Add no scribbles model (#1586)

* Add no_scribbles model to remove the scribbles

Signed-off-by: Matthias Hadlich <[email protected]>

* Disable scribbles if flag is passed

Signed-off-by: Matthias Hadlich <[email protected]>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Signed-off-by: Matthias Hadlich <[email protected]>

* Rework scribbles flag, now configurable via --conf

Signed-off-by: Matthias Hadlich <[email protected]>

* Update README for scribbles flag and change to MONAILabel semantics

Signed-off-by: Matthias Hadlich <[email protected]>

* Fix typos

Signed-off-by: Matthias Hadlich <[email protected]>

---------

Signed-off-by: Matthias Hadlich <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: matt3o

sample-apps/radiology/README.md

@@ -188,7 +188,8 @@ the model to learn on new organ.
 | Name                 | Values             | Description                                                     |
 |----------------------|--------------------|-----------------------------------------------------------------|
 | use_pretrained_model | **true**, false    | Disable this NOT to load any pretrained weights                 |
-| preload              | true, **false**    | Preload model into GPU                                                                                |
+| preload              | true, **false**    | Preload model into GPU                                          |
+| scribbles            | **true**, false    | Don't load the scribble models, useful for user studies         |
 
 - Network: This model uses the [UNet](https://docs.monai.io/en/latest/networks.html#unet) as the default network. Researchers can define their own network or use one of the listed [here](https://docs.monai.io/en/latest/networks.html)
 - Labels

sample-apps/radiology/main.py

@@ -66,6 +66,8 @@ def __init__(self, app_dir, studies, conf):
 
         models = models.split(",")
         models = [m.strip() for m in models]
+        # Can be configured with --conf scribbles false or true
+        self.scribbles = conf.get("scribbles", "true") == "true"
         invalid = [m for m in models if m != "all" and not configs.get(m)]
         if invalid:
             print("")
@@ -138,26 +140,27 @@ def init_infers(self) -> Dict[str, InferTask]:
         #################################################
         # Scribbles
         #################################################
-        infers.update(
-            {
-                "Histogram+GraphCut": HistogramBasedGraphCut(
-                    intensity_range=(-300, 200, 0.0, 1.0, True),
-                    pix_dim=(2.5, 2.5, 5.0),
-                    lamda=1.0,
-                    sigma=0.1,
-                    num_bins=64,
-                    labels=task_config.labels,
-                ),
-                "GMM+GraphCut": GMMBasedGraphCut(
-                    intensity_range=(-300, 200, 0.0, 1.0, True),
-                    pix_dim=(2.5, 2.5, 5.0),
-                    lamda=5.0,
-                    sigma=0.5,
-                    num_mixtures=20,
-                    labels=task_config.labels,
-                ),
-            }
-        )
+        if self.scribbles:
+            infers.update(
+                {
+                    "Histogram+GraphCut": HistogramBasedGraphCut(
+                        intensity_range=(-300, 200, 0.0, 1.0, True),
+                        pix_dim=(2.5, 2.5, 5.0),
+                        lamda=1.0,
+                        sigma=0.1,
+                        num_bins=64,
+                        labels=task_config.labels,
+                    ),
+                    "GMM+GraphCut": GMMBasedGraphCut(
+                        intensity_range=(-300, 200, 0.0, 1.0, True),
+                        pix_dim=(2.5, 2.5, 5.0),
+                        lamda=5.0,
+                        sigma=0.5,
+                        num_mixtures=20,
+                        labels=task_config.labels,
+                    ),
+                }
+            )
 
         #################################################
         # Pipeline based on existing infers