A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme.
A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme.
复制标题
基于深度学习的放射组学模型，用于预测多形性胶质母细胞瘤的生存期
DOI：
10.1038/s41598-017-10649-8
复制
发表时间：
2017-09-04
影响因子：
4.6
通讯作者：
Zhai G
中科院分区：
文献类型：
--
作者：
Lao J;Chen Y;Li ZC;Li Q;Zhang J;Liu J;Zhai G
传统的放射组学模型主要依赖于医学图像中明确设计的手工特征。本文旨在研究通过迁移学习提取的深度特征是否可以生成放射组学特征，用于预测多形性胶质母细胞瘤（GBM）患者的总生存期（OS）。本研究包括75例患者的发现数据集和37例患者的独立验证数据集。从术前多模态MR图像中共提取了1403个手工特征和98304个深层特征。在特征选择之后，通过使用最小绝对收缩和选择算子（LASSO）考克斯回归模型构造六深度特征签名。放射组学列线图进一步提出了结合签名和临床风险因素，如年龄和Karnofsky性能评分。与传统的危险因素相比，所提出的签名在预测OS方面取得了更好的性能（C指数= 0.710，95% CI：0.588，0.932），并将患者显著分层为不同的组（P < 0.001，HR = 5.128，95% CI：2.029，12.960）。组合模型实现了改进的预测性能（C指数= 0.739）。我们的研究表明，基于迁移学习的深度特征能够生成用于OS预测和GBM患者分层的预后成像特征，表明基于深度成像特征的生物标志物在GBM患者术前护理中的潜力。
Traditional radiomics models mainly rely on explicitly-designed handcrafted features from medical images. This paper aimed to investigate if deep features extracted via transfer learning can generate radiomics signatures for prediction of overall survival (OS) in patients with Glioblastoma Multiforme (GBM). This study comprised a discovery data set of 75 patients and an independent validation data set of 37 patients. A total of 1403 handcrafted features and 98304 deep features were extracted from preoperative multi-modality MR images. After feature selection, a six-deep-feature signature was constructed by using the least absolute shrinkage and selection operator (LASSO) Cox regression model. A radiomics nomogram was further presented by combining the signature and clinical risk factors such as age and Karnofsky Performance Score. Compared with traditional risk factors, the proposed signature achieved better performance for prediction of OS (C-index = 0.710, 95% CI: 0.588, 0.932) and significant stratification of patients into prognostically distinct groups (P < 0.001, HR = 5.128, 95% CI: 2.029, 12.960). The combined model achieved improved predictive performance (C-index = 0.739). Our study demonstrates that transfer learning-based deep features are able to generate prognostic imaging signature for OS prediction and patient stratification for GBM, indicating the potential of deep imaging feature-based biomarker in preoperative care of GBM patients.
登录
查看更多内容
影响因子：
30.8
作者：
Weinstein, John N.;Collisson, Eric A.;Mills, Gordon B.;Shaw, Kenna R. Mills;Ozenberger, Brad A.;Ellrott, Kyle;Shmulevich, Ilya;Sander, Chris;Stuart, Joshua M.
通讯作者：
Stuart, Joshua M.
影响因子：
15.9
作者：
Dolecek, Therese A.;Propp, Jennifer M.;Kruchko, Carol
通讯作者：
Kruchko, Carol
影响因子：
39.2
作者：
Collins, Gary S.;Reitsma, Johannes B.;Moons, Karel G. M.
通讯作者：
Moons, Karel G. M.
放射组学特征：预测早期（I 期或 II 期）非小细胞肺癌无病生存的潜在生物标志物
影响因子：
19.7
作者：
Huang, Yanqi;Liu, Zaiyi;Liang, Changhong
通讯作者：
Liang, Changhong
影响因子：
2.7
作者：
FLEISS, JL;COHEN, J
通讯作者：
COHEN, J