Deep learning-based noise reduction preserves quantitative MRI biomarkers in patients with brain tumors

Geoffroy Pouliquen; Clément Debacker; Sylvain Charron; Alexandre Roux; Corentin Provost; Joseph Benzakoun; Wolter de Graaf; Valentin Prevost; Johan Pallud; Catherine Oppenheim

doi:10.1016/j.neurad.2023.10.008

Deep learning-based noise reduction preserves quantitative MRI biomarkers in patients with brain tumors

J Neuroradiol. 2023 Oct 28:S0150-9861(23)00260-2. doi: 10.1016/j.neurad.2023.10.008. Online ahead of print.

Affiliations

¹ Imaging 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.
² Université Paris Cité, Institute of Psychiatry and Neuroscience (IPNP), INSERM U1266, 75014, Paris, France; Neurosurgery department, GHU-Paris Psychiatrie et Neurosciences, Hôpital Sainte Anne, F-75014, Paris, France.
³ Canon Medical Systems Europe B.V., 2718, RP, The Netherlands.
⁴ Canon Medical Systems Corporation, Otawara, Japan.
⁵ Imaging 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. Electronic address: [email protected].

PMID: 39492549
DOI: 10.1016/j.neurad.2023.10.008

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.

Keywords: Brain tumors; Deep learning; Denoising; Diffusion tensor imaging; Magnetic Resonance Imaging; Relaxometry.