Brain MRI Segmentation Playground


Accurate brain segmentation is critical for many magnetic resonance imaging (MRI) analysis pipelines. Machine-learning-based brain MR image segmentation methods are among the state-of-the-art techniques for this task. Nevertheless, the segmentations produced by machine learning models often degrade in the presence of expected domain shifts between the test and train sets data distributions. These domain shifts are expected due to several factors, such as scanner hardware and software differences, technology evolution over time, and differences in MRI acquisition parameters. Domain adaptation (DA) methods can make machine learning models more robust to these domain shifts.

In this brain MRI segmentation playground, part of the Calgary-Campinas (CC) dataset initiative, we investigate DA techniques for brain MR image segmentation using the 3 T portion of the CC-359 dataset. These data were collected across sites with scanners from different vendors (Philips, Siemens, and General Electric) and different magnetic fields (1.5 T and 3 T).

Currently, our playground supports the following segmentation tasks:

  • Skull-Stripping (SS)

  • White-Matter (WM), Gray-Matter (WM), and Cerebrospinal Fluid (CSF) segmentation

  • Hippocampus segmentation (TBD soon)

We expect to expand our playground to include other brain structures in the future.

The details about this DA playground will be released after the manuscript is peer-reviewed and accepted for publication.