Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using (18)F-FDG PET Images.
Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using (18)F-FDG PET Images.
复制标题
DOI：
10.3390/diagnostics11061049
复制
发表时间：
2021-06-07
期刊：
影响因子：
--
通讯作者：
Nagata Y
中科院分区：
文献类型：
--
作者：
Murakami Y;Kawahara D;Tani S;Kubo K;Katsuta T;Imano N;Takeuchi Y;Nishibuchi I;Saito A;Nagata Y
背景资料：本研究旨在提出一种机器学习模型，使用预处理18-氟脱氧葡萄糖正电子发射断层扫描（FDG PET）图像预测新辅助放化疗（NCRT）治疗的可切除局部晚期食管鳞状细胞癌（LA-ESCC）的局部反应。方法：将98例局部缓解患者分为完全缓解组和非完全缓解组。我们使用在FDG PET图像上创建的五个分割进行了放射组学分析，导致每个患者有4250个特征。为了构建机器学习模型，我们使用最小绝对收缩和选择算子（LASSO）回归来提取最适合预测的放射组学特征。然后，通过使用神经网络分类器构建预测模型。训练模型采用5重交叉验证进行评估。结果：通过对训练数据的LASSO分析，提取了22个放射组学特征。在测试数据中，五个预测模型的平均准确性、敏感性、特异性和受试者工作特征曲线下面积得分分别为89.6%、92.7%、89.5%和0.95。结论：使用放射组学提出的机器学习模型显示出NCRT治疗LA-ESCC局部反应的预测准确性。
Background: This study aimed to propose a machine learning model to predict the local response of resectable locally advanced esophageal squamous cell carcinoma (LA-ESCC) treated by neoadjuvant chemoradiotherapy (NCRT) using pretreatment 18-fluorodeoxyglucose positron emission tomography (FDG PET) images. Methods: The local responses of 98 patients were categorized into two groups (complete response and noncomplete response). We performed a radiomics analysis using five segmentations created on FDG PET images, resulting in 4250 features per patient. To construct a machine learning model, we used the least absolute shrinkage and selection operator (LASSO) regression to extract radiomics features optimal for the prediction. Then, a prediction model was constructed by using a neural network classifier. The training model was evaluated with 5-fold cross-validation. Results: By the LASSO analysis of the training data, 22 radiomics features were extracted. In the testing data, the average accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve score of the five prediction models were 89.6%, 92.7%, 89.5%, and 0.95, respectively. Conclusions: The proposed machine learning model using radiomics showed promising predictive accuracy of the local response of LA-ESCC treated by NCRT.
登录
查看更多内容
影响因子：
11.2
作者：
van Griethuysen JJM;Fedorov A;Parmar C;Hosny A;Aucoin N;Narayan V;Beets-Tan RGH;Fillion-Robin JC;Pieper S;Aerts HJWL
通讯作者：
Aerts HJWL
影响因子：
19.7
作者：
Westerterp, M;van Westreenen, HL;Sloof, GW
通讯作者：
Sloof, GW
影响因子：
3.7
作者：
Ando, Nobutoshi;Kato, Hoichi;Fukuda, Haruhiko
通讯作者：
Fukuda, Haruhiko
DOI：
10.1016/j.compmedimag.2016.12.002
发表时间：
2017-09-01
影响因子：
5.7
作者：
Paul, Desbordes;Su, Ruan;Isabelle, Gardin
通讯作者：
Isabelle, Gardin
影响因子：
2
作者：
Murakami Y;Hamai Y;Emi M;Hihara J;Imano N;Takeuchi Y;Takahashi I;Nishibuchi I;Kimura T;Okada M;Nagata Y
通讯作者：
Nagata Y