Magnetic resonance imaging (MRI) is the preferred imaging modality for paediatric medical conditions due to its high spatial resolution, soft tissue characterisation and lack of ionising radiation. However, its main limitation is long scan durations due to the intrinsic relationship between SNR, resolution and scan time[1,2]. The project assesses the performance of GE Healthcare’s deep learning-based reconstruction method, Air Recon^TM DL (ARDL), for paediatric brain scanning. ARDL reduces image noise to the desired level: ‘Low’, ‘Medium’ or ‘High’, while improving perceived spatial resolution by reducing Gibbs artefact [1,2]. However, its performance is context-dependent [3-6], emphasising the need for local validation studies based on their intended clinical use [7-9]. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), spatial resolution and extent of Gibbs artefact were quantified in ARDL reconstructed images and compared to conventionally reconstructed images. In parallel, a qualitative review by radiologists evaluated the image sharpness, noisiness, lesion/feature detectability and artefact occurrence using a Likert scale.