基于 MRI 的放射组学列线图预测 FIGOⅠ期子宫内膜癌的深肌层浸润。
MRI-based radiomics nomogram for the preoperative prediction of deep myometrial invasion of FIGO stage I endometrial carcinoma.
机构信息
Radiology Department, Liaoning Cancer Hospital & Institute, China Medical University, Shenyang, Liaoning, China.
Radiology Department, Shengjing Hospital, China Medical University, Shenyang, Liaoning, China.
出版信息
Med Phys. 2022 Oct;49(10):6505-6516. doi: 10.1002/mp.15835. Epub 2022 Aug 15.
BACKGROUND
Endometrial carcinoma (EC) is one of the most common gynecological malignancies with an increasing incidence, and an accurate preoperative diagnosis of deep myometrial invasion (DMI) is crucial for personalized treatment.
OBJECTIVE
To determine the predictive value of a magnetic resonance imaging (MRI)-based radiomics nomogram for the presence of DMI in the International Federation of Gynecology and Obstetrics (FIGO) stage I EC.
METHODS
We retrospectively collected 163 patients with pathologically confirmed stage I EC from two centers and divided all samples into a training group (Center 1) and a validation group (Center 2). Clinical and routine imaging indicators were analyzed by logistical regression to construct a conventional diagnostic model (M1). Radiomics features extracted from the axial T2-weighted and axial contrast-enhanced T1-weighted (CE-T1W) images were treated with the intraclass correlation coefficient, Mann-Whitney U test, least absolute shrinkage and selection operator, and logistic regression analysis with Akaike information criterion to build a combined radiomics signature (M2). A nomogram (M3) was constructed by M1 and M2. Calibration and decision curves were drawn to evaluate the nomogram in the training and validation cohorts. The diagnostic performance of each indicator and model was evaluated by the area under the receiver operating characteristic curve (AUC).
RESULT
The four most significant radiomics features were finally selected from the CE-T1W MRI. For the diagnosis of DMI, the AUC /AUC of M1 was 0.798/0.738, the AUC /AUC of M2 was 0.880/0.852, and the AUC /AUC of M3 was 0.936/0.871 in the training and validation groups, respectively. The calibration curves showed that M3 was in good agreement with the ideal values. The decision curve analysis suggested potential clinical application values of the nomogram.
CONCLUSION
A nomogram based on MRI radiomics and clinical imaging indicators can improve the diagnosis of DMI in patients with FIGO stage I EC.
背景
子宫内膜癌（EC）是最常见的妇科恶性肿瘤之一，发病率呈上升趋势，准确的术前诊断深部肌层浸润（DMI）对于个体化治疗至关重要。
目的
确定基于磁共振成像（MRI）的放射组学列线图预测国际妇产科联合会（FIGO）分期 I 期 EC 中 DMI 存在的价值。
方法
我们回顾性地从两个中心收集了 163 例经病理证实的 FIGO 分期 I 期 EC 患者，将所有样本分为训练组（中心 1）和验证组（中心 2）。通过逻辑回归分析临床和常规影像学指标，构建传统诊断模型（M1）。对轴向 T2 加权和轴向对比增强 T1 加权（CE-T1W）图像提取的放射组学特征进行了组内相关系数、Mann-Whitney U 检验、最小绝对收缩和选择算子以及基于 Akaike 信息准则的逻辑回归分析，以构建联合放射组学特征（M2）。通过 M1 和 M2 构建列线图（M3）。在训练和验证队列中绘制校准和决策曲线以评估列线图。通过受试者工作特征曲线下面积（AUC）评估每个指标和模型的诊断性能。
结果
最终从 CE-T1W MRI 中选择了四个最重要的放射组学特征。对于 DMI 的诊断，M1 的 AUC/AUC 在训练和验证组中分别为 0.798/0.738、M2 的 AUC/AUC 为 0.880/0.852，M3 的 AUC/AUC 为 0.936/0.871。校准曲线表明 M3 与理想值吻合良好。决策曲线分析表明该列线图具有潜在的临床应用价值。
结论
基于 MRI 放射组学和临床影像学指标的列线图可以提高 FIGO 分期 I 期 EC 患者 DMI 的诊断能力。
Zotero 插件