Veiga-Canuto Diana, Fernández-Patón Matías, Cerdà Alberich Leonor, Jiménez Pastor Ana, Gomis Maya Armando, Carot Sierra Jose Miguel, Sangüesa Nebot Cinta, Martínez de Las Heras Blanca, Pötschger Ulrike, Taschner-Mandl Sabine, Neri Emanuele, Cañete Adela, Ladenstein Ruth, Hero Barbara, Alberich-Bayarri Ángel, Martí-Bonmatí Luis
From the Grupo de Investigación Biomédica en Imagen, Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106 Torre A planta 7, 46026 Valencia, Spain (D.V.C., M.F.P., L.C.A., A.G.M., L.M.B.); Área Clínica de Imagen Médica (D.V.C., C.S.N., L.M.B.) and Department of Pediatric Oncology (B.M.d.l.H., A.C.), Hospital Universitari i Politècnic La Fe, Valencia, Spain; Quantitative Imaging Biomarkers in Medicine, QUIBIM SL, Valencia, Spain (A.J.P., A.A.B.); Departamento de Estadística e Investigación Operativa Aplicadas y Calidad, Universitat Politècnica de València, Valencia, Spain (J.M.C.S.); St. Anna Children's Cancer Research Institute, Vienna, Austria (U.P., S.T.M., R.L.); Division of Academic Radiology, Department of Translational Research, University of Pisa, Pisa, Italy (E.N.); and Department of Pediatric Oncology and Hematology, University Children's Hospital of Cologne, Medical 18 Faculty, University of Cologne, Cologne, Germany (B.H.).
Radiol Artif Intell. 2024 Jul;6(4):e230208. doi: 10.1148/ryai.230208.
Purpose To evaluate the reproducibility of radiomics features extracted from T2-weighted MR images in patients with neuroblastoma. Materials and Methods A retrospective study included 419 patients (mean age, 29 months ± 34 [SD]; 220 male, 199 female) with neuroblastic tumors diagnosed between 2002 and 2023, within the scope of the PRedictive In-silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis, Empowered by imaging biomarkers (ie, PRIMAGE) project, involving 746 T2/T2*-weighted MRI sequences at diagnosis and/or after initial chemotherapy. Images underwent processing steps (denoising, inhomogeneity bias field correction, normalization, and resampling). Tumors were automatically segmented, and 107 shape, first-order, and second-order radiomics features were extracted, considered as the reference standard. Subsequently, the previous image processing settings were modified, and volumetric masks were applied. New radiomics features were extracted and compared with the reference standard. Reproducibility was assessed using the concordance correlation coefficient (CCC); intrasubject repeatability was measured using the coefficient of variation (CoV). Results When normalization was omitted, only 5% of the radiomics features demonstrated high reproducibility. Statistical analysis revealed significant changes in the normalization and resampling processes ( < .001). Inhomogeneities removal had the least impact on radiomics (83% of parameters remained stable). Shape features remained stable after mask modifications, with a CCC greater than 0.90. Mask modifications were the most favorable changes for achieving high CCC values, with a radiomics features stability of 70%. Only 7% of second-order radiomics features showed an excellent CoV of less than 0.10. Conclusion Modifications in the T2-weighted MRI preparation process in patients with neuroblastoma resulted in changes in radiomics features, with normalization identified as the most influential factor for reproducibility. Inhomogeneities removal had the least impact on radiomics features. Pediatrics, MR Imaging, Oncology, Radiomics, Reproducibility, Repeatability, Neuroblastic Tumors © RSNA, 2024 See also the commentary by Safdar and Galaria in this issue.
目的 评估从神经母细胞瘤患者的T2加权磁共振成像（MRI）中提取的影像组学特征的可重复性。材料与方法 一项回顾性研究纳入了2002年至2023年间诊断为神经母细胞瘤的419例患者（平均年龄29个月±34[标准差]；男性220例，女性199例），该研究属于支持癌症个性化诊断和预后的预测性计算机多尺度分析项目（PRedictive In-silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis，由影像生物标志物赋能，即PRIMAGE项目），涉及诊断时和/或初始化疗后的746个T2/T2*加权MRI序列。图像经过了处理步骤（去噪、不均匀性偏差场校正、归一化和重采样）。肿瘤被自动分割，并提取了107个形状、一阶和二阶影像组学特征，将其视为参考标准。随后，修改了之前的图像处理设置，并应用了体积掩码。提取新的影像组学特征并与参考标准进行比较。使用一致性相关系数（CCC）评估可重复性；使用变异系数（CoV）测量受试者内重复性。结果 当省略归一化时，只有5%的影像组学特征显示出高可重复性。统计分析显示归一化和重采样过程有显著变化（P<0.001）。不均匀性去除对影像组学的影响最小（83%的参数保持稳定）。掩码修改后形状特征保持稳定，CCC大于0.90。掩码修改是实现高CCC值最有利的变化，影像组学特征稳定性为70%。只有7%的二阶影像组学特征显示出小于0.10的优异CoV。结论 神经母细胞瘤患者T2加权MRI制备过程中的修改导致了影像组学特征的变化，归一化被确定为可重复性最有影响的因素。不均匀性去除对影像组学特征的影响最小。儿科学、磁共振成像、肿瘤学、影像组学、可重复性、重复性、神经母细胞瘤 © RSNA，2024 另见本期Safdar和Galaria的评论。
Zotero 插件