diff --git a/docs/replication-guide/baselines.md b/docs/replication-guide/baselines.md
index 99d08f0..60678ef 100644
--- a/docs/replication-guide/baselines.md
+++ b/docs/replication-guide/baselines.md
@@ -1,2 +1,46 @@
 # Reproduce Baselines
-:hourglass_flowing_sand: Coming soon! :hourglass_flowing_sand:
+
+Reproducing baselines used in this study is very similar to the adaptation of the FM as essentially we are just using the FM weights for adaptation. 
+
+## Randomly initialized
+
+We provide the YAML configuration to train the random init baseline at `experiments/baselines/supervised_training/supervised_random_init.yaml`
+
+By default, we configure this for Task 1. You can adapt this for Task 2 and Task 3 by searching for `Note: ` comments in the YAML that outline what must be changed. 
+
+You can start training by running this in the root code folder,
+```bash
+lighter fit --config_file ./experiments/baselines/supervised_training/supervised_random_init.yaml
+```
+ 
+## Transfer learning
+We provide the YAML configuration to train the transfer learning baseline at `experiments/baselines/supervised_training/supervised_finetune.yaml`
+
+This baseline is only used for Task 2 and Task 3 as we use the random init baseline from Task 1 for the transfer. Follow the `Note: ` comments to switch between Task 2 and Task 3 configurations. 
+
+You can start training by running this in the root code folder,
+```bash
+lighter fit --config_file ./experiments/baselines/supervised_training/supervised_finetune.yaml
+```
+
+## Med3D / MedicalNet
+Original repo: https://github.com/Tencent/MedicalNet
+
+We have provided re-implementations of Med3D to fit into our YAML workflows at `experiments/baselines/med3d/finetune.yaml`. Again, the `Note: ` comments help adapt for different tasks. 
+
+
+You can start training by running this in the root code folder,
+```bash
+lighter fit --config_file ./experiments/baselines/med3d/finetune.yaml
+```
+
+## Models Genesis
+Original repo: https://github.com/MrGiovanni/ModelsGenesis
+
+We have provided re-implementations of Models Genesis to fit into our YAML workflows at `experiments/baselines/models_genesis/finetune.yaml`. Again, the `Note: ` comments help adapt for different tasks. 
+
+
+You can start training by running this in the root code folder,
+```bash
+lighter fit --config_file ./experiments/baselines/models_genesis/finetune.yaml
+```
diff --git a/docs/replication-guide/fm_adaptation.md b/docs/replication-guide/fm_adaptation.md
index 593225c..ba24c36 100644
--- a/docs/replication-guide/fm_adaptation.md
+++ b/docs/replication-guide/fm_adaptation.md
@@ -6,7 +6,7 @@ The FM was adapted by either fine-tuning all its weights or by freezing its weig
 
 We provide the YAML configuration for this at `experiments/adaptation/fmcib_finetune.yaml`.
 
-By default, we configure this for Task 1. You can adapt this for Task 2 and Task 3 by searching for 'Note: ' comments in the YAML that outline what must be changed. Make sure you download the weights for the pre-trained foundation model before attempting to reproduce this training. 
+By default, we configure this for Task 1. You can adapt this for Task 2 and Task 3 by searching for `Note: ` comments in the YAML that outline what must be changed. Make sure you download the weights for the pre-trained foundation model before attempting to reproduce this training. 
 
 
 You can start training by running this in the root code folder,
diff --git a/docs/replication-guide/inference.md b/docs/replication-guide/inference.md
index 54bc25e..9566e84 100644
--- a/docs/replication-guide/inference.md
+++ b/docs/replication-guide/inference.md
@@ -12,10 +12,10 @@ lighter predict --config_file ./experiments/inference/extract_features.yaml
 !!! note
      While the above pipeline will allow you to extract features, we provide an easier and simpler, recommended API to do this. Please refer to [Quick Start](../getting-started/quick-start.md) or [Cloud Quick Start](../getting-started/cloud-quick-start.md)
 
-However, this method might be preferred when features need to be extracted from different models (used as baselines in our study). Follow the `Note:` in the corresponding config file to change model paths. 
 
