Notebook For ER Prediction Using SlideGraph Pipeline #207
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Moved local test files into `tiatoolbox/data`. - Using `pkg_resources` to properly load bundled resources (target_image.png) in `tiatoolbox.data`. Bundled sample can now be loaded via `tiatoolbox.data` e.g. `img = tiatoolbox.data.stainnorm_target`. - Removed duplicate code in `conftest.py` for downlading remote files. This is now in `tiatoolbox.data._fetch_remote_file` which will load a remote resource using the corresponding key in `tiatoolbox/data`.
This is intentional in the test.
Codecov Report
@@ Coverage Diff @@
## develop #207 +/- ##
===========================================
+ Coverage 99.81% 99.83% +0.01%
===========================================
Files 53 52 -1
Lines 4867 4848 -19
Branches 800 796 -4
===========================================
- Hits 4858 4840 -18
Misses 2 2
+ Partials 7 6 -1
Continue to review full report at Codecov.
|
…to example-ER-slidegraph-pipeline
John-P
changed the title
…example-ER-slidegraph-pipeline
vqdang
reviewed
Dec 20, 2021
Comment on lines
+44
to
+54
| "- Extraction of deep features\n", | ||
| "\n", | ||
| "> **Note**: Although the original paper was evaluated for HER2. The method itself\n", | ||
| "> can be applicable for other mutation prediction. We provide a pretrained model\n", | ||
| "> for predicting [ER (Estrogen receptor)](https://en.wikipedia.org/wiki/Estrogen_receptor)\n", | ||
| "> status [here (model weights)](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/model.weights.pth)\n", | ||
| "> and [here (model auxiliary)](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/model.aux.dat).\n", | ||
| "> You can get the pre-generated graphs [here](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/graphs.zip)\n", | ||
| "> and its node preprocessing model [here](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/node_scaler.dat).\n", | ||
| "> For predicting ER status, we use deep features coming from ResNet50 rather than\n", | ||
| "> the cellular composition.\n" |
Contributor
There was a problem hiding this comment.
@shaneahmed URLs are here, all of them are for ER
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Text in the notebook are edited for the ER status prediction task. In this notebook, we use Resnet feature which gives higher accuracy.
Cells before training part are tested and working well.
Training is in progress...