Introduction: The incidence of occult cervical lymph node metastases (OCLNM) is reported to be 20–30% in early-stage oral cancer and oropharyngeal cancer. There is a lack of an accurate diagnostic method to predict occult lymph node metastasis and to help surgeons make precise treatment decisions. Aim: To construct and evaluate a preoperative diagnostic method to predict OCLNM in early-stage oral and oropharyngeal squamous cell carcinoma (OC and OP SCC) based on deep learning features (DLFs) and radiomics features. Methods: A total of 319 patients diagnosed with early-stage OC or OP SCC were retrospectively enrolled and divided into training, test and external validation sets. Traditional radiomics features and DLFs were extracted from their MRI images. The least absolute shrinkage and selection operator (LASSO) analysis was employed to identify the most valuable features. Prediction models for OCLNM were developed using radiomics features and DLFs. The effectiveness of the models and their clinical applicability were evaluated using the area under the curve (AUC), decision curve analysis (DCA), and survival analysis. Results: Seventeen prediction models were constructed. The Resnet50 deep learning (DL) model based on the combination of radiomics and DL features achieves the optimal performance, with AUC values of 0.928 (95% CI: 0.881–0.975), 0.878 (95% CI: 0.766–0.990), 0.796 (95% CI: 0.666–0.927), and 0.834 (95% CI: 0.721–0.947) in the training, test, external validation set1, and external validation set2, respectively. Moreover, the Resnet50 model has great prediction value of prognosis in patients with early-stage OC and OP SCC. Conclusion: The proposed MRI-based Resnet50 DL model demonstrated high capability in diagnosis of OCLNM and prognosis prediction in the early-stage OC and OP SCC. The Resnet50 model could help refine the clinical diagnosis and treatment of the early-stage OC and OP SCC.

M2 tumor-associated macrophages (TAMs) have been a well-established promoter of oral squamous cell carcinoma (OSCC) progression. However, the mechanisms of M2 TAMs promoting OSCC metastasis have not been elucidated clearly. This study illustrated the regulatory mechanisms in which M2 TAMs enhance OSCC malignancy in a novel point of view. In this study, mass spectrometry was utilized to analyze the proteins expression profile of M2 type monocyte-derived macrophages (MDMs-M2), whose results revealed the high expression of G3BP1 in M2 macrophages. RNA sequencing analyzed the genome-wide changes upon G3BP1 knockdown in MDMs-M2 and identified that CCL13 was the most significantly downregulated inflammatory cytokines in MDMs-M2. Co-immunoprecipitation and qualitative mass spectrometry were used to identify the proteins that directly interacted with endogenous G3BP1 in MDMs-M2. Elevated stress granule (SG) formation in stressed M2 TAMs enhanced the expression of CCL13, which promoted OSCC metastasis both in vitro and in vivo. For mechanisms, we demonstrated SG formation improved DDX3Y/hnRNPF-mediated CCL13 mRNA stability, thus enhancing CCL13 expression and promoting OSCC metastasis. Collectively, our findings demonstrated for the first time the roles of CCL13 in improving OSCC metastasis and illustrated the molecular mechanisms of CCL13 expression regulated by SG, indicating that the SG-CCL13 axis can be the potential targets for TAM-navigated tumor therapy.