-## Running predictions from our supervised models (Finetuned FM/ Baselines)
+However, this method might be preferred when features need to be extracted from different models (used as baselines in our study). Follow the `Note:` in the corresponding config file to change model paths and use different baselines tested.
 
+## Running predictions from our supervised models (Finetuned FM/ Baselines)
 
 To run predictions from our models (both supervised and self-supervised), we provide YAML files that can be run with the lighter interface. These are found in `experiments/inference`, namely `get_predictions.yaml` for getting the predictions. 
 
@@ -37,3 +37,5 @@ lighter predict --config_file ./experiments/inference/get_predictions.yaml
 ```
 As with the previous YAMLS, please follow the 'Note:' tags to place appropriate data paths and change relevant parameters. This YAML is to be used if you want to get target predictions from the models.
 
+!!! note
+     The predictions can be extracted for different tasks as well as different baselines by following the `Note:` comments. 
diff --git a/experiments/baselines/med3d/extract_features.yaml b/experiments/baselines/med3d/extract_features.yaml
deleted file mode 100644
index b71a547..0000000
--- a/experiments/baselines/med3d/extract_features.yaml
+++ /dev/null
@@ -1,60 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 32
-    pin_memory: True
-    num_workers: 6
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: monai.networks.nets.resnet50
-          widen_factor: 1
-          bias_downsample: False
-          n_input_channels: 1
-          conv1_t_stride: 1
-          feed_forward: False
-          pretrained: False
-        weights_path: "./models/pretrained/med3d/resnet_50.pth"
-
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_test.csv" # Note: Change path to the CSV file to extract features from.
-        label: "survival" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 25
-        orient: False # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                # - _target_: fmcib.transforms.IntensityNormalizeOneVolume ## Only for Med3D, MR only?
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
-
diff --git a/experiments/baselines/med3d/supervised_training/finetune.yaml b/experiments/baselines/med3d/finetune.yaml
similarity index 94%
rename from experiments/baselines/med3d/supervised_training/finetune.yaml
rename to experiments/baselines/med3d/finetune.yaml
index 64c2f23..c504517 100644
--- a/experiments/baselines/med3d/supervised_training/finetune.yaml
+++ b/experiments/baselines/med3d/finetune.yaml
@@ -57,21 +57,20 @@ system:
     criterion:
         _target_: torch.nn.CrossEntropyLoss # Note: Change to torch.nn.BCEWithLogitsLoss for Task 2 and Task 3
 
-    optimizers:
+    optimizer:
         _target_: torch.optim.Adam
         params: "$@system#model.parameters()"
         # lr: 0.001 # Compute L  R dynamically for different batch sizes
         # weight_decay: 0.0
         # momentum: 0.9
 
-    schedulers:
-      scheduler:
+    scheduler:
         _target_: torch.optim.lr_scheduler.StepLR
         optimizer: "@system#optimizers"
         step_size: 30
-      strict: True
 
-    train_metrics: 
+    metrics: 
+      train:
         - _target_: torchmetrics.AveragePrecision
           task: binary # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
           # num_classes: 8 
@@ -79,12 +78,11 @@ system:
         - _target_: torchmetrics.AUROC
           task: binary # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
           # num_classes: 8 
+      val: "%#train"
+      test: "%#train"
 
-
-    val_metrics: "%system#train_metrics"
-    test_metrics: "%system#train_metrics"
-
-    train_dataset:
+    datasets:
+      train:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: null # Note: Change path
         label: "survival" # Note: Change to "malignancy" for Task 2 and "survival" for Task 3
@@ -118,7 +116,7 @@ system:
                 #   subtrahend: -1024
                 #   divisor: 3072
 
-    val_dataset:
+      val:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: null # Note: Change path
         label: "@system#train_dataset#label"
@@ -141,6 +139,4 @@ system:
                 - _target_: monai.transforms.SpatialPad
                   spatial_size: [50, 50, 50]
 
-
-    test_dataset: null
-    predict_dataset: null
\ No newline at end of file
+      test: null
\ No newline at end of file
diff --git a/experiments/baselines/med3d/supervised_training/get_predictions_task1.yaml b/experiments/baselines/med3d/supervised_training/get_predictions_task1.yaml
deleted file mode 100644
index 6518a1f..0000000
