Abstract：
OBJECTIVE: Personalized treatments such as targeted therapy and immunotherapy have revolutionized the predominantly therapeutic paradigm for non-small cell lung cancer (NSCLC). However, these treatment decisions require the determination of targetable genomic and molecular alterations through invasive genetic or immunohistochemistry (IHC) tests. Numerous previous studies have demonstrated that artificial intelligence can accurately predict the single-gene status of tumors based on radiologic imaging, but few studies have achieved the simultaneous evaluation of multiple genes to reflect more realistic clinical scenarios.
METHODS: We proposed a multi-label multi-task deep learning (MMDL) system for non-invasively predicting actionable NSCLC mutations and PD-L1 expression utilizing routinely acquired computed tomography (CT) images. This radiogenomic system integrated transformer-based deep learning features and radiomic features of CT volumes from 1096 NSCLC patients based on next-generation sequencing (NGS) and IHC tests.
RESULTS: For each task cohort, we randomly split the corresponding dataset into training (80%), validation (10%), and testing (10%) subsets. The area under the receiver operating characteristic curves (AUCs) of the MMDL system achieved 0.862 (95% confidence interval (CI), 0.758-0.969) for discrimination of a panel of 8 mutated genes, including EGFR, ALK, ERBB2, BRAF, MET, ROS1, RET and KRAS, 0.856 (95% CI, 0.663-0.948) for identification of a 10-molecular status panel (previous 8 genes plus TP53 and PD-L1); and 0.868 (95% CI, 0.641-0.972) for classifying EGFR / PD-L1 subtype, respectively.
CONCLUSIONS: To the best of our knowledge, this study is the first deep learning system to simultaneously analyze 10 molecular expressions, which might be utilized as an assistive tool in conjunction with or in lieu of ancillary testing to support precision treatment options.
METHODS: We proposed a multi-label multi-task deep learning (MMDL) system for non-invasively predicting actionable NSCLC mutations and PD-L1 expression utilizing routinely acquired computed tomography (CT) images. This radiogenomic system integrated transformer-based deep learning features and radiomic features of CT volumes from 1096 NSCLC patients based on next-generation sequencing (NGS) and IHC tests.
RESULTS: For each task cohort, we randomly split the corresponding dataset into training (80%), validation (10%), and testing (10%) subsets. The area under the receiver operating characteristic curves (AUCs) of the MMDL system achieved 0.862 (95% confidence interval (CI), 0.758-0.969) for discrimination of a panel of 8 mutated genes, including EGFR, ALK, ERBB2, BRAF, MET, ROS1, RET and KRAS, 0.856 (95% CI, 0.663-0.948) for identification of a 10-molecular status panel (previous 8 genes plus TP53 and PD-L1); and 0.868 (95% CI, 0.641-0.972) for classifying EGFR / PD-L1 subtype, respectively.
CONCLUSIONS: To the best of our knowledge, this study is the first deep learning system to simultaneously analyze 10 molecular expressions, which might be utilized as an assistive tool in conjunction with or in lieu of ancillary testing to support precision treatment options.
摘要：
目的：个性化治疗如靶向治疗和免疫治疗已经彻底改变了非小细胞肺癌（NSCLC）的主要治疗模式。然而,这些治疗决定需要通过侵袭性遗传学或免疫组织化学(IHC)试验确定可靶向的基因组和分子改变.此前的大量研究表明，人工智能可以基于放射影像学准确预测肿瘤的单基因状态，但很少有研究能同时评估多个基因以反映更真实的临床情况.
方法：我们提出了一种多标签多任务深度学习（MMDL）系统，用于利用常规获取的计算机断层扫描（CT）图像非侵入性预测可操作的NSCLC突变和PD-L1表达。该放射学系统基于下一代测序（NGS）和IHC测试，整合了来自1096例NSCLC患者的基于变压器的深度学习特征和CT体积的放射学特征。
结果：对于每个任务队列，我们将相应的数据集随机分成训练(80%)，验证(10%)，和测试（10％）子集。MMDL系统的接收器工作特性曲线下面积（AUC）达到0.862（95％置信区间（CI），0.758-0.969）用于区分一组8个突变基因，包括EGFR,ALK,ERBB2,BRAF,MET,ROS1RET和KRAS,0.856（95％CI，0.663-0.948）用于鉴定10分子状态组（先前的8个基因加上TP53和PD-L1）；0.868（95％CI，0.641-0.972）用于分类EGFR/PD-L1亚型，分别。
结论：据我们所知，这项研究是第一个同时分析10个分子表达的深度学习系统，它可以用作辅助工具，与辅助测试一起使用或代替辅助测试，以支持精密治疗选项。
方法：我们提出了一种多标签多任务深度学习（MMDL）系统，用于利用常规获取的计算机断层扫描（CT）图像非侵入性预测可操作的NSCLC突变和PD-L1表达。该放射学系统基于下一代测序（NGS）和IHC测试，整合了来自1096例NSCLC患者的基于变压器的深度学习特征和CT体积的放射学特征。
结果：对于每个任务队列，我们将相应的数据集随机分成训练(80%)，验证(10%)，和测试（10％）子集。MMDL系统的接收器工作特性曲线下面积（AUC）达到0.862（95％置信区间（CI），0.758-0.969）用于区分一组8个突变基因，包括EGFR,ALK,ERBB2,BRAF,MET,ROS1RET和KRAS,0.856（95％CI，0.663-0.948）用于鉴定10分子状态组（先前的8个基因加上TP53和PD-L1）；0.868（95％CI，0.641-0.972）用于分类EGFR/PD-L1亚型，分别。
结论：据我们所知，这项研究是第一个同时分析10个分子表达的深度学习系统，它可以用作辅助工具，与辅助测试一起使用或代替辅助测试，以支持精密治疗选项。
