Priya Sarv, Liu Yanan, Ward Caitlin, Le Nam H, Soni Neetu, Pillenahalli Maheshwarappa Ravishankar, Monga Varun, Zhang Honghai, Sonka Milan, Bathla Girish
Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA.
College of Engineering, University of Iowa, Iowa City, IA 52242, USA.
Cancers (Basel). 2021 May 24;13(11):2568. doi: 10.3390/cancers13112568.
Prior radiomics studies have focused on two-class brain tumor classification, which limits generalizability. The performance of radiomics in differentiating the three most common malignant brain tumors (glioblastoma (GBM), primary central nervous system lymphoma (PCNSL), and metastatic disease) is assessed; factors affecting the model performance and usefulness of a single sequence versus multiparametric MRI (MP-MRI) remain largely unaddressed. This retrospective study included 253 patients (120 metastatic (lung and brain), 40 PCNSL, and 93 GBM). Radiomic features were extracted for whole a tumor mask (enhancing plus necrotic) and an edema mask (first pipeline), as well as for separate enhancing and necrotic and edema masks (second pipeline). Model performance was evaluated using MP-MRI, individual sequences, and the T1 contrast enhanced (T1-CE) sequence without the edema mask across 45 model/feature selection combinations. The second pipeline showed significantly high performance across all combinations (Brier score: 0.311-0.325). GBRM fit using the full feature set from the T1-CE sequence was the best model. The majority of the top models were built using a full feature set and inbuilt feature selection. No significant difference was seen between the top-performing models for MP-MRI (AUC 0.910) and T1-CE sequence with (AUC 0.908) and without edema masks (AUC 0.894). T1-CE is the single best sequence with comparable performance to that of multiparametric MRI (MP-MRI). Model performance varies based on tumor subregion and the combination of model/feature selection methods.
先前的放射组学研究主要集中在两类脑肿瘤分类上，这限制了其通用性。本研究评估了放射组学在区分三种最常见的恶性脑肿瘤（胶质母细胞瘤（GBM）、原发性中枢神经系统淋巴瘤（PCNSL）和转移性疾病）方面的性能；影响模型性能的因素以及单序列与多参数MRI（MP-MRI）的实用性在很大程度上仍未得到解决。这项回顾性研究纳入了253例患者（120例转移性（肺和脑）、40例PCNSL和93例GBM）。针对整个肿瘤掩码（强化加坏死）和水肿掩码（第一个流程），以及单独的强化、坏死和水肿掩码（第二个流程）提取放射组学特征。使用MP-MRI、单个序列以及无水肿掩码的T1对比增强（T1-CE）序列，在45种模型/特征选择组合中评估模型性能。第二个流程在所有组合中均显示出显著的高性能（Brier评分：0.311 - 0.325）。使用T1-CE序列的完整特征集进行的GBRM拟合是最佳模型。大多数顶级模型是使用完整特征集和内置特征选择构建的。MP-MRI的顶级模型（AUC 0.910）与有（AUC 0.908）和无水肿掩码（AUC 0.894）的T1-CE序列之间未观察到显著差异。T1-CE是性能与多参数MRI（MP-MRI）相当的单一最佳序列。模型性能因肿瘤亚区域以及模型/特征选择方法的组合而异。
