当前位置: X-MOL 学术Multimedia Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Identification of changes in grey matter volume using an evolutionary approach: an MRI study of schizophrenia
Multimedia Systems ( IF 3.5 ) Pub Date : 2020-02-13 , DOI: 10.1007/s00530-020-00649-6
Indranath Chatterjee , Virendra Kumar , Bharti Rana , Manoj Agarwal , Naveen Kumar

Schizophrenia, a serious psychological disorder, causes auditory and visual hallucinations, and delusions in a person. Several studies have shown that schizophrenia imposes structural changes in human brain. Relative changes in the grey matter volume of the schizophrenia patients in comparison to healthy controls have been well explored. However, identification of relevant brain regions that exhibit grey matter atrophy and also aid in the classification of schizophrenic patients and healthy controls has not been extensively investigated. In this study, a novel application of the non-dominated sorting genetic algorithm has been developed to select a set of relevant features (voxels) that show grey matter changes in the brain regions attributable to schizophrenia. This study uses MRI data of 32 healthy controls and 28 schizophrenia patients. The results show notable shrink in the gray matter volume in the brain of the schizophrenia patients, mostly in inferior frontal gyrus, superior temporal gyrus, middle occipital gyrus, and insula. The proposed approach yields a mean classification accuracy close to 90% with a feature set having around 70 voxels. This study may open a means of investigation of underlying neurobiology of schizophrenic brain for effective clinical intervention.

中文翻译:

使用进化方法识别灰质体积的变化:精神分裂症的 MRI 研究

精神分裂症是一种严重的心理障碍,会导致人出现幻听和幻视以及妄想。多项研究表明,精神分裂症会导致人脑结构发生变化。与健康对照相比,精神分裂症患者的灰质体积的相对变化已经得到很好的探索。然而,对表现出灰质萎缩并有助于对精神分裂症患者和健康对照进行分类的相关大脑区域的鉴定尚未得到广泛研究。在这项研究中,开发了一种非支配排序遗传算法的新应用,以选择一组相关特征(体素),这些特征显示出可归因于精神分裂症的大脑区域的灰质变化。本研究使用了 32 名健康对照者和 28 名精神分裂症患者的 MRI 数据。结果显示,精神分裂症患者大脑灰质体积明显缩小,主要集中在额下回、颞上回、枕中回和岛叶。所提出的方法产生接近 90% 的平均分类准确率,特征集具有大约 70 个体素。这项研究可能为研究精神分裂症大脑的潜在神经生物学提供一种有效的临床干预手段。
更新日期:2020-02-13
down
wechat
bug