🆕 Add GrandQC tissue detection model #965
Conversation
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## dev-define-engines-abc #965 +/- ##
==========================================================
- Coverage 94.72% 94.65% -0.08%
==========================================================
Files 73 74 +1
Lines 9235 9278 +43
Branches 1208 1209 +1
==========================================================
+ Hits 8748 8782 +34
- Misses 452 460 +8
- Partials 35 36 +1 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
There was a problem hiding this comment.
Pull Request Overview
This PR integrates the GrandQC tissue detection model into TIAToolBox, adding a UNet++ based tissue segmentation capability trained at 10 microns per pixel resolution. The implementation leverages the segmentation-models-pytorch library to avoid reimplementing the UNet++ architecture.
- Adds GrandQC tissue detection model architecture and pretrained weights
- Integrates model with existing tissue masking functionality
- Adds comprehensive test coverage and example usage
Reviewed Changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| tiatoolbox/models/architecture/grandqc.py | Defines the TissueDetectionModel class with UNet++ architecture and custom preprocessing/postprocessing |
| tiatoolbox/data/pretrained_model.yaml | Adds GrandQC model configuration and fixes IOConfig class references across multiple models |
| tests/models/test_arch_grandqc.py | Implements unit tests for model creation, weight loading, and inference |
| requirements/requirements.txt | Adds segmentation-models-pytorch dependency |
| tiatoolbox/wsicore/wsireader.py | Integrates GrandQC masker into tissue_mask method with 10mpp resolution handling |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
| @staticmethod | ||
| def preproc(image: np.ndarray) -> np.ndarray: | ||
| """Apply jpg compression then ImageNet normalise.""" |
There was a problem hiding this comment.
Corrected spelling of 'normalise' to 'normalize' for consistency with American English spelling used elsewhere in the codebase.
| """Apply jpg compression then ImageNet normalise.""" | |
| """Apply jpg compression then ImageNet normalize.""" |
|
|
||
| @staticmethod | ||
| def preproc(image: np.ndarray) -> np.ndarray: | ||
| """Apply jpg compression then ImageNet normalise.""" |
There was a problem hiding this comment.
The preproc docstring lacks parameter and return type documentation. Consider adding a complete docstring with Args and Returns sections following the pattern used in other models like HoVerNet and MicroNet.
| """Apply jpg compression then ImageNet normalise.""" | |
| """Apply JPEG compression and ImageNet normalization to the input image. | |
| Args: | |
| image (np.ndarray): | |
| Input image as a NumPy array (H, W, C) in uint8 format. | |
| Returns: | |
| np.ndarray: | |
| The preprocessed image as a float32 NumPy array, normalized using ImageNet mean and std. | |
| """ |
This PR adds GrandQC tissue detection (Unet++) model to TIAToolBox models. GrandQC Original Github.
Tasks
pretrained_model.yamlrequirements.txt