基于非增强 MRI 的放射组学模型用于术前预测高强度聚焦超声消融子宫肌瘤的非灌注体积比。

Nonenhanced MRI-based radiomics model for preoperative prediction of nonperfused volume ratio for high-intensity focused ultrasound ablation of uterine leiomyomas.

机构信息

Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, PR China.

State Key Laboratory of Ultrasound in Medicine and Engineering, Chongqing Medical University, Chongqing, China.

出版信息

Int J Hyperthermia. 2021;38(1):1349-1358. doi: 10.1080/02656736.2021.1972170.

DOI:10.1080/02656736.2021.1972170

PMID:34486913

Abstract

OBJECTIVES

To develop and assess nonenhanced MRI-based radiomics model for the preoperative prediction of nonperfused volume (NPV) ratio of uterine leiomyomas after high-intensity focused ultrasound (HIFU) treatment.

METHODS

Two hundred and five patients with uterine leiomyomas treated by HIFU were enrolled and allocated to training ( =164) and testing cohorts ( = 41). Pyradiomics was used to extract radiomics features from T2-weighted images and apparent diffusion coefficient (ADC) map generated from diffusion-weighted imaging (DWI). The clinico-radiological model, radiomics model, and radiomics-clinical model which combined the selected radiomics features and clinical parameters were used to predict technical outcomes determined by NPV ratios where three classification groups were created (NPV ratio ≤ 50%, 50-80% or ≥ 80%). The receiver operating characteristic (ROC) curve, area under the curve (AUC), and calibration and decision curve analyses were performed to illustrate the prediction performance and clinical usefulness of model in the training and testing cohorts.

RESULTS

The multi-parametric MRI-based radiomics model outperformed T2-weighted imaging (T2WI)-based radiomics model, which achieved an average AUC of 0.769 (95% confidence interval [CI], 0.701-0.842), and showed satisfactory prediction performance for NPV ratio classification. The radiomics-clinical model demonstrated best prediction performance for HIFU treatment outcome, with an average AUC of 0.802 (95% CI, 0.796-0.850) and an accuracy of 0.762 (95% CI, 0.698-0.815) in the testing cohort, compared to the clinico-radiological and radiomics models. The decision curve also indicated favorable clinical usefulness of the radiomics-clinical model.

CONCLUSIONS

Nonenhanced MRI-based radiomics has potential in the preoperative prediction of NPV ratio for HIFU ablation of uterine leiomyomas.

摘要

目的

开发并评估基于非增强 MRI 的放射组学模型，以预测高强度聚焦超声（HIFU）治疗后子宫肌瘤的非灌注体积（NPV）比值。

方法

共纳入 205 例接受 HIFU 治疗的子宫肌瘤患者，将其分为训练集（n=164）和测试集（n=41）。使用 Pyradiomics 从 T2 加权成像（T2WI）和扩散加权成像（DWI）生成的表观扩散系数（ADC）图中提取放射组学特征。使用临床-放射学模型、放射组学模型和结合选择的放射组学特征和临床参数的放射组学-临床模型来预测由 NPV 比值确定的技术结果，其中创建了三个分类组（NPV 比值≤50%、50-80%或≥80%）。在训练集和测试集中，使用受试者工作特征（ROC）曲线、曲线下面积（AUC）、校准和决策曲线分析来评估模型的预测性能和临床实用性。

结果

多参数 MRI 基放射组学模型优于 T2WI 基放射组学模型，平均 AUC 为 0.769（95%置信区间 [CI]，0.701-0.842），对 NPV 比值分类具有较好的预测性能。放射组学-临床模型对 HIFU 治疗结果的预测性能最佳，在测试集中的平均 AUC 为 0.802（95%CI，0.796-0.850）和准确率为 0.762（95%CI，0.698-0.815），优于临床-放射学和放射组学模型。决策曲线也表明放射组学-临床模型具有良好的临床实用性。