Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis.
Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis.
复制标题
DOI：
10.1371/journal.pone.0261401
复制
发表时间：
2021
期刊：
影响因子：
3.7
通讯作者：
Frauenfelder T
中科院分区：
文献类型：
--
作者：
Blüthgen C;Patella M;Euler A;Baessler B;Martini K;von Spiczak J;Schneiter D;Opitz I;Frauenfelder T
评价CT衍生放射组学用于基于机器学习的胸腺上皮肿瘤（泰特）分期（TNM分类）、组织学（WHO分类）和重症肌无力（MG）的分类。回顾性纳入了2000-2018年间经组织学证实的泰特患者，排除了影像学不相容或其他肿瘤的患者。对CT扫描图像进行统一的重新格式化，对灰度值进行归一化和离散化。手动分割肿瘤; 2周后由两名阅片员重新分割15次扫描。计算了1316个放射组学特征（pyRadiomics）。排除了具有低内部/内部阅读者一致性（ICC<0.75）的特征。重复嵌套交叉验证用于特征选择（Boruta算法）、模型训练和评估（折外预测）。计算Shapley加性解释（SHAP）值以评估特征重要性。确定了105例因泰特接受手术的患者。在应用排除标准后，62名患者（28名女性;平均年龄，57±14岁;范围，22-82岁）被纳入，其中34名低风险泰特（LRT; WHO A/AB/B1型），28名高风险泰特（HRT; WHO B2/B3/C型）处于早期（49名，TNM分期I-II）或晚期（13名，TNM III-IV）。14例（23%）患者患有MG。334（25%）个特征在阅片者内/阅片者间分析后被排除。随机森林分类器对组织学（AUC，87.6%; 95%置信区间，76.3-94.3）和TNM分期（AUC，83.8%; 95%CI，66.9-93.4）的判别性能良好，但对MG的预测较差（AUC，63.9%; 95%CI，44.8-79.5）。CT衍生的放射组学特征可能是泰特组织学和TNM分期的有用的成像生物标志物。
To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG). Patients with histologically confirmed TET in the years 2000–2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance. 105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22–82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3–94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9–93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8–79.5). CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.
登录
查看更多内容
影响因子：
5.8
作者：
Kursa, Miron B.;Rudnicki, Witold R.
通讯作者：
Rudnicki, Witold R.
影响因子：
4.2
作者：
Chen, Xiangmeng;Feng, Bao;Long, Wansheng
通讯作者：
Long, Wansheng
影响因子：
8.9
作者：
Iannarelli, Angelo;Sacconi, Beatrice;Catalano, Carlo
通讯作者：
Catalano, Carlo
影响因子：
19.7
作者：
Orlhac, Fanny;Frouin, Frederique;Buvat, Irene
通讯作者：
Buvat, Irene
影响因子：
6.7
作者：
Mannil, Manoj;von Spiczak, Jochen;Alkadhi, Hatem
通讯作者：
Alkadhi, Hatem