Add commands to README
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags:
|
|
| 6 |
A pre-trained model for volumetric (3D) segmentation of the spleen from CT image.
|
| 7 |
|
| 8 |
# Model Overview
|
| 9 |
-
This model is trained using the
|
| 10 |
|
| 11 |
## Data
|
| 12 |
The training dataset is Task09_Spleen.tar from http://medicaldecathlon.com/.
|
|
@@ -22,19 +22,34 @@ Input: 1 channel CT image
|
|
| 22 |
Output: 2 channels: Label 1: spleen; Label 0: everything else
|
| 23 |
|
| 24 |
## Scores
|
| 25 |
-
This model
|
| 26 |
|
| 27 |
-
Mean
|
| 28 |
|
| 29 |
## commands example
|
| 30 |
Execute inference:
|
| 31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
Verify the metadata format:
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
Verify the data shape of network:
|
| 35 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
Export checkpoint to TorchScript file:
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
# Disclaimer
|
| 40 |
This is an example, not to be used for diagnostic purposes.
|
|
|
|
| 6 |
A pre-trained model for volumetric (3D) segmentation of the spleen from CT image.
|
| 7 |
|
| 8 |
# Model Overview
|
| 9 |
+
This model is trained using the runner-up [1] awarded pipeline of the "Medical Segmentation Decathlon Challenge 2018" using the UNet architecture [2] with 32 training images and 9 validation images.
|
| 10 |
|
| 11 |
## Data
|
| 12 |
The training dataset is Task09_Spleen.tar from http://medicaldecathlon.com/.
|
|
|
|
| 22 |
Output: 2 channels: Label 1: spleen; Label 0: everything else
|
| 23 |
|
| 24 |
## Scores
|
| 25 |
+
This model achieves the following Dice score on the validation data (our own split from the training dataset):
|
| 26 |
|
| 27 |
+
Mean Dice = 0.96
|
| 28 |
|
| 29 |
## commands example
|
| 30 |
Execute inference:
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
python -m monai.bundle run evaluator --meta_file configs/metadata.json --config_file configs/inference.json --logging_file configs/logging.conf
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
Verify the metadata format:
|
| 37 |
+
|
| 38 |
+
```
|
| 39 |
+
python -m monai.bundle verify_metadata --meta_file configs/metadata.json --filepath eval/schema.json
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
Verify the data shape of network:
|
| 43 |
+
|
| 44 |
+
```
|
| 45 |
+
python -m monai.bundle verify_net_in_out network_def --meta_file configs/metadata.json --config_file configs/inference.json
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
Export checkpoint to TorchScript file:
|
| 49 |
+
|
| 50 |
+
```
|
| 51 |
+
python -m monai.bundle export network_def --filepath models/model.ts --ckpt_file models/model.pt --meta_file configs/metadata.json --config_file configs/inference.json
|
| 52 |
+
```
|
| 53 |
|
| 54 |
# Disclaimer
|
| 55 |
This is an example, not to be used for diagnostic purposes.
|