探讨多模态深度学习放射组学（MDLR）模型在预测实体I期非小细胞肺癌（NSCLC）术后进展风险状态中的应用价值。共459例经组织学证实的实体I期NSCLC患者，对2014年1月至2019年9月期间在我院接受手术切除的患者进行回顾性分析。在另一个医疗中心，104 名患者根据相同的标准作为外部验证队列进行了审查。对进展组和非进展组的临床病理特征和主观CT表现进行单因素分析。将表现出显着差异的临床病理特征和主观CT表现作为极限学习机（ELM）分类器的输入变量来构建临床模型。我们使用迁移学习策略训练ResNet18模型，使用该模型从所有CT图像中提取深度学习特征，然后使用ELM分类器对深度学习特征进行分类以获得深度学习签名（DLS）。构建了结合临床病理特征、主观CT表现和DLS的MDLR模型。通过曲线下面积（AUC）评价临床模型、DLS模型和MDLR模型的诊断效率。单变量分析表明，大小（p = 0.004）、神经元特异性烯醇化酶（NSE）（p = 0.03）、碳水化合物抗原19 - 9 (CA199) (p = 0.003)和病理分期(p = 0.027)与实体I期NSCLC术后进展显着相关。因此，将这些临床特征纳入临床模型，以预测术后实体期 NSCLC 患者的进展风险。总共选择了 294 个非零系数的深度学习特征。进展组的DLS为(0.721±0.371)，高于非进展组的(0.113±0.350)(p<0.001)。大小、NSE、CA199、病理分期和DLS的结合在区分术后进展状态方面表现出优越的性能。 MDLR模型的AUC为0.885（95%置信区间[CI]：0.842-0.927），高于临床模型（0.675（95% CI：0.599-0.752））和DLS模型（0.882（95% CI） ：0.835-0.929））。 DeLong检验和曲线分析判定结果表明MDLR模型是最具预测性和临床实用性的模型。MDLR模型可以有效预测I期实体NSCLC术后进展风险，有助于治疗和随访I 期 NSCLC 实体瘤患者。© 2024。作者。

To explore the application value of a multimodal deep learning radiomics (MDLR) model in predicting the risk status of postoperative progression in solid stage I non-small cell lung cancer (NSCLC).A total of 459 patients with histologically confirmed solid stage I NSCLC who underwent surgical resection in our institution from January 2014 to September 2019 were reviewed retrospectively. At another medical center, 104 patients were reviewed as an external validation cohort according to the same criteria. A univariate analysis was conducted on the clinicopathological characteristics and subjective CT findings of the progression and non-progression groups. The clinicopathological characteristics and subjective CT findings that exhibited significant differences were used as input variables for the extreme learning machine (ELM) classifier to construct the clinical model. We used the transfer learning strategy to train the ResNet18 model, used the model to extract deep learning features from all CT images, and then used the ELM classifier to classify the deep learning features to obtain the deep learning signature (DLS). A MDLR model incorporating clinicopathological characteristics, subjective CT findings and DLS was constructed. The diagnostic efficiencies of the clinical model, DLS model and MDLR model were evaluated by the area under the curve (AUC).Univariate analysis indicated that size (p = 0.004), neuron-specific enolase (NSE) (p = 0.03), carbohydrate antigen 19 - 9 (CA199) (p = 0.003), and pathological stage (p = 0.027) were significantly associated with the progression of solid stage I NSCLC after surgery. Therefore, these clinical characteristics were incorporated into the clinical model to predict the risk of progression in postoperative solid-stage NSCLC patients. A total of 294 deep learning features with nonzero coefficients were selected. The DLS in the progressive group was (0.721 ± 0.371), which was higher than that in the nonprogressive group (0.113 ± 0.350) (p < 0.001). The combination of size、NSE、CA199、pathological stage and DLS demonstrated the superior performance in differentiating postoperative progression status. The AUC of the MDLR model was 0.885 (95% confidence interval [CI]: 0.842-0.927), higher than that of the clinical model (0.675 (95% CI: 0.599-0.752)) and DLS model (0.882 (95% CI: 0.835-0.929)). The DeLong test and decision in curve analysis revealed that the MDLR model was the most predictive and clinically useful model.MDLR model is effective in predicting the risk of postoperative progression of solid stage I NSCLC, and it is helpful for the treatment and follow-up of solid stage I NSCLC patients.© 2024. The Author(s).