Objective To evaluate the degree of brain atrophy in spinocerebellar ataxia type 3(SCA3)patients based on artificial intelligence(AI)technology,and to explore the correlation between the degree of brain atrophy and the severity of the disease.Methods The clinical and imaging data of 23 SCA3 patients(SCA3 group)and 24 healthy controls(HC)(HC group)were collected.The International Cooperative Ataxia Rating Scale(ICARS)was used to evaluate the severity of ataxia in patients with SCA3.AI technology was used to process the 3D-T1 WI MR image data of the SCA3 and HC groups to segment and measure the volume and volume percentage of brain,followed by correlation analyses between brain structural alterations and the severity of ataxia in SCA3 patients.Results There were no significant differences in gender and age between the two groups(P＞0.05).The SCA3 group had a significant reduction in the volume and volume percentage of various brain regions,such as the frontal,temporal,parietal,occipital,limbic,right cerebral white mat-ter,subcortical gray matter,cerebellum and brainstem,compared to the HC group(multiple hypothesis testing adjusted P＜0.01).In the SCA3 group,the ICARS showed positive correlation with patient age(r=0.571,P=0.004)and negative correlation with the vol-ume of the left cerebellar white matter,vermis,medulla oblongata,and the volume percentages of bilateral cerebellar white matter,vermis,pons,medulla oblongata(P＜0.05).Conclusion The significant atrophy of the supratentorial and subtentorial regions of the brain in SCA3 patients.The globus pallidus exhibits the most substantial atrophy,suggesting its potential as an imaging diagnostic marker of SC A3.