Deep learning-based noise reduction preserves quantitative MRI biomarkers in patients with brain tumors
Geoffroy Pouliquen1, Clément Debacker1, Sylvain Charron1
1Imaging department, GHU-Paris Psychiatrie et Neurosciences, Hôpital Sainte Anne, F-75014, Paris, France; Université Paris Cité, Institute of Psychiatry and Neuroscience (IPNP), INSERM U1266, 75014, Paris, France.
Abstract:
The use of relaxometry and Diffusion-Tensor Imaging sequences for brain tumor assessment is limited by their long acquisition time. We aim to test the effect of a denoising algorithm based on a Deep Learning Reconstruction (DLR) technique on quantitative MRI parameters while reducing scan time. In 22 consecutive patients with brain tumors, DLR applied to fast and noisy MR sequences preserves the mean values of quantitative parameters (Fractional anisotropy, mean Diffusivity, T1 and T2-relaxation time) and produces maps with higher structural similarity compared to long duration sequences. This could promote wider use of these biomarkers in clinical setting.
