Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
Department of Neurosurgery, The Henan Provincial People's Hospital, Zhengzhou, Henan, China.
J Magn Reson Imaging. 2023 Oct;58(4):1234-1242. doi: 10.1002/jmri.28630. Epub 2023 Feb 2.
BACKGROUND: Genetic testing for molecular markers of gliomas sometimes is unavailable because of time-consuming and expensive, even limited tumor specimens or nonsurgery cases. PURPOSE: To train a three-class radiomic model classifying three molecular subtypes including isocitrate dehydrogenase (IDH) mutations and 1p/19q-noncodeleted (IDHmut-noncodel), IDH wild-type (IDHwt), IDH-mutant and 1p/19q-codeleted (IDHmut-codel) of adult gliomas and investigate whether radiomic features from diffusion-weighted imaging (DWI) could bring additive value. STUDY TYPE: Retrospective. POPULATION: A total of 755 patients including 111 IDHmut-noncodel, 571 IDHwt, and 73 IDHmut-codel cases were divided into training (n = 480) and internal validation set (n = 275); 139 patients including 21 IDHmut-noncodel, 104 IDHwt, and 14 IDHmut-codel cases were utilized as external validation set. FIELD STRENGTH/SEQUENCE: A 1.5 T or 3.0 T/multiparametric MRI, including T1-weighted (T1), T1-weighted gadolinium contrast-enhanced (T1c), T2-weighted (T2), fluid attenuated inversion recovery (FLAIR), and DWI. ASSESSMENT: The performance of multiparametric radiomic model (random-forest model) using 22 selected features from T1, T2, FLAIR, T1c images and apparent diffusion coefficient (ADC) maps, and conventional radiomic model using 20 selected features from T1, T2, FLAIR, and T1c images was assessed in internal and external validation sets by comparing probability values and actual incidence. STATISTICAL TESTS: Mann-Whitney U test, Chi-Squared test, Wilcoxon test, receiver operating curve (ROC), and area under the curve (AUC); DeLong analysis. P < 0.05 was statistically significant. RESULTS: The multiparametric radiomic model achieved AUC values for IDHmut-noncodel, IDHwt, and IDHmut-codel of 0.8181, 0.8524, and 0.8502 in internal validation set and 0.7571, 0.7779, and 0.7491 in external validation set, respectively. Multiparametric radiomic model showed significantly better diagnostic performance after DeLong analysis, especially in classifying IDHwt and IDHmut-noncodel subtypes. DATA CONCLUSION: Radiomic features from DWI could bring additive value and improve the performance of conventional MRI-based radiomic model for classifying the molecular subtypes especially IDHmut-noncodel and IDHwt of adult gliomas. TECHNICAL EFFICACY: Stage 2.
背景：由于耗时且昂贵，甚至是由于肿瘤标本有限或无法进行手术，有时无法对分子标志物进行基因检测。
目的：旨在训练一个能够对包括异柠檬酸脱氢酶（IDH）突变和 1p/19q 未缺失（IDHmut-noncodel）、IDH 野生型（IDHwt）、IDH 突变且 1p/19q 缺失（IDHmut-codel）的成人脑胶质瘤的三种分子亚型进行分类的三分类放射组学模型，并探讨弥散加权成像（DWI）的放射组学特征是否具有附加价值。
研究类型：回顾性研究。
人群：共有 755 例患者，包括 111 例 IDHmut-noncodel、571 例 IDHwt 和 73 例 IDHmut-codel，将其分为训练集（n=480）和内部验证集（n=275）；另外有 139 例患者，包括 21 例 IDHmut-noncodel、104 例 IDHwt 和 14 例 IDHmut-codel，被用于外部验证集。
磁场强度/序列：1.5T 或 3.0T/多参数 MRI，包括 T1 加权（T1）、T1 加权钆增强（T1c）、T2 加权（T2）、液体衰减反转恢复（FLAIR）和 DWI。
评估：通过比较概率值和实际发生率，评估了从 T1、T2、FLAIR、T1c 图像和表观扩散系数（ADC）图中选择的 22 个特征的多参数放射组学模型（随机森林模型）和从 T1、T2、FLAIR 和 T1c 图像中选择的 20 个特征的常规放射组学模型在内部和外部验证集中的性能。
统计学检验：Mann-Whitney U 检验、卡方检验、Wilcoxon 检验、受试者工作特征曲线（ROC）和曲线下面积（AUC）；DeLong 分析。P<0.05 具有统计学意义。
结果：在内部验证集中，多参数放射组学模型对 IDHmut-noncodel、IDHwt 和 IDHmut-codel 的 AUC 值分别为 0.8181、0.8524 和 0.8502，在外部验证集中的 AUC 值分别为 0.7571、0.7779 和 0.7491。经 DeLong 分析，多参数放射组学模型的诊断性能显著提高，尤其是在分类 IDHwt 和 IDHmut-noncodel 亚型方面。
数据结论：DWI 的放射组学特征可提供附加价值，并提高基于常规 MRI 的放射组学模型对成人脑胶质瘤分子亚型的分类性能，特别是 IDHmut-noncodel 和 IDHwt 亚型。
技术功效：2 级。
Diagnostics (Basel). 2024-12-5
Zotero 插件