748 replace AsChannelFirst as EnsureChannelFirst

2d_classification/mednist_tutorial.ipynb

@@ -109,7 +109,7 @@
     "from monai.networks.nets import DenseNet121\n",
     "from monai.transforms import (\n",
     "    Activations,\n",
-    "    AddChannel,\n",
+    "    EnsureChannelFirst,\n",
     "    AsDiscrete,\n",
     "    Compose,\n",
     "    LoadImage,\n",
@@ -361,7 +361,7 @@
     "train_transforms = Compose(\n",
     "    [\n",
     "        LoadImage(image_only=True),\n",
-    "        AddChannel(),\n",
+    "        EnsureChannelFirst(),\n",
     "        ScaleIntensity(),\n",
     "        RandRotate(range_x=np.pi / 12, prob=0.5, keep_size=True),\n",
     "        RandFlip(spatial_axis=0, prob=0.5),\n",
@@ -370,7 +370,7 @@
     ")\n",
     "\n",
     "val_transforms = Compose(\n",
-    "    [LoadImage(image_only=True), AddChannel(), ScaleIntensity()])\n",
+    "    [LoadImage(image_only=True), EnsureChannelFirst(), ScaleIntensity()])\n",
     "\n",
     "y_pred_trans = Compose([Activations(softmax=True)])\n",
     "y_trans = Compose([AsDiscrete(to_onehot=num_class)])"
@@ -1340,7 +1340,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.8.13"
   }
  },
  "nbformat": 4,

2d_segmentation/torch/unet_evaluation_array.py

@@ -23,7 +23,7 @@
 from monai.inferers import sliding_window_inference
 from monai.metrics import DiceMetric
 from monai.networks.nets import UNet
-from monai.transforms import Activations, AddChannel, AsDiscrete, Compose, LoadImage, SaveImage, ScaleIntensity
+from monai.transforms import Activations, AsDiscrete, Compose, LoadImage, SaveImage, ScaleIntensity
 
 
 def main(tempdir):
@@ -40,8 +40,8 @@ def main(tempdir):
     segs = sorted(glob(os.path.join(tempdir, "seg*.png")))
 
     # define transforms for image and segmentation
-    imtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
-    segtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
+    imtrans = Compose([LoadImage(image_only=True, ensure_channel_first=True), ScaleIntensity()])
+    segtrans = Compose([LoadImage(image_only=True, ensure_channel_first=True), ScaleIntensity()])
     val_ds = ArrayDataset(images, imtrans, segs, segtrans)
     # sliding window inference for one image at every iteration
     val_loader = DataLoader(val_ds, batch_size=1, num_workers=1, pin_memory=torch.cuda.is_available())

2d_segmentation/torch/unet_evaluation_dict.py

@@ -23,7 +23,7 @@
 from monai.inferers import sliding_window_inference
 from monai.metrics import DiceMetric
 from monai.networks.nets import UNet
-from monai.transforms import Activations, AddChanneld, AsDiscrete, Compose, LoadImaged, SaveImage, ScaleIntensityd
+from monai.transforms import Activations, EnsureChannelFirstd, AsDiscrete, Compose, LoadImaged, SaveImage, ScaleIntensityd
 
 
 def main(tempdir):
@@ -44,7 +44,7 @@ def main(tempdir):
     val_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
-            AddChanneld(keys=["img", "seg"]),
+            EnsureChannelFirstd(keys=["img", "seg"]),
             ScaleIntensityd(keys=["img", "seg"]),
         ]
     )

