Brain-computer interface (BCI) aims to translate human intention into a control output signal. In motor-imaginary (MI) BCI, the imagination of movement modifies the cortex brain activity. Such activities are then used in pattern recognition to identify certain movement classes. MI-BCI could be used to enhance the life quality of physically impaired subjects. Several challenges exist in MI-BCI, including selecting appropriate channels, usually linked with a suitable classifier choice. The entire procedure must be real time in practical applications. A variety of channel selection and classification methods were used for MI-BCI in the literature. Also, hybrid machine learning (ML) and deep learning (DL) methods were used in the literature. In this chapter, different channel selection, ML and DL methods, validation frameworks, and performance indices of EEG-based methods were investigated. Three hundred and twenty-two papers published between January 2000 and March 2021 were analyzed in this systematic review. Specific challenges and future directions were then provided.