Spherical Harmonic Residual Network for Diffusion Signal Harmonization
This addresses the challenge of scanner-induced variability in multi-site neuroscience studies, enabling more reliable quantitative measures, but it is incremental as it builds on existing deep learning approaches for signal harmonization.
The paper tackled the problem of measurement variability in diffusion MRI signals from different scanners, which increases variance in quantitative metrics, by proposing a deep learning residual network for harmonization without additional preprocessing. The results showed that harmonized signals were significantly more similar to ground truth compared to no harmonization and improved over another deep learning method, with the same effect demonstrated in derived metrics.
Diffusion imaging is an important method in the field of neuroscience, as it is sensitive to changes within the tissue microstructure of the human brain. However, a major challenge when using MRI to derive quantitative measures is that the use of different scanners, as used in multi-site group studies, introduces measurement variability. This can lead to an increased variance in quantitative metrics, even if the same brain is scanned. Contrary to the assumption that these characteristics are comparable and similar, small changes in these values are observed in many clinical studies, hence harmonization of the signals is essential. In this paper, we present a method that does not require additional preprocessing, such as segmentation or registration, and harmonizes the signal based on a deep learning residual network. For this purpose, a training database is required, which consist of the same subjects, scanned on different scanners. The results show that harmonized signals are significantly more similar to the ground truth signal compared to no harmonization, but also improve in comparison to another deep learning method. The same effect is also demonstrated in commonly used metrics derived from the diffusion MRI signal.