Merge pull request #37 from andreped/demo-fix
Browse files- README.md +13 -0
- demo/src/utils.py +1 -0
README.md
CHANGED
|
@@ -19,6 +19,12 @@ app_file: demo/app.py
|
|
| 19 |
<h1 align="center">DDMR: Deep Deformation Map Registration</h1>
|
| 20 |
<h3 align="center">Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation</h3>
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
**DDMR** was developed by SINTEF Health Research. The corresponding manuscript describing the framework has been published in [PLOS ONE](https://journals.plos.org/plosone/) and the manuscript is openly available [here](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0282110).
|
| 23 |
|
| 24 |
</div>
|
|
@@ -74,6 +80,13 @@ where:
|
|
| 74 |
|
| 75 |
Use ```ddmr --help``` to see additional options like using precomputed segmentations to crop the images to the desired ROI, or debugging.
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
## 🏋️♂️ Training
|
| 78 |
|
| 79 |
Use the "MultiTrain" scripts to launch the trainings, providing the neccesary parameters. Those in the COMET folder accepts a .ini configuration file (see COMET/train_config_files for example configurations).
|
|
|
|
| 19 |
<h1 align="center">DDMR: Deep Deformation Map Registration</h1>
|
| 20 |
<h3 align="center">Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation</h3>
|
| 21 |
|
| 22 |
+
[](https://github.com/DAVFoundation/captain-n3m0/blob/master/LICENSE)
|
| 23 |
+
[](https://github.com/jpdefrutos/DDMR/actions/workflows/deploy.yml)
|
| 24 |
+
[](https://doi.org/10.1371/journal.pone.0282110)
|
| 25 |
+
<a target="_blank" href="https://huggingface.co/spaces/andreped/DDMR"><img src="https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-yellow.svg"></a>
|
| 26 |
+
|
| 27 |
+
|
| 28 |
**DDMR** was developed by SINTEF Health Research. The corresponding manuscript describing the framework has been published in [PLOS ONE](https://journals.plos.org/plosone/) and the manuscript is openly available [here](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0282110).
|
| 29 |
|
| 30 |
</div>
|
|
|
|
| 80 |
|
| 81 |
Use ```ddmr --help``` to see additional options like using precomputed segmentations to crop the images to the desired ROI, or debugging.
|
| 82 |
|
| 83 |
+
## 🤗 Demo <a target="_blank" href="https://huggingface.co/spaces/andreped/DDMR"><img src="https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-yellow.svg"></a>
|
| 84 |
+
|
| 85 |
+
A live demo to easily test the best performing pretrained models was developed in Gradio and is deployed on `Hugging Face`.
|
| 86 |
+
|
| 87 |
+
To access the live demo, click on the `Hugging Face` badge above. Below is a snapshot of the current state of the demo app.
|
| 88 |
+
|
| 89 |
+
|
| 90 |
## 🏋️♂️ Training
|
| 91 |
|
| 92 |
Use the "MultiTrain" scripts to launch the trainings, providing the neccesary parameters. Those in the COMET folder accepts a .ini configuration file (see COMET/train_config_files for example configurations).
|
demo/src/utils.py
CHANGED
|
@@ -9,6 +9,7 @@ def load_ct_to_numpy(data_path):
|
|
| 9 |
data_path = data_path.name
|
| 10 |
|
| 11 |
image = nib.load(data_path)
|
|
|
|
| 12 |
resampled = resample_to_output(image, None, order=0)
|
| 13 |
data = resampled.get_fdata()
|
| 14 |
|
|
|
|
| 9 |
data_path = data_path.name
|
| 10 |
|
| 11 |
image = nib.load(data_path)
|
| 12 |
+
print("original nibabel image shape:", image.shape)
|
| 13 |
resampled = resample_to_output(image, None, order=0)
|
| 14 |
data = resampled.get_fdata()
|
| 15 |
|