CT imaging of thyroid cartilage invasion in glottic laryngeal cancer: correlation of traditional semiotics and texture analysis with histopathology.

OBJECTIVES

To evaluate the diagnostic performance of contrast-enhanced CT and CT-based radiomics in detecting thyroid cartilage invasion in patients with laryngeal squamous cell carcinoma (LSCC), using histopathology as the reference standard.

METHOD: This retrospective single center study included 60 patients with histologically confirmed glottic LSCC who underwent pre-treatment contrast-enhanced CT between January 2015 and December 2025. Two head and neck radiologists independently assessed thyroid cartilage invasion based on established imaging criteria. Texture analysis was performed on manually segmented thyroid cartilage volumes, extracting 107 textural features. Feature selection and model construction were performed using LASSO logistic regression, whereas diagnostic performance was evaluated using receiver operating characteristic (ROC) curve.

RESULTS

CT-based radiologist assessment showed moderate diagnostic performance in detecting thyroid cartilage invasion, with 63.3% sensitivity, 90.0% specificity and 76.7% accuracy (Cohen's κ = 0.534). Radiomics analysis identified shape-related and textural features as potential markers of cartilage invasion. The final radiomics model, incorporating "Shape_Maximum 2D Diameter Slice" and "glcm_Imc1," achieved an AUC of 0.73, 81% sensitivity, 55% specificity and 67% accuracy. While radiologist evaluation offered higher specificity, radiomics demonstrated greater sensitivity, particularly in detecting subtle early-stage infiltration.

CONCLUSIONS

Radiologist assessment and radiomics demonstrated different diagnostic strengths in the evaluation of thyroid cartilage invasion in glottic cancer. Although radiomics alone was not sufficient to guide clinical decision-making, the present findings suggested that it may provide additional quantitative information beyond visual assessment. Further studies will be needed to determine whether integration of radiomic features into the diagnostic workflow can improve the assessment of thyroid cartilage invasion.