PET/CT Based EGFR Mutation Status Classification of NSCLC Using Deep Learning Features and Radiomics Features.
PET/CT Based EGFR Mutation Status Classification of NSCLC Using Deep Learning Features and Radiomics Features.
复制标题
使用深度学习特征和放射组学特征对基于 PET/CT 的 NSCLC EGFR 突变状态进行分类
DOI：
10.3389/fphar.2022.898529
复制
发表时间：
2022
影响因子：
5.6
通讯作者：
Cao, Xin
中科院分区：
文献类型：
--
作者：
Huang, Weicheng;Wang, Jingyi;Wang, Haolin;Zhang, Yuxiang;Zhao, Fengjun;Li, Kang;Su, Linzhi;Kang, Fei;Cao, Xin
目的：比较放射组学和深度学习在基于PET/CT图像预测肺癌患者EGFR突变状态中的作用，试图探索一种预测性能优良的模型来准确预测非小细胞肺癌(NSCLC)患者的EGFR突变状态。方法：收集西京医院194例非小细胞肺癌患者的PET/CT图像，按7：3的比例分为训练集和验证集。对患者的临床特征进行统计，利用放射组学工具包和三维卷积神经网络对患者的PET/CT图像进行特征提取(4306个放射组学特征和2048个深度学习特征)。然后建立放射组学模型(RM)、深度学习模型(DLM)和混合模型(HM)。通过受试者工作特征(ROC)曲线、灵敏度、特异度、准确度、校准曲线和判定曲线比较三种模型的性能。此外，还绘制了基于深度学习评分(DS)和最显著的临床特征的诺模图。结果：在138例患者(有EGFR突变，74例无突变)中，HM的ROC曲线下面积(AUC)(0.91，95%CI：0.86~0.96)高于RM(0.82，95%CI：0.75~0.89)和DLm(0.90，95%CI：0.85~0.95)。在57例(32例有EGFR突变和25例无EGFR突变)患者中，HM的AUC(0.85，95%CI：0.77~0.93)也高于RM(0.68，95%CI：0.52~0.84)和DLM(0.79，95%CI：0.67~0.91)。总体而言，HM在预测非小细胞肺癌患者的EGFR突变状态方面取得了比其他两个模型更好的诊断性能。结论：基于PET/CT图像的深度学习模型在诊断非小细胞肺癌患者EGFR突变状态方面优于放射组学模型。结合最具统计学意义的临床特征(吸烟)和深度学习特征，我们的混合模型在预测患者的EGFR突变类型方面比其他两个模型具有更好的性能，这可以使NSCLC患者选择更个性化的治疗方案。
Purpose: This study aimed to compare the performance of radiomics and deep learning in predicting EGFR mutation status in patients with lung cancer based on PET/CT images, and tried to explore a model with excellent prediction performance to accurately predict EGFR mutation status in patients with non-small cell lung cancer (NSCLC). Method: PET/CT images of 194 NSCLC patients from Xijing Hospital were collected and divided into a training set and a validation set according to the ratio of 7:3. Statistics were made on patients’ clinical characteristics, and a large number of features were extracted based on their PET/CT images (4306 radiomics features and 2048 deep learning features per person) with the pyradiomics toolkit and 3D convolutional neural network. Then a radiomics model (RM), a deep learning model (DLM), and a hybrid model (HM) were established. The performance of the three models was compared by receiver operating characteristic (ROC) curves, sensitivity, specificity, accuracy, calibration curves, and decision curves. In addition, a nomogram based on a deep learning score (DS) and the most significant clinical characteristic was plotted. Result: In the training set composed of 138 patients (64 with EGFR mutation and 74 without EGFR mutation), the area under the ROC curve (AUC) of HM (0.91, 95% CI: 0.86–0.96) was higher than that of RM (0.82, 95% CI: 0.75–0.89) and DLM (0.90, 95% CI: 0.85–0.95). In the validation set composed of 57 patients (32 with EGFR mutation and 25 without EGFR mutation), the AUC of HM (0.85, 95% CI: 0.77–0.93) was also higher than that of RM (0.68, 95% CI: 0.52–0.84) and DLM (0.79, 95% CI: 0.67–0.91). In all, HM achieved better diagnostic performance in predicting EGFR mutation status in NSCLC patients than two other models. Conclusion: Our study showed that the deep learning model based on PET/CT images had better performance than radiomics model in diagnosing EGFR mutation status of NSCLC patients based on PET/CT images. Combined with the most statistically significant clinical characteristic (smoking) and deep learning features, our hybrid model had better performance in predicting EGFR mutation types of patients than two other models, which could enable NSCLC patients to choose more personalized treatment schemes.
登录
查看更多内容
影响因子：
4.8
作者：
Jiang, Mengmeng;Sun, Dazhen;Yao, Xiuzhong
通讯作者：
Yao, Xiuzhong
影响因子：
3.8
作者：
Ren, Meihong;Yang, Huazhe;Jiang, Xiran
通讯作者：
Jiang, Xiran
影响因子：
4.7
作者：
Zhang B;Qi S;Pan X;Li C;Yao Y;Qian W;Guan Y
通讯作者：
Guan Y
影响因子：
15.1
作者：
Cui Y;Zhang J;Li Z;Wei K;Lei Y;Ren J;Wu L;Shi Z;Meng X;Yang X;Gao X
通讯作者：
Gao X
将手动诊断融入放射组学降低疑似肺癌患者F-18-FDG PET/CT诊断假阳性率
DOI：
10.1007/s00259-019-04418-0
发表时间：
2019-12-01
影响因子：
9.1
作者：
Kang, Fei;Mu, Wei;Wang, Jing
通讯作者：
Wang, Jing