Contrast-Enhanced CT-Based Deep Learning and Habitat Radiomics for Analysing the Predictive Capability for Oral Squamous Cell Carcinoma

• Published in: International dental journal Vol. 75; no. 5; p. 100914
• Main Authors: Liu, Qilin, Liang, Zhuang, Qi, Xiaoshuang, Yang, Shuwen, Fu, Binyang, Dong, Hui
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.10.2025; Elsevier
• Subjects: Deep learning; Dentistry; Oral squamous cell carcinoma; Precision medicine; Radiomics; Scientific Research Report; CNN; DL; CECT; LNM-DL Model; IBSI; Radiomics; Deep learning; LNM-H Model; Precision medicine; LNM-C Model; LNM-Cli model; LBP; OSCC; ROC; AI; P-C Model; Oral squamous cell carcinoma; SLNB; ROI; GLCM; P-Cli Model; FCN; P-H Model; CLNM; P-DL Model; sentinel lymph node biopsy; Lymph Node Metastasis Deep Learning Model; oral squamous cell cancer; Lymph Node Metastasis Habitat Model; Pathological Typing Deep Learning Model; Pathological Typing Clinical Model; pathological typing combined model; artificial intelligence; cervical lymph node metastasis; Lymph Node Metastasis Clinical Model; fully connected neural network; local binary patterns; receiver operating characteristic; Lymph Node Metastasis Combined model; contrast-enhanced CT; gray-level co-occurrence matrix; regions of interest; convolutional neural network; Imaging Biomarker Standardisation Initiative; Pathological Typing Habitat Model
• DOI: 10.1016/j.identj.2025.100914
• ISSN: 0020-6539; 1875-595X

This study aims to explore a novel approach for predicting cervical lymph node metastasis (CLNM) and pathological subtypes in oral squamous cell carcinoma (OSCC) by comparing deep learning (DL) and habitat analysis models based on contrast-enhanced CT (CECT). A retrospective analysis was conducted using CECT images from patients diagnosed with OSCC via paraffin pathology at the Second Affiliated Hospital of Dalian Medical University. All patients underwent primary tumor resection and cervical lymph node dissection, with a total of 132 cases included. A DL model was developed by analysing regions of interest (ROIs) in the CECT images using a convolutional neural network (CNN). For habitat analysis, the ROI images were segmented into 3 regions using K-means clustering, and features were selected through a fully connected neural network (FCNN) to build the model. A separate clinical model was constructed based on nine clinical features, including age, gender, and tumor location. Using LNM and pathological subtypes as endpoints, the predictive performance of the clinical model, DL model, habitat analysis model, and a combined clinical + habitat model was evaluated using confusion matrices and receiver operating characteristic (ROC) curves. For LNM prediction, the combined clinical + habitat model achieved an area under the ROC curve (AUC) of 0.97. For pathological subtype prediction, the AUC was 0.96. The DL model yielded an AUC of 0.83 for LNM prediction and 0.91 for pathological subtype classification. The clinical model alone achieved an AUC of 0.94 for predicting LNM. The integrated habitat-clinical model demonstrates improved predictive performance. Combining habitat analysis with clinical features offers a promising approach for the prediction of oral cancer. The habitat-clinical integrated model may assist clinicians in performing accurate preoperative prognostic assessments in patients with oral cancer.