A deep learning nomogram kit for predicting metastatic lymph nodes in rectal cancer.
A deep learning nomogram kit for predicting metastatic lymph nodes in rectal cancer.
复制标题
用于预测直肠癌转移淋巴结的深度学习列线图套件
作者：
Ding L;Liu G;Zhang X;Liu S;Li S;Zhang Z;Guo Y;Lu Y
利用最先进的基于更快区域的卷积神经网络（Faster R - CNN）深度学习技术在术前诊断转移性淋巴结（LNs）尚未有报道。2016年1月至2019年3月共纳入545例经病理证实的直肠癌患者，并按2:1的分割比例随机分配到训练组和验证组。转移性LNs的MRI图像采用Faster R - CNN进行评估。采用多元回归分析建立预测模型。基于训练集的多变量分析构建了更快的R - CNN模态图，并在验证集中进行了验证。用于预测转移性LN状态的Faster R - CNN nomogram包含年龄、Faster R - CNN转移性LN和肿瘤分化程度的预测因子，在训练集和验证集的曲线下面积（auc）分别为0.862 （95% CI: 0.816‐0.909）和0.920 （95% CI: 0.876‐0.964）。用于预测淋巴结转移程度的Faster R - CNN nomogram包含了通过Faster R - CNN预测转移性淋巴结和肿瘤分化程度的指标，在训练集和验证集的auc分别为0.859 （95% CI: 0.804‐0.913）和0.886 （95% CI: 0.822‐0.950）。校准图和决策曲线分析显示了良好的校准和临床应用。这两种形态图被联合用作预测转移性LNs的试剂盒。Faster R - CNN nomogram kit在鉴别、校准和临床应用方面表现优异，在术前预测转移性LNs方面方便可靠。临床试验注册：ChiCTR‐DDD‐17013842。用于预测转移性LN状态的深度学习nomogram表现出良好的鉴别率，约为0.900，具有良好的校准和临床实用性。预测淋巴结转移程度的深度学习nomogram也表现出良好的判别率（约为0.900）、可校准性和临床实用性。两种形态图可联合作为直肠癌各种淋巴结转移的术前风险预测工具。
Preoperative diagnoses of metastatic lymph nodes (LNs) by the most advanced deep learning technology of Faster Region‐based Convolutional Neural Network (Faster R‐CNN) have not yet been reported. In total, 545 patients with pathologically confirmed rectal cancer between January 2016 and March 2019 were included and were randomly allocated with a split ratio of 2:1 to the training and validation sets, respectively. The MRI images for metastatic LNs were evaluated by Faster R‐CNN. Multivariate regression analyses were used to develop the predictive models. Faster R‐CNN nomograms were constructed based on the multivariate analyses in the training sets and were validated in the validation sets. The Faster R‐CNN nomogram for predicting metastatic LN status contained predictors of age, metastatic LNs by Faster R‐CNN and differentiation degrees of tumors, with areas under the curves (AUCs) of 0.862 (95% CI: 0.816‐0.909) and 0.920 (95% CI: 0.876‐0.964) in the training and validation sets, respectively. The Faster R‐CNN nomogram for predicting LN metastasis degree contained predictors of metastatic LNs by Faster R‐CNN and differentiation degrees of tumors, with AUCs of 0.859 (95% CI: 0.804‐0.913) and 0.886 (95% CI: 0.822‐0.950) in the training and validation sets, respectively. Calibration plots and decision curve analyses demonstrated good calibrations and clinical utilities. The two nomograms were used jointly as a kit for predicting metastatic LNs. The Faster R‐CNN nomogram kit exhibits excellent performance in discrimination, calibration, and clinical utility and is convenient and reliable for predicting metastatic LNs preoperatively. Clinical trial registration: ChiCTR‐DDD‐17013842. The deep learning nomogram for predicting metastatic LN status exhibits excellent discrimination of around 0.900, and good calibration and clinical utility. The deep learning nomogram for predicting LN metastasis degree also exhibits excellent discrimination of around 0.900, and calibration and clinical utility. The 2 nomograms can be jointly used as a kit for the preoperative risk prediction of various LN metastases in rectal cancer.
登录
查看更多内容
影响因子：
3.9
作者：
Ishihara, Soichiro;Kawai, Kazushige;Watanabe, Toshiaki
通讯作者：
Watanabe, Toshiaki
基于新型血清 miRNA 特征和 CT 扫描，开发结直肠癌淋巴结转移的术前预测列线图。
影响因子：
11.1
作者：
Qu A;Yang Y;Zhang X;Wang W;Liu Y;Zheng G;Du L;Wang C
通讯作者：
Wang C
影响因子：
11.2
作者：
Lu, Yun;Yu, Qiyue;Yang, Shujian
通讯作者：
Yang, Shujian
影响因子：
3.6
作者：
Vickers, Andrew J.;Elkin, Elena B.
通讯作者：
Elkin, Elena B.
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S