和额叶体积显著小于轻度组,梗死总体积显著大于轻度组,差异有统计学意义(P<0.05),中度与重度组比较差异无统计学意义(P>0.05)。Spearman检验显示,颞叶和额叶体积与NIHSS评分和梗死总体积呈负相关(P<0.05),而梗死总体积与NIHSS评分无明显相关性(P>0.05)。结论MRI人工智能脑分割软件能够精准定位并测量各脑区体积,颞叶和额叶体积缩小可能与脑梗死患者入院NIHSS评分增加有关,有助于病情严重程度评估。 Objective To explore the correlation between the measurement of brain area volume in patients with cerebral infarction using magnetic resonance artificial intelligence brain segmentation software and the National Institutes of Health Stroke Scale(NIHSS)score.Methods 83 patients with cerebral infarction diagnosed in our hospital from August 2022 to August 2023 were randomly selected as the study subjects.According to the admission NIHSS score,they were divided into mild group of 18 cases(0~4 points),moderate group of 45 cases(5~15 points),and severe group of 20 cases(6~42 points).After admission,1.43T MRI scanning of the head and artificial intelligence brain segmentation software were used to measure the volume of various brain regions,including the whole brain,temporal lobe,occipital lobe,frontal lobe,parietal lobe,cerebellum,and ventricles.The total infarct volume was calculated based on T2WI sequence.Results There were no differences of gender,age,body mass index,systolic and diastolic blood pressure,fasting blood glucose,and total cholesterol levels among the three groups of patients(P>0.05).There were no differences in the volume of the whole brain,occipital lobe,parietal lobe,cerebellum,and ventricles among the three groups(P>0.05).However,the volume of the temporal and frontal lobes in the moderate to severe group was significantly smaller than that in the mild group,and the total volume of infarction was significantly larger than that in the mild group(P<0.05).There was no significant difference between the moderate and severe groups(P>0.05).Spearman test showed negative correlation between temporal,frontal lobe volume and NIHSS score,total infarct volume(P<0.05),while there was no correlation between total infarct volume and NIHSS score(P>0.05).Conclusion Magnetic resonance artificial intelligence brain segmentation software can accurately locate and measure the volume of each brain area.The reduction of temporal and frontal lobe volume may be related to increase of NIHSS scores for admitted cerebral infarction patients,which is Med Imaging Vol.34 No.62024 helpful for assessing the severity of the condition.
作者 罗长国 周扬 于足 LUO Changguo;ZHOU Yang;YU Zu(Department of Radiology,Second Hospital of Jinhua City,Jinhua 321000,China;Seven Wards of Geriatric Department,Second Hospital of Jinhua City,Jinhua 321000,China;The Fourth Ward of Geriatric Department,Second Hospital of Jinhua City,Jinhua 321000,China)
出处 《医学影像学杂志》 2024年第6期5-8,共4页 Journal of Medical Imaging
基金 浙江省金华市公益性技术应用研究项目(编号:2023-4-152)。
关键词 脑梗死 磁共振成像 人工智能脑分割 脑区 体积 Cerebral infarction Magnetic resonance imaging Artificial intelligence brain segmentation Brain area Volume
  • 相关文献

参考文献12

二级参考文献79

共引文献24

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部