Susceptibility DistortionSusceptibility distortion Correction of Diffusion MRIDiffusion MRI with a single Phase-EncodingPhase Encoding Direction

Diffusion MRI (dMRI)DMRIDiffusion MRI is a valuable tool to map brain microstructure and connectivity by analyzing water molecule diffusion in tissue. However, acquiring dMRIDMRI data requires to capture multiple 3D brain volumes in a short time, often leading to trade-offs in image quality. One challenging artifact is susceptibility-induced distortionSusceptibility distortion, which introduces significant geometric and intensity deformations. Traditional correction methods, such as topupTopup, rely on having access to blip-upBlip-up and blip-downBlip-down image pairs, limiting their applicability to retrospective data acquired with a single phase encodingPhase Encoding direction. In this work, we propose a deep learning-basedDeep learning approach to correct susceptibility distortionsSusceptibility distortion using only a single acquisition (either blip-upBlip-up or blip-downBlip-down), eliminating the need for paired acquisitions. Experimental results show that our method achieves performance comparable to topupTopup, demonstrating its potential as an efficient and practical alternative for susceptibility distortion correction in dMRIDMRI.