Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans.
Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans.
复制标题
DOI：
10.1038/s42003-021-02814-7
复制
发表时间：
2021-11-12
影响因子：
5.9
通讯作者：
Park H
中科院分区：
文献类型：
--
作者：
Cho HH;Lee HY;Kim E;Lee G;Kim J;Kwon J;Park H
深度学习是医学影像领域的一项突破性技术，具有较高的样本量要求和可解释性问题。通过放射组学引导的方法使用预先训练的DL模型，我们提出了一种基于预处理CT的肺腺癌预后分层方法。我们的方法允许我们以更小的样本量要求和增强的可解释性来应用数字逻辑。建立了预测肺腺癌预后的基线放射组学和DL模型，并使用本地(n = 617)队列进行了检验。DL模型进一步在外部验证(n = 70)队列中进行了测试。当地的队列被分为培训队列和测试队列。使用Cox-Lasso建立放射组学风险评分(RRS)。从自然图像中提取出三个预先训练好的DL网络来提取DL特征。通过保留那些与放射组学特征相关性高且Bonferroni校正的p值低的DL特征，使用放射组学进一步指导这些特征。在构建DL风险评分(DRS)时，保留的DL特征受到Cox-Lasso的约束。按RRS和DRS分层的风险组在培训、测试和验证队列中显示出显著差异。利用已有的放射组学特征解释了数字减影特征，纹理特征很好地解释了数字减影特征。赵等人使用放射组学指导的深度学习方法，根据CT扫描数据对肺腺癌的预后进行建模。这项研究证明了这项技术作为临床预后分组分层的预测方法的实用性。
Deep learning (DL) is a breakthrough technology for medical imaging with high sample size requirements and interpretability issues. Using a pretrained DL model through a radiomics-guided approach, we propose a methodology for stratifying the prognosis of lung adenocarcinomas based on pretreatment CT. Our approach allows us to apply DL with smaller sample size requirements and enhanced interpretability. Baseline radiomics and DL models for the prognosis of lung adenocarcinomas were developed and tested using local (n = 617) cohort. The DL models were further tested in an external validation (n = 70) cohort. The local cohort was divided into training and test cohorts. A radiomics risk score (RRS) was developed using Cox-LASSO. Three pretrained DL networks derived from natural images were used to extract the DL features. The features were further guided using radiomics by retaining those DL features whose correlations with the radiomics features were high and Bonferroni-corrected p-values were low. The retained DL features were subject to a Cox-LASSO when constructing DL risk scores (DRS). The risk groups stratified by the RRS and DRS showed a significant difference in training, testing, and validation cohorts. The DL features were interpreted using existing radiomics features, and the texture features explained the DL features well. Cho et al. use a radiomics-guided deep-learning approach to model the prognosis of lung adenocarcinoma from CT scan data. This study demonstrates the utility of this technology as a predictive approach for stratifying clinical prognostic groups.
登录
查看更多内容
DOI：
10.1186/s13058-017-0846-1
发表时间：
2017-05-18
期刊：
Breast cancer research : BCR
影响因子：
--
作者：
Braman NM;Etesami M;Prasanna P;Dubchuk C;Gilmore H;Tiwari P;Plecha D;Madabhushi A
通讯作者：
Madabhushi A
影响因子：
5.9
作者：
Cho, Hwan-ho;Lee, Geewon;Park, Hyunjin
通讯作者：
Park, Hyunjin
影响因子：
9.8
作者：
Bakr S;Gevaert O;Echegaray S;Ayers K;Zhou M;Shafiq M;Zheng H;Benson JA;Zhang W;Leung ANC;Kadoch M;Hoang CD;Shrager J;Quon A;Rubin DL;Plevritis SK;Napel S
通讯作者：
Napel S
影响因子：
20.4
作者：
Goldstraw, Peter;Chansky, Kari;Bolejack, Vanessa
通讯作者：
Bolejack, Vanessa
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred