Gossamer: Scaling Image Processing and Reconstruction to Whole Brains
Marrett, K.; Moradi, K.; Park, C. S.; Yan, M.; Choi, C.; Zhu, M.; Akram, M.; Nanda, S.; Xue, Q.; Mun, H.-S.; Gutierrez, A. E.; Rudd, M.; Zingg, B.; Magat, G.; Wijaya, K.; Dong, H.; Yang, X. W.; Cong, J.
Show abstract
Neuronal reconstruction-a process that transforms image volumes into 3D geometries and skeletons of cells- bottlenecks the study of brain function, connectomics and pathology. Domain scientists need exact and complete segmentations to study subtle topological differences. Existing methods are diskbound, dense-access, coupled, single-threaded, algorithmically unscalable and require manual cropping of small windows and proofreading of skeletons due to low topological accuracy. Designing a data-intensive parallel solution suited to a neurons shape, topology and far-ranging connectivity is particularly challenging due to I/O and load-balance, yet by abstracting these vision tasks into strategically ordered specializations of search, we progressively lower memory by 4 orders of magnitude. This enables 1 mouse brain to be fully processed in-memory on a single server, at 67x the scale with 870x less memory while having 78% higher automated yield than APP2, the previous state of the art in performant reconstruction.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ShuTu: Open-Source Software for Efficient and Accurate Reconstruction of Dendritic Morphology 95%
- A scalable implementation of the recursive least-squares algorithm for training spiking neural networks 95%
- Systems Neuroscience Computing in Python (SyNCoPy): A Python Package for Large-scale Analysis of Electrophysiological Data 95%
Similar papers in this journal
- Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images 95%
- SAMCell: Generalized Label-Free Biological Cell Segmentation with Segment Anything 95%
- Deep Learning Classification of Lipid Droplets in Quantitative Phase Images 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.