Integrating Multiomics Information in Deep Learning Architectures for Joint Actuarial Outcome Prediction in Non-Small Cell Lung Cancer Patients After Radiation Therapy.
Integrating Multiomics Information in Deep Learning Architectures for Joint Actuarial Outcome Prediction in Non-Small Cell Lung Cancer Patients After Radiation Therapy.
复制标题
在放射治疗后，在非小细胞肺癌患者中，将多组学信息整合在深度学习体系结构中。
DOI：
10.1016/j.ijrobp.2021.01.042
复制
发表时间：
2021-07-01
期刊：
影响因子：
--
通讯作者：
El Naqa I
中科院分区：
文献类型：
--
作者：
Cui S;Ten Haken RK;El Naqa I
提出了新的精算深度学习神经网络（ADNN）架构，用于联合预测放射治疗结果，即，放射性肺炎（RP）和局部控制（LC）在III期非小细胞肺癌（NSCLC）患者。与仅使用剂量信息的NTCP/TCP模型不同，我们提出的模型考虑了包括PET放射组学，细胞因子和miRNA在内的多组学信息之间的复杂相互作用。在精算预测中还利用了额外的事件发生时间信息。研究了三种架构：ADNN-DVH仅考虑剂量测定信息; ADNN-com集成多组学信息; ADNN-com联合RP 2（RP等级大于或等于2）和LC预测。在这些架构中，差分剂量体积直方图（DVH）被馈送到1D卷积神经网络（CNN）中，用于提取简化的表示。变分编码器（VAE）用于学习成像和生物数据的表示。将简化的表示输入Surv-Nets，通过将时间信息纳入指定的损失函数，独立或联合预测RP 2和LC的事件时间概率。模型在117例回顾性患者中进行了评估，并在25例新入组患者中进行了独立的前瞻性测试。327例患者的多机构RTOG 0617数据集用于外部验证。ADNN-DVH产生的RP 2预测交叉验证c指数[95% CI]为0.660 [0.630 - 0.690]，LC预测为0.727 [0.700-0.753]，优于RP 2的广义莱曼模型（0.613 [0.583-0.643]）和LC的广义对数逻辑模型（0.569 [0.545-0.594]）。独立的内部测试和外部验证得出了类似的结果。ADNN-com在交叉验证（CV）和独立内部测试中的性能甚至优于ADNN-DVH。此外，ADNN-com-joint产生了与ADNN-com相似的性能，实现了RP 2的联合预测，c指数为0.705 [0.676-0.734]，LC为0.740 [0.714-0.765]，RP 2和LC的联合预测的AU-FROC为0.729 [0.697-0.773]。集成多组学信息的新型深度学习架构在RP 2和LC的精算预测方面优于传统的TCP/NTCP模型。
Novel actuarial deep learning neural network (ADNN) architectures are proposed for joint prediction of radiotherapy outcomes, i.e., radiation pneumonitis (RP) and local control (LC) in stage III non-small-cell lung cancer (NSCLC) patients. Unlike NTCP/TCP models that use dosimetric information solely, our proposed models consider complex interactions among multi-omics information including PET radiomics, cytokines and miRNAs. Additional time-to-event information is also utilized in the actuarial prediction. Three architectures were investigated: ADNN-DVH considered dosimetric information only; ADNN-com integrated multi-omics information; ADNN-com-joint combined RP2 (RP grade greater or equal to 2) and LC prediction. In these architectures, differential dose volume histograms (DVHs) were fed into 1D convolutional neural networks (CNNs) for extracting reduced representations. Variational encoders (VAEs) were used to learn representations of imaging and biological data. Reduced representations were fed into Surv-Nets to predict time-to-event probabilities for RP2 and LC independently and jointly by incorporating time information into designated loss functions. Models were evaluated on 117 retrospective patients and were independently tested on 25 newly accrued patients prospectively. A multi-institutional RTOG0617 dataset of 327 patients was used for external validation. ADNN-DVH yielded cross-validated c-indexes [95% CIs] of 0.660 [0.630 −0.690] for RP2 prediction and 0.727 [0.700–0.753] for LC prediction, outperforming a generalized Lyman model for RP2 (0.613 [0.583–0.643]) and a generalized log-logistic model for LC (0.569 [0.545–0.594]). The independent internal test and external validation yielded similar results. ADNN-com achieved an even better performance than ADNN-DVH on both cross-validation (CV) and independent internal test. Furthermore, ADNN-com-joint which yielded similar performance as ADNN-com realized joint prediction with c-indexes of 0.705 [0.676–0.734] for RP2, 0.740 [0.714–0.765] for LC and achieved an AU-FROC 0.729 [0.697–0.773] for the joint prediction of RP2 and LC. Novel deep learning architectures that integrate multi-omics information outperformed traditional TCP/NTCP models in actuarial prediction of RP2 and LC.
登录
查看更多内容
DOI：
10.1109/trpms.2018.2884134
发表时间：
2019-03-01
影响因子：
4.4
作者：
Cui, Sunan;Luo, Yi;El Naqa, Issam
通讯作者：
El Naqa, Issam
影响因子：
51.1
作者：
Bradley, Jeffrey D.;Paulus, Rebecca;Komaki, Ritsuko;Masters, Gregory;Blumenschein, George;Schild, Steven;Bogart, Jeffrey;Hu, Chen;Forster, Kenneth;Magliocco, Anthony;Kavadi, Vivek;Garces, Yolanda I.;Narayan, Samir;Iyengar, Puneeth;Robinson, Cliff;Wynn, Raymond B.;Koprowski, Christopher;Meng, Joanne;Beitler, Jonathan;Gaur, Rakesh;Curran, Walter, Jr.;Choy, Hak
通讯作者：
Choy, Hak
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred
影响因子：
3.8
作者：
El Naqa, Issam;Ruan, Dan;Ten Haken, Randall
通讯作者：
Ten Haken, Randall
DOI：
10.1016/j.ijrobp.2004.03.036
发表时间：
2004-10-01
影响因子：
7
作者：
Hicks, RJ;Mac Manus, MP;Peters, LJ
通讯作者：
Peters, LJ