Quantitative analysis of brain volume in children with autism spectrum disorder based on artificial intelligence automatic brain segmentation technology
10.3760/cma.j.cn101070-20240515-00297
- VernacularTitle:基于人工智能自动脑分割技术定量分析孤独症谱系障碍患儿脑体积
- Author:
Xiaowen XU
1
;
Yang LI
;
Ning DING
;
Guifen ZHENG
;
Tongtong WU
;
Yang LI
;
Shanshan SUN
;
Xiufeng SONG
Author Information
1. 青岛大学附属妇女儿童医院医学影像科，青岛 266000
- Publication Type:Journal Article
- Keywords:
Brain structure volume;
Automatic brain segmentation technique;
Magnetic resonance imaging;
Autism spectrum disorder
- From:
Chinese Journal of Applied Clinical Pediatrics
2025;40(1):50-55
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To characterize the brain structure of Chinese children with autism spectrum disorder (ASD) using artificial intelligence automatic brain segmentation technique, and to analyze the correlation between the characteristics of the brain structure and the degree of brain development.Methods:A case-control study.The data of 52 children who were diagnosed with ASD according to the diagnostic criteria for ASD in the Diagnostic and Statistical Manual of Mental Disorders-Fifth Edition of the United States at the Department of Psychology of Qingdao University Affiliated Women and Children′s Hospital from January 2023 to April 2024 were prospectively analyzed.Meanwhile, 48 gender- and age-matched typically developing (TD) children in Qingdao were also included.The three-dimensional T1 weighted imaging sequences of all patients were obtained using a GE 3.0T magnetic resonance imaging scanner.Automated brain segmentation techniques were used to obtain the standardized volumes of each brain structure (the ratio of the absolute volume of the brain structure to the whole brain volume).Two-independent-samples t and Mann-Whitney U tests were used to compare the standardized volumes of different brain regions between the 2 groups.Pearson and Spearman correlation analyses were used to depict the correlations between volume data of brain areas with significant differences and Gesell Developmental Scale scores. Results:Compared with those in the TD group, the volumes of the left grey matter[25.45%(0.70%) vs.25.16%(1.05%)], the right grey matter [(25.89±0.71)% vs.(25.51±0.73)%], the right lateral orbitofrontal cortex [(0.62±0.03)% vs.(0.59±0.05)%], the right medial orbitofrontal cortex[(0.48±0.04)% vs.(0.46±0.04)%], the right pars triangularis [(0.38±0.07)% vs.(0.35±0.05)%], the left hippocampus [0.22%(0.04%) vs.0.20%(0.02%)], the right hippocampus [0.23%(0.04%) vs.0.22%(0.02%)], the left parahippocampal gyrus [0.15%(0.03%) vs.0.14%(0.02%)], the right parahippocampal gyrus [(0.15±0.02)% vs.(0.14±0.02)%], the left fusiform gyrus [(0.82±0.08)% vs.(0.78±0.08)%], the right superior temporal gyrus [(0.96±0.10)% vs.(0.90±0.09)%], the left insular lobe [(0.54±0.03)% vs.(0.53±0.04)%], the right insular lobe [(0.55±0.03)% vs.(0.53±0.04)%], the right inferior parietal cortex [(1.40±0.16)% vs.(1.33±0.12)%], the right precuneus cortex [(0.99±0.09)% vs.(0.94±0.09)%], the right putamen [(0.37±0.04)% vs.(0.35±0.03)%], the left pallidum [(0.14±0.01)% vs.(0.13±0.01)%], the right pallidum [0.14%(0.02%) vs.0.13%(0.01%)], and the right thalamus [(0.51±0.04)% vs.(0.49±0.03)%] were significantly increased in the ASD group (all P<0.05).Nonetheless, the volumes of the left pericalcarine cortex [(0.19±0.04)% vs.(0.20±0.04)%] and the corpus callosum posterior region [0.05%(0.01%) vs.0.06%(0.01%)] in the ASD group were considerably smaller than those in the TD group (all P<0.05).Correlation analysis showed that the right thalamus volume was negatively correlated with the Gesell-adaptation development quotient in children with ASD ( r=-0.276, P=0.048).The volumes of the left fusiform gyrus and left pericalcarine cortex were negatively correlated with the Gesell-fine motor development quotient in children with ASD ( r=-0.290, P=0.037; r=-0.368, P=0.007). The right precuneus cortex volume was negatively correlated with the Gesell-personal and social competence development quotient in children with ASD ( r=-0.396, P=0.007). Conclusions:Children with ASD show abnormalities in the volumes of multiple brain regions, and some brain regions are related to the degree of brain development.Automatic brain segmentation technology based on artificial intelligence can rapidly and directly measure and display the volume of brain structures in both ASD and TD children.
