Abstract
BACKGROUND: Occult pleural dissemination (PD) in non-small cell lung cancer (NSCLC) patients is likely to be missed on computed tomography (CT) scans, associated with poor survival, and generally contraindicated for radical surgery. This study aimed to develop and compare the performance of radiomics-based machine learning (ML), deep learning (DL), and fusion models to preoperatively identify occult PD in NSCLC patients. MATERIALS AND METHODS: A total of 326 NSCLC patients from three Chinese high-volume medical centers (2016-2023) were retrospectively collected and divided into training (n = 216), internal test (n = 54), and external test (n = 56) cohorts. Ten radiomics-based ML models and eight DL models were trained using CT images at the maximum cross-sectional slice of the primary tumor. Moreover, another two fusion models (prefusion and postfusion) were developed using feature-based and decision-based methods. The receiver operating characteristic curve (ROC) and area under the curve (AUC) were mainly used to compare the predictive performance of the models. RESULTS: The GBM (AUC: 0.821) and DenseNet121 (AUC: 0.764) models achieved the highest AUC among ML and DL models in the external test cohorts, respectively. The postfusion model, integrating the output probabilities from GBM and DenseNet121 models, showed superior performance (AUC: 0.828-0.978) compared to the prefusion model (AUC: 0.817-0.877). Moreover, the postfusion model demonstrated the highest degree of sensitivity (82.1-97.2%) among all models across the three cohorts. CONCLUSIONS: The postfusion model, which integrates radiomics-based ML and DL models, can serve as a sensitive diagnostic tool to predict occult PD in NSCLC patients, thereby helping to avoid unnecessary surgeries.