Spontaneous brain activity in patients with central retinal artery occlusion: a resting-state functional MRI study using machine learning.

Abstract

Central retinal artery occlusion (CRAO) is a serious eye condition that poses a risk to vision, resulting from the blockage of the central retinal artery. Because of the anatomical connection between the ocular artery, which derives from the internal carotid artery, and the anterior middle cerebral artery, hemodynamic alterations and sudden vision loss associated with CRAO may impact brain functionality. This study aimed to examine alterations in spontaneous neural activity among patients with CRAO by resting-state functional MRI. In addition, we selected the amplitude of low-frequency fluctuation (ALFF) and fractional amplitude of low-frequency fluctuation (fALFF) values as classification features for distinguishing CRAO from healthy controls (HCs) using a support vector machine classifier. A total of 18 patients diagnosed with CRAO and 18 HCs participated in the study. Resting-state brain function images and structural images were acquired from both groups. Aberrant changes in spontaneous brain functional activity among CRAO patients were investigated utilizing ALFF and fALFF analysis methods. Group differences in ALFF/fALFF values were assessed through a two-sample t -test. Subsequently, a machine learning classifier was developed to evaluate the clinical diagnostic potential of ALFF and fALFF values. In comparison to HCs, individuals with CRAO exhibited significantly higher ALFF values in the left cerebellum_6, vermis_7, left superior frontal gyrus, and left inferior frontal gyrus, triangular part. Conversely, the CRAO group displayed notably lower ALFF values in the left precuneus and left median cingulum gyri. Furthermore, higher fALFF values were observed in the left inferior frontal gyrus, triangular part, whereas lower fALFF values were noted in the right cerebellum_Crus2, left precuneus, right angular gyrus, left angular gyrus, right supramarginal gyrus, right superior parietal gyrus, and left precuneus. Utilizing the ALFF/fALFF values, the receiver operating characteristic curves (area under the curve) yielded 0.99 and 0.94 through machine learning analysis techniques. CRAO patients exhibit atypical neural activity in the brain, characterized by ALFF and fALFF values predominantly localized in the frontal, parietal, and cerebellar regions, which are closely linked to visual cognition and motor control impairments. Furthermore, ALFF and fALFF could serve as potential neuroimaging markers beyond the orbit among CRAO.