Yan Bi Cong, Ma Xiao Liang, Li Ying, Duan Shao Feng, Zhang Guo Fu, Qiang Jin Wei
Department of Radiology, Jinshan Hospital, Fudan University, Shanghai, China.
Department of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China.
Front Oncol. 2021 Sep 9;11:730281. doi: 10.3389/fonc.2021.730281. eCollection 2021.
Ovarian preservation treatment (OPT) was recommended in young women with early-stage endometrial cancer [superficial myometrial invasion (MI) and grades (G) 1/2-endometrioid adenocarcinoma (EEC)]. A radiomics nomogram was developed to assist radiologists in assessing the depth of MI and in selecting eligible patients for OPT.
From February 2014 to May 2021, 209 G 1/2-EEC patients younger than 45 years (mean 39 ± 4.3 years) were included. Of them, 104 retrospective patients were enrolled in the primary group, and 105 prospective patients were enrolled in the validation group. The radiomics features were extracted based on multi-parametric magnetic resonance imaging, and the least absolute shrinkage and selection operator algorithm was applied to reduce the dimensionality of the data and select the radiomics features that correlated with the depth of MI in G 1/2-EEC patients. A radiomics nomogram for evaluating the depth of MI was developed by combing the selected radiomics features with the cancer antigen 125 and tumor size. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of the radiomics nomogram and of radiologists without and with the aid of the radiomics nomogram. The net reclassification index (NRI) and total integrated discrimination index (IDI) based on the total included patients to assess the clinical benefit of radiologists with the radiomics nomogram were calculated.
In the primary group, for evaluating the depth of MI, the AUCs were 0.96 for the radiomics nomogram; 0.80 and 0.86 for radiologists 1 and 2 without the aid of the nomogram, respectively; and 0.98 and 0.98 for radiologists 1 and 2 with the aid of the nomogram, respectively. In the validation group, the AUCs were 0.88 for the radiomics nomogram; 0.82 and 0.83 for radiologists 1 and 2 without the aid of the nomogram, respectively; and 0.94 and 0.94 for radiologists 1 and 2 with the aid of the nomogram, respectively. The yielded NRI and IDI values were 0.29 and 0.43 for radiologist 1 and 0.23 and 0.37 for radiologist 2, respectively.
The radiomics nomogram outperformed radiologists and could help radiologists in assessing the depth of MI and selecting eligible OPTs in G 1/2-EEC patients.
对于早期子宫内膜癌（浅表肌层浸润（MI）且组织学分级（G）为1/2级的子宫内膜样腺癌（EEC））的年轻女性，推荐进行卵巢保留治疗（OPT）。开发了一种放射组学列线图，以协助放射科医生评估MI的深度，并选择适合OPT的患者。
纳入2014年2月至2021年5月期间年龄小于45岁（平均39±4.3岁）的209例G 1/2-EEC患者。其中，104例回顾性患者纳入初级组，105例前瞻性患者纳入验证组。基于多参数磁共振成像提取放射组学特征，并应用最小绝对收缩和选择算子算法降低数据维度，选择与G 1/2-EEC患者MI深度相关的放射组学特征。通过将选定的放射组学特征与癌抗原125和肿瘤大小相结合，开发了一种用于评估MI深度的放射组学列线图。采用受试者操作特征（ROC）曲线评估放射组学列线图以及不借助和借助放射组学列线图的放射科医生的诊断性能。计算基于所有纳入患者的净重新分类指数（NRI）和总综合鉴别指数（IDI），以评估放射科医生使用放射组学列线图的临床获益。
在初级组中，对于评估MI深度，放射组学列线图的曲线下面积（AUC）为0.96；不借助列线图时，放射科医生1和2的AUC分别为0.80和0.86；借助列线图时，放射科医生1和2的AUC分别为0.98和0.98。在验证组中，放射组学列线图的AUC为0.88；不借助列线图时，放射科医生1和2的AUC分别为0.82和0.83；借助列线图时，放射科医生1和2的AUC分别为0.94和0.94。放射科医生1的NRI和IDI值分别为0.29和0.43，放射科医生2的NRI和IDI值分别为0.23和0.37。
放射组学列线图的表现优于放射科医生，可帮助放射科医生评估G 1/2-EEC患者的MI深度并选择合适的OPT治疗方案。
