Classification of Myelin Oligodendrocyte Glycoprotein Antibody-Related Disease and Its Mimicking Acute Demyelinating Syndromes in Children Using MRI-Based Radiomics: From Lesion to Subject

作者全名：Ding, Shuang; Zheng, Helin; Wang, Longlun; Fan, Xiao; Yang, Xinyi; Huang, Zhongxin; Zhang, Xiangmin; Yan, Zichun; Li, Xiujuan; Cai, Jinhua

作者地址：[Ding, Shuang; Zheng, Helin; Wang, Longlun; Fan, Xiao; Yang, Xinyi; Huang, Zhongxin; Zhang, Xiangmin; Cai, Jinhua] Chongqing Med Univ, Chongqing Key Lab Pediat, Key Lab Child Dev & Disorders, Minist Educ,Dept Radiol,Childrens Hosp,Natl Clin R, Chongqing 400014, Peoples R China; [Li, Xiujuan] Chongqing Med Univ, Chongqing Key Lab Pediat, Key Lab Child Dev & Disorders, Minist Educ,Dept Neurol,Childrens Hosp,Natl Clin R, Chongqing 400014, Peoples R China; [Yan, Zichun] Chongqing Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing, Peoples R China

通信作者：Cai, JH (通讯作者)，Chongqing Med Univ, Chongqing Key Lab Pediat, Key Lab Child Dev & Disorders, Minist Educ,Dept Radiol,Childrens Hosp,Natl Clin R, Chongqing 400014, Peoples R China.

来源：ACADEMIC RADIOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001239890000001

JCR分区：Q1

影响因子：3.8

年份：2024

卷号：31

期号：5

开始页：2085

结束页：2096

文献类型：Article

关键词：Myelin Oligodendrocyte Glycoprotein Antibody-related Disease; Radiomics; Machine Learning; Multi-Sequence MRI; Pediatric

摘要：Rationale and Objectives: To develop MRI-based radiomics models from the lesion level to the subject level and assess their value for differentiating myelin oligodendrocyte glycoprotein antibody-related disease (MOGAD) from non-MOGAD acute demyelinating syndromes in pediatrics. Materials and Methods: 66 MOGAD and 66 non-MOGAD children were assigned to the training set (36/35), internal test set (14/16), and external test set (16/15), respectively. At the lesion level, five single-sequence models were developed alongside a fusion model (combining these five sequences). The radiomics features of each lesion were quantified as the lesion-level radscore (LRS) using the best-performing model. Subsequently, a lesion-typing function was employed to classify lesions into two types (MOGAD-like or nonMOGAD-like), and the average LRS of the predominant type lesions in each subject was considered as the subject-level radscore (SRS). Based on SRS, a subject-level model was established and compared to both clinical models and radiologists' assessments. Results: At the lesion level, the fusion model outperformed the five single-sequence models in distinguishing MOGAD and non-MOGAD lesions (0.867 and 0.810 of area under the curve [AUC] in internal and external testing, respectively). At the subject level, the SRS model showed superior performance (0.844 and 0.846 of AUC in internal and external testing, respectively) compared to clinical models and radiologists' assessments for distinguishing MOGAD and non-MOGAD. Conclusion: MRI-based radiomics models have potential clinical value for identifying MOGAD from non-MOGAD. The fusion model and SRS model can distinguish between MOGAD and non-MOGAD at the lesion level and subject level, respectively, providing a differential diagnosis method for these two diseases.

基金机构：Postgraduate Innovation Research Project of Chongqing [CYB22212]; Chongqing Medical University Program for Youth Innovation in Future Medicine [W0116]

基金资助正文：<BOLD>Funding</BOLD> This work was supported by the Postgraduate Innovation Research Project of Chongqing (No. CYB22212) and Chongqing Medical University Program for Youth Innovation in Future Medicine (No. W0116) .