In lung cancer patients, radiotherapy is associated with a increased risk of local relapse (LR) when compared with surgery but with a preferable toxicity profile. The KEAP1/NFE2L2 mutational status (Mut_KEAP1/NFE2L2) is significantly correlated with LR in patients treated with radiotherapy but is rarely available. Prediction of Mut_KEAP1/NFE2L2 with noninvasive modalities could help to further personalize each therapeutic strategy. Methods: Based on a public cohort of 770 patients, model RNA (M-RNA) was first developed using continuous gene expression levels to predict Mut_KEAP1/NFE2L2, resulting in a binary output. The model PET/CT (M-PET/CT) was then built to predict M-RNA binary output using PET/CT-extracted radiomics features. M-PET/CT was validated on an external cohort of 151 patients treated with curative volumetric modulated arc radiotherapy. Each model was built, internally validated, and evaluated on a separate cohort using a multilayer perceptron network approach. Results: The M-RNA resulted in a C statistic of 0.82 in the testing cohort. With a training cohort of 101 patients, the retained M-PET/CT resulted in an area under the curve of 0.90 (P < 0.001). With a probability threshold of 20% applied to the testing cohort, M-PET/CT achieved a C statistic of 0.7. The same radiomics model was validated on the volumetric modulated arc radiotherapy cohort as patients were significantly stratified on the basis of their risk of LR with a hazard ratio of 2.61 (P = 0.02). Conclusion: Our approach enables the prediction of Mut_KEAP1/NFE2L2 using PET/CT-extracted radiomics features and efficiently classifies patients at risk of LR in an external cohort treated with radiotherapy.

在肺癌患者中，与手术相比，放疗会增加局部复发 (LR) 的风险，但具有更好的毒性特征。 KEAP1/NFE2L2 突变状态 (Mut _KEAP1/NFE2L2 ) 与接受放疗的患者的 LR 显着相关，但很少可用。通过无创方式预测 Mut _KEAP1/NFE2L2有助于进一步个性化每种治疗策略。方法：基于 770 名患者的公共队列，首先使用连续基因表达水平开发模型 RNA (M-RNA) 来预测 Mut _KEAP1/NFE2L2，从而产生二进制输出。然后建立模型 PET/CT (M-PET/CT) 以使用 PET/CT 提取的放射组学特征来预测 M-RNA 二元输出。 M-PET/CT 在由 151 名接受治疗性容积调制弧放疗的患者组成的外部队列中得到验证。每个模型都是使用多层感知器网络方法在单独的队列中构建、内部验证和评估的。结果：测试队列中 M-RNA 的 C 统计值为 0.82。对于 101 名患者的训练队列，保留的 M-PET/CT 导致曲线下面积为 0.90 ( P < 0.001)。将 20% 的概率阈值应用于测试队列时，M-PET/CT 的 C 统计值为 0.7。相同的放射组学模型在体积调制弧放疗队列中得到了验证，因为患者根据 LR 风险进行了显着分层，风险比为 2.61（P = 0.02）。结论：我们的方法能够使用 PET/CT 提取的放射组学特征来预测 Mut _KEAP1/NFE2L2，并有效地对接受放射治疗的外部队列中存在 LR 风险的患者进行分类。