Ultrasound images-based deep learning radiomics nomogram for preoperative prediction of RET rearrangement in papillary thyroid carcinoma.
Ultrasound images-based deep learning radiomics nomogram for preoperative prediction of RET rearrangement in papillary thyroid carcinoma.
复制标题
基于超声图像的深度学习放射组学列线图用于甲状腺乳头状癌 RET 重排的术前预测
DOI：
10.3389/fendo.2022.1062571
复制
发表时间：
2022
影响因子：
5.2
通讯作者：
Lu, Xiubo
中科院分区：
文献类型：
--
作者：
Yu, Jialong;Zhang, Yihan;Zheng, Jian;Jia, Meng;Lu, Xiubo
目的 创建基于超声的深度学习放射组学列线图 (DLRN)，用于术前预测甲状腺乳头状癌 (PTC) 患者是否存在 RET 重排。方法 我们回顾性纳入 650 名 PTC 患者。患者被分为 RET/PTC 重排组 (n = 103) 和非 RET/PTC 重排组 (n = 547)。基于超声图像中的手工特征提取放射组学特征，并使用深度学习网络提取深度迁移学习特征。应用最小绝对收缩和选择算子回归从放射组学和深度迁移学习特征中选择非零系数的特征；然后，我们建立了深度学习放射组学签名。 DLRN 是使用逻辑回归算法结合临床和深度学习放射组学特征构建的。使用受试者工作特征曲线、校准曲线和决策曲线分析来评估预测性能。结果通过连接每个模型的受试者工作特征曲线下面积来比较模型的有效性，我们发现测试队列中的DLRN曲线下面积可以达到0.9545（95％置信区间：0.9133-0.9558），训练队列中可以达到0.9396（95％置信区间：0.9185-0.9607），表明该模型具有出色的预测性能PTC 中的 RET 重排。决策曲线分析表明组合模型在临床上是有用的。结论基于超声的新型DLRN对于预测PTC中RET重排具有重要的临床价值。它可以为医生提供一种术前无创的RET重排诊断初步筛查方法，从而方便有针对性的患者进行有目的的分子测序，避免不必要的医疗投入，改善治疗效果。
Purpose To create an ultrasound -based deep learning radiomics nomogram (DLRN) for preoperatively predicting the presence of RET rearrangement among patients with papillary thyroid carcinoma (PTC). Methods We retrospectively enrolled 650 patients with PTC. Patients were divided into the RET/PTC rearrangement group (n = 103) and the non-RET/PTC rearrangement group (n = 547). Radiomics features were extracted based on hand-crafted features from the ultrasound images, and deep learning networks were used to extract deep transfer learning features. The least absolute shrinkage and selection operator regression was applied to select the features of nonzero coefficients from radiomics and deep transfer learning features; then, we established the deep learning radiomics signature. DLRN was constructed using a logistic regression algorithm by combining clinical and deep learning radiomics signatures. The prediction performance was evaluated using the receiver operating characteristic curve, calibration curve, and decision curve analysis. Results Comparing the effectiveness of the models by linking the area under the receiver operating characteristic curve of each model, we found that the area under the curve of DLRN could reach 0.9545 (95% confidence interval: 0.9133–0.9558) in the test cohort and 0.9396 (95% confidence interval: 0.9185–0.9607) in the training cohort, indicating that the model has an excellent performance in predicting RET rearrangement in PTC. The decision curve analysis demonstrated that the combined model was clinically useful. Conclusion The novel ultrasonic-based DLRN has an important clinical value for predicting RET rearrangement in PTC. It can provide physicians with a preoperative non-invasive primary screening method for RET rearrangement diagnosis, thus facilitating targeted patients with purposeful molecular sequencing to avoid unnecessary medical investment and improve treatment outcomes.
登录
查看更多内容
影响因子：
64.5
作者：
Cancer Genome Atlas Research Network
通讯作者：
Cancer Genome Atlas Research Network
DOI：
10.1038/s41379-020-0638-5
发表时间：
2020-12
期刊：
Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc
影响因子：
--
作者：
Chu YH;Wirth LJ;Farahani AA;Nosé V;Faquin WC;Dias-Santagata D;Sadow PM
通讯作者：
Sadow PM
影响因子：
5.2
作者：
Wang, Yu-guo;Xu, Fei-ju;Agyekum, Enock Adjei;Xiang, Hong;Wang, Yuan-dong;Zhang, Jin;Sun, Hui;Zhang, Guo-liang;Bo, Xiang-shu;Lv, Wen-zhi;Wang, Xian;Hu, Shu-dong;Qian, Xiao-qin
通讯作者：
Qian, Xiao-qin
影响因子：
4.8
作者：
Shangguan, Ronger;Hu, Yuan-Ping;Li, Peng
通讯作者：
Li, Peng
影响因子：
5.6
作者：
Adeniran, AJ;Zhu, ZW;Nikiforov, YE
通讯作者：
Nikiforov, YE