Continuous longitudinal fetus brain atlas construction via implicit neural representation
This work addresses the issue of inaccurate brain developmental parameter estimation in fetal neuroscience, offering a more reliable tool for researchers, though it is incremental as it builds on existing atlas construction methods.
The authors tackled the problem of temporal inconsistency in existing fetal brain atlases, which are constructed at discrete time points, by proposing a multi-stage deep-learning framework using implicit neural representation to create a continuous and noise-free 4D atlas; experimental results on two public datasets showed significant improvement in temporal consistency while maintaining good structural representation.
Longitudinal fetal brain atlas is a powerful tool for understanding and characterizing the complex process of fetus brain development. Existing fetus brain atlases are typically constructed by averaged brain images on discrete time points independently over time. Due to the differences in onto-genetic trends among samples at different time points, the resulting atlases suffer from temporal inconsistency, which may lead to estimating error of the brain developmental characteristic parameters along the timeline. To this end, we proposed a multi-stage deep-learning framework to tackle the time inconsistency issue as a 4D (3D brain volume + 1D age) image data denoising task. Using implicit neural representation, we construct a continuous and noise-free longitudinal fetus brain atlas as a function of the 4D spatial-temporal coordinate. Experimental results on two public fetal brain atlases (CRL and FBA-Chinese atlases) show that the proposed method can significantly improve the atlas temporal consistency while maintaining good fetus brain structure representation. In addition, the continuous longitudinal fetus brain atlases can also be extensively applied to generate finer 4D atlases in both spatial and temporal resolution.