Prognostic value of FDG-PET radiomics with machine learning in pancreatic cancer.

Prognostic value of FDG-PET radiomics with machine learning in pancreatic cancer.
复制标题

DOI:
10.1038/s41598-020-73237-3
复制
发表时间:
2020-10-12
期刊:
影响因子:
4.6
通讯作者:
Takase K
Takase K
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Toyama Y;Hotta M;Motoi F;Takanami K;Minamimoto R;Takase K

文献摘要

参考文献

被引文献

相似文献

胰腺癌患者的预后较差,因此确定与预后相关的特定肿瘤特征非常重要。本研究旨在探讨使用 18F-氟脱氧葡萄糖 (FDG)-PET 进行机器学习的放射组学在胰腺癌患者中的实用性。我们招募了 161 名胰腺癌患者,接受了预处理 FDG-PET/CT。以最大标准化摄取值的 40% 为阈值,对原发肿瘤区域进行半自动轮廓绘制,并提取 42 个 PET 特征。为了确定预测 1 年生存率的相关 PET 参数,使用随机森林 (RF) 分类器测量基尼指数。随访 1 年内对 23 名患者进行了审查,其余 138 名患者用于分析。在 PET 参数中,有 10 个特征对于预测总生存期具有统计学意义。使用 Cox HR 回归的多变量分析表明,灰度区域长度矩阵 (GLZLM) 灰度不均匀性 (GLNU) 是唯一显示统计显着性的 PET 参数。在 RF 模型中,GLZLM GLNU 是预测 1 年生存率最相关的因素,其次是总病变糖酵解 (TLG)。 GLZLM GLNU 和 TLG 的组合根据不良预后的风险将患者分为三组。使用 FDG-PET 进行机器学习的放射组学为胰腺癌患者提供了有用的预后信息。
Patients with pancreatic cancer have a poor prognosis, therefore identifying particular tumor characteristics associated with prognosis is important. This study aims to investigate the utility of radiomics with machine learning using 18F-fluorodeoxyglucose (FDG)-PET in patients with pancreatic cancer. We enrolled 161 patients with pancreatic cancer underwent pretreatment FDG-PET/CT. The area of the primary tumor was semi-automatically contoured with a threshold of 40% of the maximum standardized uptake value, and 42 PET features were extracted. To identify relevant PET parameters for predicting 1-year survival, Gini index was measured using random forest (RF) classifier. Twenty-three patients were censored within 1 year of follow-up, and the remaining 138 patients were used for the analysis. Among the PET parameters, 10 features showed statistical significance for predicting overall survival. Multivariate analysis using Cox HR regression revealed gray-level zone length matrix (GLZLM) gray-level non-uniformity (GLNU) as the only PET parameter showing statistical significance. In RF model, GLZLM GLNU was the most relevant factor for predicting 1-year survival, followed by total lesion glycolysis (TLG). The combination of GLZLM GLNU and TLG stratified patients into three groups according to risk of poor prognosis. Radiomics with machine learning using FDG-PET in patients with pancreatic cancer provided useful prognostic information.
DOI: 10.1007/s11605-017-3627-3
发表时间: 2018-02-01
影响因子: 3.2
作者:
Ariake, Kyohei;Motoi, Fuyuhiko;Unno, Michiaki
通讯作者: Unno, Michiaki
DOI: 10.1097/rlu.0000000000001098
发表时间: 2016-03-01
影响因子: 10.6
作者:
Pimiento, Jose M.;Davis-Yadley, Ashley H.;Malafa, Mokenge P.
通讯作者: Malafa, Mokenge P.
DOI: 10.1038/nature09460
发表时间: 2010-10-28
期刊: Nature
影响因子: 64.8
作者:
通讯作者: --
DOI: 10.1093/annonc/mdu138
发表时间: 2014-08-01
期刊: ANNALS OF ONCOLOGY
影响因子: 50.5
作者:
Malvezzi, M.;Bertuccio, P.;Negri, E.
通讯作者: Negri, E.
DOI: 10.2967/jnumed.113.131847
发表时间: 2014-06-01
影响因子: 9.3
作者:
Lee, Jeong Won;Kang, Chang Moo;Lee, Jong Doo
通讯作者: Lee, Jong Doo