Constrained self-supervised method with temporal ensembling for fiber bundle detection on anatomic tracing data
This work addresses a domain-specific problem in neuroscience for researchers analyzing brain circuitry, offering an incremental improvement with constrained self-supervised learning for fiber bundle segmentation.
The authors tackled automated fiber bundle detection in anatomic tracing data from macaque brains, which is challenging due to distortions and noise, by proposing a deep learning method with self-supervised and semi-supervised techniques incorporating anatomy-based constraints. Their method achieved a true positive rate of approximately 0.90 on unseen data.
Anatomic tracing data provides detailed information on brain circuitry essential for addressing some of the common errors in diffusion MRI tractography. However, automated detection of fiber bundles on tracing data is challenging due to sectioning distortions, presence of noise and artifacts and intensity/contrast variations. In this work, we propose a deep learning method with a self-supervised loss function that takes anatomy-based constraints into account for accurate segmentation of fiber bundles on the tracer sections from macaque brains. Also, given the limited availability of manual labels, we use a semi-supervised training technique for efficiently using unlabeled data to improve the performance, and location constraints for further reduction of false positives. Evaluation of our method on unseen sections from a different macaque yields promising results with a true positive rate of ~0.90. The code for our method is available at https://github.com/v-sundaresan/fiberbundle_seg_tracing.