Cortical functional and structural alterations in rhegmatogenous retinal detachment: a multimodal analysis using surface-based independent component analysis, morphometry, and machine learning

裂孔性视网膜脱离的皮质功能和结构改变:基于表面独立成分分析、形态测量和机器学习的多模态分析

阅读:2

Abstract

BACKGROUND: Although previous research has identified functional abnormalities in visual pathways and gray matter areas linked to visual processing in patients with rhegmatogenous retinal detachment (RRD), the precise nature and extent of cortical functional and structural disruptions in these individuals remain insufficiently explored. This study aimed to characterize cortical changes in RRD and investigate their utility as neuroimaging markers. METHODS: This study used surface-based independent component analysis (ICA) and morphological measurement techniques to investigate cortical functional and structural changes in RRD patients. Subsequently, it applied support vector machine (SVM) and SHapley Additive exPlanations (SHAP) methods to classify RRD patients and healthy controls (HCs), identifying key brain regions that contribute most to the prediction model. RESULTS: In terms of cortical function, the RRD patients showed significant increases in functional connectivity (FC) in the visual, cognitive, auditory, and motor networks (voxel P<0.001, cluster P<0.05), as well as a significant enhancement in functional network connectivity (FNC) between the visual network (VN) and sensorimotor network (SMN) (P<0.01) compared to the HCs. The RRD patients exhibited significant cortical thinning in the left hemisphere lateral occipital cortex (lh_lateraloccipital), right hemisphere pericalcarine cortex (rh_pericalcarine), and right hemisphere lateral orbitofrontal cortex (rh_lateralorbitofrontal) regions (voxel P<0.01, cluster P<0.05) in the cortical structure. Notably, the FC value in the VN1 region showed the best classification performance in both the SVM and SHAP analyses. CONCLUSIONS: This study found pronounced functional and structural abnormalities in the cortex of RRD patients, potentially linked to cognitive and visual dysfunction. Notably, FC alterations in the VN1 region may act as a robust neuroimaging indicator capable of distinguishing individuals with RRD from HCs. Our results offer novel insights into the underlying neuropathological processes of RRD, and underscore the value of early neuroimaging markers for timely diagnosis and clinical intervention.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。