基于集成学习的多序列磁共振成像放射组学在良恶性软组织肿瘤鉴别中的应用。

Ensemble learning-based radiomics with multi-sequence magnetic resonance imaging for benign and malignant soft tissue tumor differentiation.

机构信息

Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.

Division of Biomedical Engineering, Hankuk University of Foreign Studies, Seoul, Gyeonggi-do, Republic of Korea.

出版信息

PLoS One. 2023 May 31;18(5):e0286417. doi: 10.1371/journal.pone.0286417. eCollection 2023.

DOI:10.1371/journal.pone.0286417

PMID:37256875

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10231763/

Abstract

Many previous studies focused on differentiating between benign and malignant soft tissue tumors using radiomics model based on various magnetic resonance imaging (MRI) sequences, but it is still unclear how to set up the input radiomic features from multiple MRI sequences. Here, we evaluated two types of radiomics models generated using different feature incorporation strategies. In order to differentiate between benign and malignant soft tissue tumors (STTs), we compared the diagnostic performance of an ensemble of random forest (R) models with single-sequence MRI inputs to R models with pooled multi-sequence MRI inputs. One-hundred twenty-five STT patients with preoperative MRI were retrospectively included and consisted of training (n = 100) and test (n = 25) sets. MRI included T1-weighted (T1-WI), T2-weighted (T2-WI), contrast-enhanced (CE)-T1-WI, diffusion-weighted images (DWIs, b = 800 sec/mm2) and apparent diffusion coefficient (ADC) maps. After tumor segmentation on each sequence, 100 original radiomic features were extracted from each sequence image and divided into three-feature sets: T features from T1- and T2-WI, CE features from CE-T1-WI, and D features from DWI and ADC maps. Four radiomics models were built using Lasso and R with four combinations of three-feature sets as inputs: T features (R-T), T+CE features (R-C), T+D features (R-D), and T+CE+D features (R-A) (Type-1 model). An ensemble model was built by soft voting of five, single-sequence-based R models (Type-2 model). AUC, sensitivity, specificity, and accuracy of each model was calculated with five-fold cross validation. In Type-1 model, AUC, sensitivity, specificity, and accuracy were 0.752, 71.8%, 61.1%, and 67.2% in R-T; 0.756, 76.1%, 70.4%, and 73.6% in R-C; 0.750, 77.5%, 63.0%, and 71.2% in R-D; and 0.749, 74.6%, 61.1%, and 68.8% R-A models, respectively. AUC, sensitivity, specificity, and accuracy of Type-2 model were 0.774, 76.1%, 68.5%, and 72.8%. In conclusion, an ensemble method is beneficial to incorporate features from multi-sequence MRI and showed diagnostic robustness for differentiating malignant STTs.

摘要

许多先前的研究都集中在使用基于各种磁共振成像（MRI）序列的放射组学模型来区分良性和恶性软组织肿瘤，但如何从多个 MRI 序列中设置输入放射组学特征仍不清楚。在这里，我们评估了使用两种不同特征纳入策略生成的两种放射组学模型。为了区分良性和恶性软组织肿瘤（STT），我们比较了基于单序列 MRI 输入的随机森林（R）模型的诊断性能与基于多序列 MRI 输入的 R 模型的诊断性能。回顾性纳入了 125 例术前 MRI 的 STT 患者，包括训练集（n=100）和测试集（n=25）。MRI 包括 T1 加权（T1-WI）、T2 加权（T2-WI）、对比增强（CE）-T1-WI、弥散加权图像（DWI，b=800 sec/mm2）和表观弥散系数（ADC）图。在对每个序列的肿瘤进行分割后，从每个序列图像中提取 100 个原始放射组学特征，并将其分为三个特征集：T1-WI 和 T2-WI 的 T 特征、CE-T1-WI 的 CE 特征以及 DWI 和 ADC 图的 D 特征。使用 Lasso 和 R 构建了四个放射组学模型，四个组合的三个特征集作为输入：T 特征（R-T）、T+CE 特征（R-C）、T+D 特征（R-D）和 T+CE+D 特征（R-A）（类型 1 模型）。通过软投票构建了一个由五个基于单序列的 R 模型组成的集成模型（类型 2 模型）。使用五重交叉验证计算每个模型的 AUC、敏感性、特异性和准确性。在类型 1 模型中，R-T 模型的 AUC、敏感性、特异性和准确性分别为 0.752、71.8%、61.1%和 67.2%；R-C 模型的 AUC、敏感性、特异性和准确性分别为 0.756、76.1%、70.4%和 73.6%；R-D 模型的 AUC、敏感性、特异性和准确性分别为 0.750、77.5%、63.0%和 71.2%；R-A 模型的 AUC、敏感性、特异性和准确性分别为 0.749、74.6%、61.1%和 68.8%。类型 2 模型的 AUC、敏感性、特异性和准确性分别为 0.774、76.1%、68.5%和 72.8%。总之，集成方法有利于从多序列 MRI 中提取特征，并在区分恶性 STT 方面表现出诊断稳健性。