2d_segmentation/torch/unet_training_array.py

@@ -25,7 +25,6 @@
 from monai.metrics import DiceMetric
 from monai.transforms import (
     Activations,
-    AddChannel,
     AsDiscrete,
     Compose,
     LoadImage,
@@ -53,24 +52,22 @@ def main(tempdir):
     # define transforms for image and segmentation
     train_imtrans = Compose(
         [
-            LoadImage(image_only=True),
-            AddChannel(),
+            LoadImage(image_only=True, ensure_channel_first=True),
             ScaleIntensity(),
             RandSpatialCrop((96, 96), random_size=False),
             RandRotate90(prob=0.5, spatial_axes=(0, 1)),
         ]
     )
     train_segtrans = Compose(
         [
-            LoadImage(image_only=True),
-            AddChannel(),
+            LoadImage(image_only=True, ensure_channel_first=True),
             ScaleIntensity(),
             RandSpatialCrop((96, 96), random_size=False),
             RandRotate90(prob=0.5, spatial_axes=(0, 1)),
         ]
     )
-    val_imtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
-    val_segtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
+    val_imtrans = Compose([LoadImage(image_only=True, ensure_channel_first=True), ScaleIntensity()])
+    val_segtrans = Compose([LoadImage(image_only=True, ensure_channel_first=True), ScaleIntensity()])
 
     # define array dataset, data loader
     check_ds = ArrayDataset(images, train_imtrans, segs, train_segtrans)

2d_segmentation/torch/unet_training_dict.py

@@ -25,7 +25,7 @@
 from monai.metrics import DiceMetric
 from monai.transforms import (
     Activations,
-    AddChanneld,
+    EnsureChannelFirstd,
     AsDiscrete,
     Compose,
     LoadImaged,
@@ -56,7 +56,7 @@ def main(tempdir):
     train_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
-            AddChanneld(keys=["img", "seg"]),
+            EnsureChannelFirstd(keys=["img", "seg"]),
             ScaleIntensityd(keys=["img", "seg"]),
             RandCropByPosNegLabeld(
                 keys=["img", "seg"], label_key="seg", spatial_size=[96, 96], pos=1, neg=1, num_samples=4
@@ -67,7 +67,7 @@ def main(tempdir):
     val_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
-            AddChanneld(keys=["img", "seg"]),
+            EnsureChannelFirstd(keys=["img", "seg"]),
             ScaleIntensityd(keys=["img", "seg"]),
         ]
     )

3d_classification/densenet_training_array.ipynb

@@ -102,7 +102,7 @@
     "from monai.config import print_config\n",
     "from monai.data import DataLoader, ImageDataset\n",
     "from monai.transforms import (\n",
-    "    AddChannel,\n",
+    "    EnsureChannelFirst,\n",
     "    Compose,\n",
     "    RandRotate90,\n",
     "    Resize,\n",
@@ -224,9 +224,9 @@
    ],
    "source": [
     "# Define transforms\n",
-    "train_transforms = Compose([ScaleIntensity(), AddChannel(), Resize((96, 96, 96)), RandRotate90()])\n",
+    "train_transforms = Compose([ScaleIntensity(), EnsureChannelFirst(), Resize((96, 96, 96)), RandRotate90()])\n",
     "\n",
-    "val_transforms = Compose([ScaleIntensity(), AddChannel(), Resize((96, 96, 96))])\n",
+    "val_transforms = Compose([ScaleIntensity(), EnsureChannelFirst(), Resize((96, 96, 96))])\n",
     "\n",
     "# Define nifti dataset, data loader\n",
     "check_ds = ImageDataset(image_files=images, labels=labels, transform=train_transforms)\n",

3d_classification/torch/densenet_evaluation_array.py

@@ -18,7 +18,7 @@
 
 import monai
 from monai.data import CSVSaver, ImageDataset, DataLoader
-from monai.transforms import AddChannel, Compose, Resize, ScaleIntensity
+from monai.transforms import EnsureChannelFirst, Compose, Resize, ScaleIntensity
 
 
 def main():
@@ -46,7 +46,7 @@ def main():
     labels = np.array([0, 0, 1, 0, 1, 0, 1, 0, 1, 0], dtype=np.int64)
 
     # Define transforms for image
-    val_transforms = Compose([ScaleIntensity(), AddChannel(), Resize((96, 96, 96))])
+    val_transforms = Compose([ScaleIntensity(), EnsureChannelFirst(), Resize((96, 96, 96))])
 
     # Define image dataset
     val_ds = ImageDataset(image_files=images, labels=labels, transform=val_transforms, image_only=True)

