Alma Lennartsson presents her master’s thesis Anisotropic to Isotropic Reconstruction of Infant Brain MRI using Deep Learning Friday 23 January at 10:15 in MH:Sigma

Abstract:

Brain magnetic resonance imaging (MRI) is an important tool for diagnosing neurological diseases and is widely used in neurological research to study brain development and aging. However, acquiring high-resolution (HR) isotropic MRI is time- and resource-consuming, which often leads to acquisition of low-resolution (LR) anisotropic MRI instead. In recent years, deep learning has shown promising advancements in synthesizing isotropic MRI from anisotropic scans. Consequently, this thesis aims to construct a deep learning pipeline specifically optimized or anisotropic to isotropic reconstruction of T2-weighted (T2w) infant brain MRI. The proposed approach is a supervised, 3D patch-based residual U-Net architecture, which has been carefully optimized in terms of network depth, patch size, input channels, residual units, and data augmentation. The final model outperforms the interpolation-based benchmark, both with visual assessment and quantitative measures. However, the network presents limited generalization to unseen types of LR anisotropic input. To address this limitation, augmentation is introduced by adding more types of LR anisotropic MRI to the training data. This shows promising results and can, with further development, be utilized for research use, and eventually in clinical practice.

Examiner: 
Mikael Nilsson, Centre for Mathematical Sciences, Lund University

Supervisors:
Kalle Åström, Centre for Mathematical Sciences, Lund University
Jacob Vogel, Dept of Clinical Sciences, Lund University
Linda Karlsson, Dept of Clinical Sciences, Lund University