Multiple sclerosis and related disorders · 2025
Radiomics-based analysis of choroid plexus abnormalities in neuromyelitis optica spectrum disorders and multiple sclerosis and their clinical implications.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Xiaohua, Wang Xiaolong, Xu Yuhui, Yan Zichun, Shi Zhuowei, Liu Yanbing, Liu Xiaojuan, Li Yongmei
Аннотация
BACKGROUND: The choroid plexus (CP) is closely linked to inflammation in multiple sclerosis (MS). While the CP volume is enlarged in MS compared with healthy controls (HC), no such changes are observed in neuromyelitis optica spectrum disorder (NMOSD), a disease with similar clinical and imaging features to MS. It remains unclear whether the CP plays a similar role in NMOSD as in MS.
PURPOSE: To investigate the abnormal CP radiomics in NMOSD and MS and explore their clinical implications.
METHODS: This retrospective study included 111 MS, 69 Aquaporin-4 (AQP4)-IgG positive NMOSD, and 82 HC, with age and sex matching. Radiomics features of the CP were extracted from T1-weighted images after automated segmentation, including shape, first order statistics (intensity), and texture features (N=1051). Analysis of covariance was used to assess group differences in these features, and 11 classic machine learning algorithms were employed to construct disease classification models. Moreover, partial correlation analysis was performed to further explore the relationships between differential radiomics features and clinical measures, such as Expanded Disability Status Scale (EDSS) and Symbol Digit Modalities Test (SDMT).
RESULTS: Compared with HC, MS exhibited significant differences in 453 features, including shape, intensity, and texture, while NMOSD displayed differences in 102 intensity and texture features, with no differences in shape. NMOSD and MS differed in 178 features, primarily texture (P < 0.05, Bonferroni correction). In the classification models based on CP radiomics features, the best AUC for MS vs HC was 0.935 (95% CI: 0.830 - 0.997) with the Partial Least Squares Regression Generalized Linear Model (plsRglm), while for NMOSD vs HC, it was 0.822 (95% CI: 0.629 - 0.962) with the Light Gradient Boosting Machine (LightGBM). Meanwhile, the best AUC for NMOSD vs MS was 0.832 (95% CI: 0.667 - 0.960) with the Quadratic Discriminant Analysis (QDA). Furthermore, of the 453 abnormal radiomics features of MS patients, 120 were significantly correlated with EDSS and 234 with SDMT scores (P < 0.05, FDR correction), while no radiomics features in NMOSD were significantly correlated with clinical scores (P > 0.05, FDR correction).
CONCLUSION: Radiomics can detect varying degrees of CP abnormalities in NMOSD and MS, suggesting CP involvement in the pathophysiology of NMOSD, albeit to a lesser extent than in MS. It may help understand the potential pathophysiological differences between the two diseases and their impact on clinical monitoring.
PURPOSE: To investigate the abnormal CP radiomics in NMOSD and MS and explore their clinical implications.
METHODS: This retrospective study included 111 MS, 69 Aquaporin-4 (AQP4)-IgG positive NMOSD, and 82 HC, with age and sex matching. Radiomics features of the CP were extracted from T1-weighted images after automated segmentation, including shape, first order statistics (intensity), and texture features (N=1051). Analysis of covariance was used to assess group differences in these features, and 11 classic machine learning algorithms were employed to construct disease classification models. Moreover, partial correlation analysis was performed to further explore the relationships between differential radiomics features and clinical measures, such as Expanded Disability Status Scale (EDSS) and Symbol Digit Modalities Test (SDMT).
RESULTS: Compared with HC, MS exhibited significant differences in 453 features, including shape, intensity, and texture, while NMOSD displayed differences in 102 intensity and texture features, with no differences in shape. NMOSD and MS differed in 178 features, primarily texture (P < 0.05, Bonferroni correction). In the classification models based on CP radiomics features, the best AUC for MS vs HC was 0.935 (95% CI: 0.830 - 0.997) with the Partial Least Squares Regression Generalized Linear Model (plsRglm), while for NMOSD vs HC, it was 0.822 (95% CI: 0.629 - 0.962) with the Light Gradient Boosting Machine (LightGBM). Meanwhile, the best AUC for NMOSD vs MS was 0.832 (95% CI: 0.667 - 0.960) with the Quadratic Discriminant Analysis (QDA). Furthermore, of the 453 abnormal radiomics features of MS patients, 120 were significantly correlated with EDSS and 234 with SDMT scores (P < 0.05, FDR correction), while no radiomics features in NMOSD were significantly correlated with clinical scores (P > 0.05, FDR correction).
CONCLUSION: Radiomics can detect varying degrees of CP abnormalities in NMOSD and MS, suggesting CP involvement in the pathophysiology of NMOSD, albeit to a lesser extent than in MS. It may help understand the potential pathophysiological differences between the two diseases and their impact on clinical monitoring.