--- a/experiments/baselines/med3d/supervised_training/get_predictions_task1.yaml
+++ /dev/null
@@ -1,64 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 32
-    pin_memory: True
-    num_workers: 3
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: monai.networks.nets.resnet50
-          widen_factor: 1
-          bias_downsample: False
-          n_input_channels: 1
-          conv1_t_stride: 1
-          feed_forward: False
-          pretrained: False
-        heads: [2048, 1024, 8] # Note: Change to [4096, 2048, 1] for Task 2 and Task 3
-        weights_path: null
-
-    post_criterion_activation: "$torch.nn.functional.softmax" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
-
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_test.csv" # Note: Change path to the CSV file to extract features from.
-        label: "Coarse_lesion_type" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 25
-        orient: True  # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                # - _target_: fmcib.transforms.IntensityNormalizeOneVolume ## Only for Med3D, MR only?
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
-
diff --git a/experiments/baselines/med3d/supervised_training/get_predictions_task2.yaml b/experiments/baselines/med3d/supervised_training/get_predictions_task2.yaml
deleted file mode 100644
index 1a3d3b5..0000000
--- a/experiments/baselines/med3d/supervised_training/get_predictions_task2.yaml
+++ /dev/null
@@ -1,62 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 8
-    pin_memory: True
-    num_workers: 3
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: monai.networks.nets.resnet50
-          widen_factor: 1
-          bias_downsample: False
-          n_input_channels: 1
-          conv1_t_stride: 1
-          feed_forward: False
-          pretrained: False
-        heads: [2048, 1024, 1] # Note: Change to [4096, 2048, 1] for Task 2 and Task 3
-        weights_path: null
-    post_criterion_activation: "$torch.sigmoid" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    # cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "/home/suraj/Repositories/foundation-cancer-image-biomarker/data/csvs/luna16/luna16/test.csv" # Note: Change path to the CSV file to extract features from.
-        label: "malignancy" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 25
-        orient: False # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                # - _target_: fmcib.transforms.IntensityNormalizeOneVolume ## Only for Med3D, MR only?
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
-
diff --git a/experiments/baselines/med3d/supervised_training/get_predictions_task3.yaml b/experiments/baselines/med3d/supervised_training/get_predictions_task3.yaml
deleted file mode 100644
index a831ebc..0000000
--- a/experiments/baselines/med3d/supervised_training/get_predictions_task3.yaml
+++ /dev/null
@@ -1,61 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 8
-    pin_memory: True
-    num_workers: 2
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: monai.networks.nets.resnet50
-          widen_factor: 1
-          bias_downsample: False
-          n_input_channels: 1
-          conv1_t_stride: 1
-          feed_forward: False
-          pretrained: False
-        heads: [2048, 1024, 512, 256, 1] # Note: Change to [4096, 2048, 1] for Task 2 and [4096, 2048, 512, 256, 1] Task 3
-        weights_path: null
-    post_criterion_activation: "$torch.sigmoid" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    # cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "/home/suraj/Repositories/foundation-cancer-image-biomarker/data/preprocessing/lung1/annotations.csv" # Note: Change path to the CSV file to extract features from.
-        label: "survival" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 25
-        orient: False # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                # - _target_: fmcib.transforms.IntensityNormalizeOneVolume ## Only for Med3D, MR only?
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
diff --git a/experiments/baselines/models_genesis/extract_features.yaml b/experiments/baselines/models_genesis/extract_features.yaml
deleted file mode 100644
index 3d7559a..0000000
--- a/experiments/baselines/models_genesis/extract_features.yaml
+++ /dev/null
@@ -1,55 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 32
-    pin_memory: True
-    num_workers: 6
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: fmcib.models.ModelsGenesisUNet3D
-          decoder: False
-        weights_path: ./models/pretrained/models_genesis/Genesis_Chest_CT.pt
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_test.csv" # Note: Change path to the CSV file to extract features from.
