Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update DeepEdit infer to accept clicks from viewer #491

Merged
merged 11 commits into from
Aug 28, 2023
+114 −44
Merged

Update DeepEdit infer to accept clicks from viewer #491

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
f74a8ea
Update DeepEdit infer to accept clicks from viewer
diazandr3s Aug 20, 2023
e1782ac
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Aug 20, 2023
df12106
Update version
diazandr3s Aug 20, 2023
4422956
add click flag
yiheng-wang-nv Aug 23, 2023
c7de02c
Add the way to add clicks when running bundle
diazandr3s Aug 23, 2023
2648a69
Update Readme
diazandr3s Aug 24, 2023
baf8b25
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Aug 24, 2023
7aedfc9
add unit test and modify readme
yiheng-wang-nv Aug 24, 2023
9380169
unify naming
yiheng-wang-nv Aug 24, 2023
83d4e20
check premerge cpu
yiheng-wang-nv Aug 25, 2023
0ab9f39
add requirements for premerge cpu
yiheng-wang-nv Aug 25, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
113 changes: 72 additions & 41 deletions models/spleen_deepedit_annotation/configs/inference.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
],
"number_intensity_ch": 1,
"device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
"use_click": false,
"network_def": {
"_target_": "DynUNet",
"spatial_dims": 3,
Expand Down Expand Up @@ -60,49 +61,79 @@
"res_block": true
},
"network": "$@network_def.to(@device)",
"preprocessing_transforms": [
{
"_target_": "LoadImaged",
"keys": "image",
"reader": "ITKReader"
Nic-Ma marked this conversation as resolved.
Show resolved Hide resolved
},
{
"_target_": "EnsureChannelFirstd",
"keys": "image"
},
{
"_target_": "Orientationd",
"keys": "image",
"axcodes": "RAS"
},
{
"_target_": "ScaleIntensityRanged",
"keys": "image",
"a_min": -175,
"a_max": 250,
"b_min": 0.0,
"b_max": 1.0,
"clip": true
}
],
"auto_seg_transforms": [
{
"_target_": "Resized",
"keys": "image",
"spatial_size": "@spatial_size",
"mode": "area"
},
{
"_target_": "DiscardAddGuidanced",
"keys": "image",
"label_names": "@label_names",
"number_intensity_ch": "@number_intensity_ch"
}
],
"deepedit_transforms": [
{
"_target_": "AddGuidanceFromPointsDeepEditd",
"ref_image": "image",
"guidance": "guidance",
"label_names": "@label_names"
},
{
"_target_": "Resized",
"keys": "image",
"spatial_size": "@spatial_size",
"mode": "area"
},
{
"_target_": "ResizeGuidanceMultipleLabelDeepEditd",
"guidance": "guidance",
"ref_image": "image"
},
{
"_target_": "AddGuidanceSignalDeepEditd",
"keys": "image",
"guidance": "guidance",
"number_intensity_ch": "@number_intensity_ch"
}
],
"extra_transforms": [
{
"_target_": "EnsureTyped",
"keys": "image"
}
],
"preprocessing": {
"_target_": "Compose",
"transforms": [
{
"_target_": "LoadImaged",
"keys": "image",
"reader": "ITKReader"
},
{
"_target_": "EnsureChannelFirstd",
"keys": "image"
},
{
"_target_": "Orientationd",
"keys": "image",
"axcodes": "RAS"
},
{
"_target_": "ScaleIntensityRanged",
"keys": "image",
"a_min": -175,
"a_max": 250,
"b_min": 0.0,
"b_max": 1.0,
"clip": true
},
{
"_target_": "Resized",
"keys": "image",
"spatial_size": "@spatial_size",
"mode": "area"
},
{
"_target_": "DiscardAddGuidanced",
"keys": "image",
"label_names": "@label_names",
"number_intensity_ch": "@number_intensity_ch"
},
{
"_target_": "EnsureTyped",
"keys": "image"
}
]
"transforms": "$@preprocessing_transforms + (@deepedit_transforms if @use_click else @auto_seg_transforms) + @extra_transforms"
Nic-Ma marked this conversation as resolved.
Show resolved Hide resolved
},
"dataset": {
"_target_": "Dataset",
Expand Down
3 changes: 2 additions & 1 deletion models/spleen_deepedit_annotation/configs/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
{
"schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
"version": "0.4.7",
"version": "0.4.8",
"changelog": {
"0.4.8": "Add infer transforms to manage clicks from viewer",
"0.4.7": "fix the wrong GPU index issue of multi-node",
"0.4.6": "update to use rc7 which solves dynunet issue",
"0.4.5": "remove error dollar symbol in readme",
Expand Down
20 changes: 20 additions & 0 deletions models/spleen_deepedit_annotation/docs/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,10 +118,30 @@ python -m monai.bundle run --config_file "['configs/train.json','configs/evaluat

#### Execute inference:


For automatic inference mode:


```
python -m monai.bundle run --config_file configs/inference.json
```

For interactive segmentation mode, in which the user provides clicks, set the **use_click** flag to true:


```
python -m monai.bundle run --config_file configs/inference.json --use_click true
```

Clicks should be added to the data dictionary that is passed to the preprocessing transforms. Label names are the keys and their values are the clicks coordinates.

Like the following format:

```
data_dict = {'background': [], 'spleen': [[I1, J1, K1], [I2, J2, K2]]}
yiheng-wang-nv marked this conversation as resolved.
Show resolved Hide resolved
```
where **[I1,J1,K1]** and **[I2,J2,K2]** are the point coordinates

#### Export checkpoint to TensorRT based models with fp32 or fp16 precision:

```bash
Expand Down