Classification of active and non-active MS lesions using various machine learning models

Introduction: Gadolinium-based T۱-weighted MRI sequence is the gold standard for the detection of active multiple sclerosis (MS) lesions. The performance of machine learning (ML) models in the classification of active and non-active MS lesions from the non-contrasted T۲-weighted MRI images has been investigated in this study.Methods: ۱۰۸ Features of ۷۵ active and ۱۰۰ non-active MS lesions was extracted by using Segment Editor and Radiomics modules of ۳D slicer software. ۱۸ ML models have been made using the ۵-fold cross-validation method and each model with its special optimized parameters has been trained by using the training-validation data sets. Performance models in test data set has been evaluated by metric parameters of accuracy, precision, sensitivity, specificity, AUC, and F۱ score.Results:The highest values of accuracy (۹۱.۹%), precision (۹۵.۵%), sensitivity (۸۵%), specificity (۹۵.۸%), AUC (۹۴.۲%), and F۱ score (۸۹.۵%) have been seen in LogisticRegression model.Conclusion:The performance of ML models in the classification of active and non-active MS lesions was evaluated. The results of this study show that the LogesticRegression model is the best and reliable ML model for this purpose.