Multi-Scale Modeling of Neural Structure in X-Ray Imagery

Aishwarya H. Balwani, Joseph D. Miano, Ran Liu, Lindsey Kitchell, Judy A. Prasad, Erik C. Johnson, William R. Gray Roncal, Eva L. Dyer

Abstract

Methods for resolving the brain’s microstructure are rapidly improving, allowing us to image large brain volumes at high resolutions. As a result, the interrogation of samples spanning multiple diversified brain regions is becoming increasingly common. Understanding these samples often requires multi-scale processing: segmentation of the detailed microstructure and large-scale modelling of the macrostructure. Current brain mapping algorithms often analyze data only at a single scale, and optimization for each scale occurs independently, potentially limiting the consistency, performance, and interpretability. In this work we introduce a deep learning framework for segmentation of brain structure at multiple scales. We leverage a modified U-Net architecture with a multi-task learning objective and unsupervised pre-training to simultaneously model both the micro and macro architecture of the brain. We successfully apply our methods to a heterogeneous, three-dimensional, X-ray micro-CT dataset spanning multiple regions in the mouse brain, and show that our approach consistently outperforms another multi-task architecture, and is competitive with strong single-task baselines at both scales.
BibTeX
@inproceedings{balwani2021multi,
  author = {Aishwarya H. Balwani and Joseph D. Miano and Ran Liu and Lindsey Kitchell and Judy A. Prasad and Erik C. Johnson and William R. Gray Roncal and Eva L. Dyer},
  title = {{Multi-Scale Modeling of Neural Structure in X-Ray Imagery}},
  booktitle = {ICIP},
  year = {2021},
  doi = {10.1109/icip42928.2021.9506174},
}

Loading related content...

Figure