Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image.

PURPOSE: To introduce multilevel binomial logistic prediction model-based computer-aided diagnostic (CAD) method of small solitary pulmonary nodules (SPNs) diagnosis by combining patient and image characteristics by textural features of CT image. MATERIALS AND METHODS: Describe fourteen gray level co-occurrence matrix textural features obtained from 2171 benign and malignant small solitary pulmonary nodules, which belongs to 185 patients. Multilevel binomial logistic model is applied to gain these initial insights. RESULTS: Five texture features, including Inertia, Entropy, Correlation, Difference-mean, Sum-Entropy, and age of patients own aggregating character on patient-level, which are statistically different (P<0.05) between benign and malignant small solitary pulmonary nodules. CONCLUSION: Some gray level co-occurrence matrix textural features are efficiently descriptive features of CT image of small solitary pulmonary nodules, which can profit diagnosis of earlier period lung cancer if combined patient-level characteristics to some extent.