请选择 进入手机版 | 继续访问电脑版

CT影像组学特征可预测胸腺上皮肿瘤的可切除性和TNM分期

已有 193 次阅读2021-4-14 20:07 |个人分类:TET学习|系统分类:医学科学| 胸腺上皮肿瘤, 胸腺瘤

CT影像组学特征可预测胸腺上皮肿瘤的可切除性和TNM分期。CT Radiomic Features for Predicting Resectability and TNM Staging in Thymic Epithelial Tumors
背景:探讨CT组学模型在胸腺上皮肿瘤(TET)的可切除性状态和TNM分期的术前预测中的效能。
方法:我们回顾了2008年2月至2019年6月在我们机构手术切除和病理检查前对TET患者进行的最后一次术前CT。提取了101个定量特征,并使用弹性网络惩罚逻辑回归分析了每个目标的组学模型。在预留的测试集中,使用受试者工作特性曲线下面积(AUC)评估每个模型的鉴别效能。
结果:我们的最终人群包括243例患者,其中:153例(87%)胸腺瘤,23例(9%)胸腺癌和9例(4%)胸腺类癌。38例(16%)患者发生不完全切除(R1或R2),而晚期肿瘤(III或IV期)的患者有67例(28%)。在预留的测试集中,影像组学模型在术前预测不完全切除(AUC 0.80)和晚期肿瘤(AUC 0.70)方面表现良好。
结论:我们的CT组学模型在预测TET的可切除性状态和分期方面表现出良好的性能,这为通过组学特征术前预测胸腺恶性肿瘤预后提供了潜在价值。


Figure 1: Flowchart of patient selection. Patients with free surgical margins (R0) were included in the resected group, while patients with microscopic (R1) or macroscopic (R2)

residual tumor were included in the unresected group. Early-stage thymic epithelial tumors (TETs) include TNM stages I and II, and advanced-stage TETs include TNM stages III and IV.

Figure 2: Preoperative chest computed tomography of a 53-year-old female patient presenting with a mediastinal mass (a). Tumor was manually segmented (b) and radiomic

features (c) were extracted. Note the tumor heterogeneity throughout the lesion illustrated in an entropy map in (c), where the blue areas represent tumor areas with low entropy. Final

diagnosis was an advanced-stage thymoma (Masaoka-Koga IV) with positive margins due to microscopic residual tumor (R1).

Figure 3: Preoperative chest computed tomography of a 55-year-old female patient presenting with a mediastinal mass (a). After tumor segmentation (b), radiomic features were extracted (c). Note that the lesion has a relative homogenous appearance (uniformly orange/red – high entropy) in the entropy map (c). The lesion (early-stage thymoma – Masaoka-Koga II) was completely resected with no evidence of residual disease (R0). 

Background: To explore the performance of a computed tomography based radiomics model in the preoperative prediction of resectability status and TNM staging in thymic epithelial tumors (TETs).
Methods: We reviewed the last preoperative computed tomography scan of patients with TETs prior to resection and pathology evaluation at our institution between February 2008 and June 2019. 101 quantitative features were extracted and a radiomics model was trained using elastic net penalized logistic regressions for each aim. In the set-aside testing sets, discriminating performance of each model was assessed with area under receiver operating characteristic curve (AUC).
Results: Our final population consisted of 243 patients with: 153 (87%) thymomas, 23 (9%) thymic carcinomas, and 9 (4%) thymic carcinoids. Incomplete resections (R1 or R2) occurred in 38 (16%) patients, and 67 (28%) patients had more advanced stage tumors (stage III or IV). In the set-aside testing sets, the radiomics model achieved good performance in preoperatively predicting incomplete resections (AUC 0.80) and advanced stage tumors (AUC 0.70).
Conclusions: Our computed tomography radiomics model achieved good performance to predict resectability status and staging in TETs, suggesting a potential value for the evaluation of radiomic features in the preoperative prediction of surgical outcomes in thymic malignancies.

Batista Araujo-Filho JA, Mayoral M, Zheng J, Tan KS, Gibbs P, Shepherd AF, Rimner A, Simone CB 2nd, Riely G, Huang J, Ginsberg MS. CT Radiomic Features for Predicting Resectability and TNM Staging in Thymic Epithelial Tumors. Ann Thorac Surg. 2021 Apr 9:S0003-4975(21)00665-2. doi: 10.1016/j.athoracsur.

路过

鸡蛋

鲜花

握手

雷人

评论 (0 个评论)

facelist

您需要登录后才可以评论 登录 | 立即注册

返回顶部