The invention relates to a magnetic resonance imaging system, the magnetic resonance imaging system (100) comprising: - a memory (134, 136) storing machine executable instructions (160, 162, 164), pulse sequence commands (140) and a first machine learning model (146) comprising a first deep learning network (502), wherein the pulse sequence commands (140) are configured for controlling the magnetic resonance imaging system (100) to acquire a set of magnetic resonance imaging data, wherein the first machine learning model (146) comprises a first input and a first output, - a processor, wherein an execution of the machine executable instructions (160, 162, 164) causes the processor (130) to control the magnetic resonance imaging system (100) to repeatedly perform an acquisition and analysis process comprising: - acquiring a dataset (142.1,..., 142.N) comprising a subset of the set of magnetic resonance imaging data from an imaging zone (108) of the magnetic resonance imaging system (100) according to the pulse sequence commands (140), - providing the dataset (142.1,..., 142.N) to the first input of the first machine learning model (146), I - n response of the providing, receiving a prediction (148, 502) of a motion artifact level of the acquired magnetic resonance imaging data from the first output of the first machine learning model (146), the motion artifact level characterizing a number and/or extent of motion artifacts present in the acquired magnetic resonance imaging data.20L'invention concerne un système d'imagerie par résonance magnétique, le système d'imagerie par résonance magnétique (100) comprenant :- une mémoire (134, 136) stockant des instructions exécutables par machine (160, 162, 164), des commandes de séquence d'impulsions (140) et un premier modèle d'apprentissage machine (146) comprenant un premier réseau d'apprentissage profond (502), les commandes de séquence d'impulsions (140) étant configurées pour commander le système d'imagerie par résonance
