Mercurial > repos > perssond > coreograph
comparison README.md @ 1:57f1260ca94e draft
"planemo upload commit fec9dc76b3dd17b14b02c2f04be9d30f71eba1ae"
| author | watsocam |
|---|---|
| date | Fri, 11 Mar 2022 23:40:51 +0000 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| 0:99308601eaa6 | 1:57f1260ca94e |
|---|---|
| 1  | |
| 2 | |
| 3 *Great*....yet **another** TMA dearray program. What does *this* one do? | |
| 4 | |
| 5 Coreograph uses UNet, a deep learning model, to identify complete/incomplete tissue cores on a tissue microarray. It has been trained on 9 TMA slides of different sizes and tissue types. | |
| 6 | |
| 7 <img src="/images/raw.jpg" width="425" height="315" /> <img src="/images/probmap.jpg" width="425" height="315" /> | |
| 8 | |
| 9 Training sets were acquired at 0.2micron/pixel resolution and downsampled 1/32 times to speed up performance. Once the center of each core has been identifed, active contours is used to generate a tissue mask of each core that can aid downstream single cell segmentation. A GPU is not required but will reduce computation time. | |
| 10 | |
| 11 *Coreograph exports these files:** | |
| 12 1. individual cores as tiff stacks with user-selectable channel ranges | |
| 13 2. binary tissue masks (saved in the 'mask' subfolder) | |
| 14 3. a TMA map showing the labels and outlines of each core for quality control purposes | |
| 15 | |
| 16  | |
| 17 | |
| 18 *Instructions for use:** | |
| 19 `python UNetCoreograph.py` | |
| 20 1. `--imagePath` : the path to the image file. Should be tif or ome.tif | |
| 21 2. `--outputPath` : the path to save the above-mentioned files | |
| 22 3. `--downsampleFactor` : how many times to downsample the raw image file. Default is 5 times to match the training data. | |
| 23 4. `--channel` : which is the channel to feed into UNet and generate probabiltiy maps from. This is usually a DAPI channel | |
| 24 5. `--buffer` : the extra space around a core before cropping it. A value of 2 means there is twice the width of the core added as buffer around it. 2 is default | |
| 25 6. `--outputChan` : a range of channels to be exported. -1 is default and will export all channels (takes awhile). Select a single channel or a continuous range. --outputChan 0 10 will export channel 0 up to (and including) channel 10 | |
| 26 |