3d_classification/torch/densenet_evaluation_dict.py

@@ -18,7 +18,7 @@
 
 import monai
 from monai.data import CSVSaver, DataLoader
-from monai.transforms import AddChanneld, Compose, LoadImaged, Resized, ScaleIntensityd
+from monai.transforms import Compose, LoadImaged, Resized, ScaleIntensityd
 
 
 def main():
@@ -49,8 +49,7 @@ def main():
     # Define transforms for image
     val_transforms = Compose(
         [
-            LoadImaged(keys=["img"]),
-            AddChanneld(keys=["img"]),
+            LoadImaged(keys=["img"], ensure_channel_first=True),
             ScaleIntensityd(keys=["img"]),
             Resized(keys=["img"], spatial_size=(96, 96, 96)),
         ]

3d_classification/torch/densenet_training_array.py

@@ -19,7 +19,7 @@
 
 import monai
 from monai.data import ImageDataset, DataLoader
-from monai.transforms import AddChannel, Compose, RandRotate90, Resize, ScaleIntensity
+from monai.transforms import EnsureChannelFirst, Compose, RandRotate90, Resize, ScaleIntensity
 
 
 def main():
@@ -57,8 +57,8 @@ def main():
     labels = np.array([0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0], dtype=np.int64)
 
     # Define transforms
-    train_transforms = Compose([ScaleIntensity(), AddChannel(), Resize((96, 96, 96)), RandRotate90()])
-    val_transforms = Compose([ScaleIntensity(), AddChannel(), Resize((96, 96, 96))])
+    train_transforms = Compose([ScaleIntensity(), EnsureChannelFirst(), Resize((96, 96, 96)), RandRotate90()])
+    val_transforms = Compose([ScaleIntensity(), EnsureChannelFirst(), Resize((96, 96, 96))])
 
     # Define image dataset, data loader
     check_ds = ImageDataset(image_files=images, labels=labels, transform=train_transforms)

3d_classification/torch/densenet_training_dict.py

@@ -20,7 +20,7 @@
 import monai
 from monai.data import decollate_batch, DataLoader
 from monai.metrics import ROCAUCMetric
-from monai.transforms import Activations, AddChanneld, AsDiscrete, Compose, LoadImaged, RandRotate90d, Resized, ScaleIntensityd
+from monai.transforms import Activations, AsDiscrete, Compose, LoadImaged, RandRotate90d, Resized, ScaleIntensityd
 
 
 def main():
@@ -62,17 +62,15 @@ def main():
     # Define transforms for image
     train_transforms = Compose(
         [
-            LoadImaged(keys=["img"]),
-            AddChanneld(keys=["img"]),
+            LoadImaged(keys=["img"], ensure_channel_first=True),
             ScaleIntensityd(keys=["img"]),
             Resized(keys=["img"], spatial_size=(96, 96, 96)),
             RandRotate90d(keys=["img"], prob=0.8, spatial_axes=[0, 2]),
         ]
     )
     val_transforms = Compose(
         [
-            LoadImaged(keys=["img"]),
-            AddChanneld(keys=["img"]),
+            LoadImaged(keys=["img"], ensure_channel_first=True),
             ScaleIntensityd(keys=["img"]),
             Resized(keys=["img"], spatial_size=(96, 96, 96)),
         ]

3d_segmentation/challenge_baseline/run_net.py

@@ -24,7 +24,6 @@
 import monai
 from monai.handlers import CheckpointSaver, MeanDice, StatsHandler, ValidationHandler, from_engine
 from monai.transforms import (
-    AddChanneld,
     AsDiscreted,
     CastToTyped,
     LoadImaged,
@@ -43,8 +42,7 @@ def get_xforms(mode="train", keys=("image", "label")):
     """returns a composed transform for train/val/infer."""
 
     xforms = [
-        LoadImaged(keys),
-        AddChanneld(keys),
+        LoadImaged(keys, ensure_channel_first=True),
         Orientationd(keys, axcodes="LPS"),
         Spacingd(keys, pixdim=(1.25, 1.25, 5.0), mode=("bilinear", "nearest")[: len(keys)]),
         ScaleIntensityRanged(keys[0], a_min=-1000.0, a_max=500.0, b_min=0.0, b_max=1.0, clip=True),

