Anatomics MLT, an AI tool for large scale quantification of ultrastructural traits
Brookhouse, A.; Ji, Y.; Knoblauch, J.; Gaburak, P.; Wager, B. M.; Lin, Z.; Kunz, H.-H.; Gebremedhin, A. M.; Pfister, H.; Peters, W. S.; Wei, D.; Knoblauch, M.
Show abstract
The ever increasing breadth of biological knowledge has led to recent efforts to combine information from various fields into cell- or tissue atlases. Anatomical features are the structural basis for such efforts, but unfortunately large scale analysis of subcellular anatomical traits is currently a missing feature. Similarly, small phenotypic alterations of organelle- or cell-specific anatomical traits, such as an increase of the total volume or the number of mitochondria in response to certain stimuli, are currently hard to quantify. To provide tools to extract quantitative information from available 3D microscopic datasets generated with methods such as serial block face scanning electron microscopy we a) developed much improved fixation and embedding protocols for plants to drastically reduce processing artifacts and b) generated an easy-to-use AI tool for quantitative analysis and visualization of large-scale data sets. We make this tool available as open source.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Automated cryo-lamella preparation for high-throughput in-situ structural biology 94%
- Automated methods for 3D Segmentation of Focused Ion Beam-Scanning Electron Microscopic Images 93%
- Miffi: Improving the accuracy of CNN-based cryo-EM micrograph filtering with fine-tuning and Fourier space information 93%
Similar papers in this journal
"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.