NCT06366906

10-year Retrospective Study of Oral and Maxillofacial Squamous Cell Carcinoma

Clinicopathological and Prognostic Analysis of Oral and Maxillofacial Squamous Cell Carcinoma: a Single-center 10-year Retrospective Study

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 319 (actual)
• Sponsor: Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University · Academic / Other
• Sex: All
• Age: —
• Healthy volunteers: Not accepted

Summary

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 occult lymph node metastasis (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.

Conditions

• HNSCC
• AI
• Radiomic
• MRI

Interventions

Type	Name	Description
DIAGNOSTIC_TEST	The Resnet50 deep learning (DL) model	The predictive capability of the above Resnet50 deep learning (DL) model was validated in the test set. Based on the AUC and ACC, the best prediction model was identified. To explore the robust of the selected model, ROC analysis was performed the in the external validation set. Moreover, the Log-rank test was applied to evaluate the prognostic value of the model.

Timeline

• Start date: 2023-05-10
• Primary completion: 2024-02-10
• Completion: 2024-02-10
• First posted: 2024-04-16
• Last updated: 2024-04-16

Locations

2 sites across 1 country: China