3d_segmentation/ignite/unet_evaluation_array.py

@@ -25,7 +25,7 @@
 from monai.handlers import CheckpointLoader, MeanDice, StatsHandler
 from monai.inferers import sliding_window_inference
 from monai.networks.nets import UNet
-from monai.transforms import Activations, AddChannel, AsDiscrete, Compose, SaveImage, ScaleIntensity
+from monai.transforms import Activations, EnsureChannelFirst, AsDiscrete, Compose, SaveImage, ScaleIntensity
 
 
 def main(tempdir):
@@ -46,8 +46,8 @@ def main(tempdir):
     segs = sorted(glob(os.path.join(tempdir, "seg*.nii.gz")))
 
     # define transforms for image and segmentation
-    imtrans = Compose([ScaleIntensity(), AddChannel()])
-    segtrans = Compose([AddChannel()])
+    imtrans = Compose([ScaleIntensity(), EnsureChannelFirst()])
+    segtrans = Compose([EnsureChannelFirst()])
     ds = ImageDataset(images, segs, transform=imtrans, seg_transform=segtrans, image_only=False)
 
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

3d_segmentation/ignite/unet_evaluation_dict.py

@@ -26,7 +26,7 @@
 from monai.handlers import CheckpointLoader, MeanDice, StatsHandler
 from monai.inferers import sliding_window_inference
 from monai.networks.nets import UNet
-from monai.transforms import Activations, AsChannelFirstd, AsDiscrete, Compose, LoadImaged, SaveImage, ScaleIntensityd
+from monai.transforms import Activations, EnsureChannelFirstd, AsDiscrete, Compose, LoadImaged, SaveImage, ScaleIntensityd
 
 
 def main(tempdir):
@@ -51,7 +51,7 @@ def main(tempdir):
     val_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
-            AsChannelFirstd(keys=["img", "seg"], channel_dim=-1),
+            EnsureChannelFirstd(keys=["img", "seg"]),
             ScaleIntensityd(keys="img"),
         ]
     )

3d_segmentation/ignite/unet_training_array.py

@@ -32,7 +32,7 @@
 )
 from monai.transforms import (
     Activations,
-    AddChannel,
+    EnsureChannelFirst,
     AsDiscrete,
     Compose,
     RandSpatialCrop,
@@ -63,17 +63,17 @@ def main(tempdir):
     train_imtrans = Compose(
         [
             ScaleIntensity(),
-            AddChannel(),
+            EnsureChannelFirst(),
             RandSpatialCrop((96, 96, 96), random_size=False),
         ]
     )
     train_segtrans = Compose(
-        [AddChannel(), RandSpatialCrop((96, 96, 96), random_size=False)]
+        [EnsureChannelFirst(), RandSpatialCrop((96, 96, 96), random_size=False)]
     )
     val_imtrans = Compose(
-        [ScaleIntensity(), AddChannel(), Resize((96, 96, 96))]
+        [ScaleIntensity(), EnsureChannelFirst(), Resize((96, 96, 96))]
     )
-    val_segtrans = Compose([AddChannel(), Resize((96, 96, 96))])
+    val_segtrans = Compose([EnsureChannelFirst(), Resize((96, 96, 96))])
 
     # define image dataset, data loader
     check_ds = ImageDataset(

3d_segmentation/ignite/unet_training_dict.py

@@ -38,7 +38,7 @@
 )
 from monai.transforms import (
     Activations,
-    AsChannelFirstd,
+    EnsureChannelFirstd,
     AsDiscrete,
     Compose,
     LoadImaged,
@@ -72,7 +72,7 @@ def main(tempdir):
     train_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
-            AsChannelFirstd(keys=["img", "seg"], channel_dim=-1),
+            EnsureChannelFirstd(keys=["img", "seg"]),
             ScaleIntensityd(keys="img"),
             RandCropByPosNegLabeld(
                 keys=["img", "seg"],
@@ -88,7 +88,7 @@ def main(tempdir):
     val_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
-            AsChannelFirstd(keys=["img", "seg"], channel_dim=-1),
+            EnsureChannelFirstd(keys=["img", "seg"]),
             ScaleIntensityd(keys="img"),
         ]
     )