Differentiation of Cervical Cancer and Pathological Type Using Quantitative Microstructural Parameters of MRI cytometry

Motivation: Preoperative differentiation between cervical intraepithelial neoplasia (CIN) and cervical cancer (CC), along with identifying pathological type of CC, is crucial for guiding subsequent treatment. Goal(s): To evaluate MRI cytometry-derived microstructural parameters for noninvasive differentiation of cervical lesions and prediction pathological type of CC. Approach: MRI cytometry extracted microstructural parameters, including diameter, intracellular volume fraction (Vin), cellularity and extracellular diffusivity (Dex). Diagnostic accuracy was assessed using using one-way ANOVA, linear regression, AUC, sensitivity and specificity. Results: Microstructural parameters showed significant differences and high diagnostic performance in identifying CIN, cervical squamous carcinoma (CSC), and adenocarcinoma (CA) groups. Impact: For the first time, MRI cytometry demonstrated the feasibility and superior diagnostic capability in noninvasively differentiating cervical intraepithelial neoplasia (CIN) from cervical cancer (CC)and identifying CC pathological types.