Computerized Tomography Texture Analysis in the Differential Diagnosis of Intracranial Epidermoid and Arachnoid Cysts

Purpose: This study evaluated the differences between arachnoid and epidermoid cysts in computerized tomography (CT) texture analysis (TA). Material methods: The included 12 patients with intracranial 26 who were diagnosed diffusion-weighted magnetic resonance imaging (DW-MRI) had undergone an unenhanced CT examination before treatment. LIFEx application software was used to obtain features. Eighty-two features from 38 lesions automatically calculated for each lesion. Shapiro-Wilk test normality of scores, Mann-Whitney U Test difference groups. Receiver operating characteristic (ROC) curves multivariate logistic regression modeling examined parameters' diagnostic performances. Results: median age 53 years (range: 19-88 years). parameters first order: gray-level co-occurrence matrix (GLCM), run length (GLRLM), neighbor gray-tone (NGTDM), size zone (GLSZM) There a statistically significant cyst variables compacity, compactness 1, 2, sphericity, asphericity, sum average, coarseness, low (p<0.05). According multiple model, it determined that average GLCM group (B=-0.11; p=0.015), coarseness (B= 869.5; p=0.044) NGTDM group, morphological sphericity (B=24.18; p=0.047) radiomics increased probability diagnosis. classification table sensitivity rate found be 83%, specificity 96%. Therefore, accurate model 92%. Conclusion: TA is method can applied high accuracy differential diagnosis cysts, especially cannot undergo MRI examination.