-        label: "survival" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 24
-        orient: False # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                - _target_: monai.transforms.Transpose ## Only for Models Genesis
-                  indices: [2, 1, 0]
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [48, 48, 48]
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
\ No newline at end of file
diff --git a/experiments/baselines/models_genesis/supervised_training/finetune.yaml b/experiments/baselines/models_genesis/finetune.yaml
similarity index 88%
rename from experiments/baselines/models_genesis/supervised_training/finetune.yaml
rename to experiments/baselines/models_genesis/finetune.yaml
index aebc8de..ab31c40 100644
--- a/experiments/baselines/models_genesis/supervised_training/finetune.yaml
+++ b/experiments/baselines/models_genesis/finetune.yaml
@@ -40,28 +40,32 @@ system:
           decoder: False
         weights_path: ./models/pretrained/models_genesis/Genesis_Chest_CT.pt
         heads: [4096, 2048, 512, 256, 8] # Note: Change to [4096, 2048, 1] for Task 2 and  [4096, 2048, 512, 256, 1] Task 3
-
-    post_criterion_activation: "$torch.sigmoid" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
+    
+    postprocessing:
+      metrics:
+        pred:
+          - "$lambda x: torch.softmax(x, 1)" # Note: Change to $lambda x: torch.sigmoid(x) for Task 2 and Task 3    
+      # criterion:
+      #   target: # Note: Uncomment for Task 2 and Task 3
+      #     - "$lambda x: x.float()"
 
     criterion:
         _target_: torch.nn.CrossEntropyLoss # Note: Change to torch.nn.BCEWithLogitsLoss for Task 2 and Task 3
 
-    optimizers:
+    optimizer:
         _target_: torch.optim.Adam
         params: "$@system#model.parameters()"
         # lr: "$((@system#batch_size * @trainer#devices)/256) * 0.1" # Compute LR dynamically for different batch sizes
         # weight_decay: 0.0
         # momentum: 0.9
 
-    schedulers:
-      scheduler:
-        _target_: torch.optim.lr_scheduler.StepLR
-        optimizer: "@system#optimizers"
-        step_size: 30
-      strict: True
+    scheduler:
+      _target_: torch.optim.lr_scheduler.StepLR
+      optimizer: "@system#optimizers"
+      step_size: 30
 
-    train_metrics: 
+    metrics:
+      train: 
         - _target_: torchmetrics.AveragePrecision
           task: binary # Note: Change to `multiclass` for Task 2 and Task 3 and remove num_classes below
           # num_classes: 8 
@@ -69,12 +73,11 @@ system:
         - _target_: torchmetrics.AUROC
           task: binary # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
           # num_classes: 8 
+      val: "%#train"
+      test: "%#train"
 
-
-    val_metrics: "%system#train_metrics"
-    test_metrics: "%system#train_metrics"
-
-    train_dataset:
+    datasets:
+      train:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: null # Note: Change path
         label: "survival" # Note: Change to "malignancy" for Task 2 and "survival" for Task 3
@@ -107,7 +110,7 @@ system:
                   b_max: 1.0
                   clip: True
 
-    val_dataset:
+      val:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: null # Note: Change path
         label: "@system#train_dataset#label"
@@ -131,5 +134,4 @@ system:
                   b_max: 1.0
                   clip: True
                   
-    test_dataset: null
-    predict_dataset: null
\ No newline at end of file
+      test: null
\ No newline at end of file
diff --git a/experiments/baselines/models_genesis/supervised_training/get_predictions_task1.yaml b/experiments/baselines/models_genesis/supervised_training/get_predictions_task1.yaml
deleted file mode 100644
index 313a236..0000000
--- a/experiments/baselines/models_genesis/supervised_training/get_predictions_task1.yaml
+++ /dev/null
@@ -1,59 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 8
-    pin_memory: True
-    num_workers: 2
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: fmcib.models.ModelsGenesisUNet3D
-          decoder: False
-        heads: [4096, 2048, 8] # Note: Change to [4096, 2048, 1] for Task 2 and Task 3
-        weights_path: null
-
-    post_criterion_activation: "$torch.nn.functional.softmax" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
-
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_test.csv" # Note: Change path to the CSV file to extract features from.
-        label: "Coarse_lesion_type" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 24
-        orient: True  # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                - _target_: monai.transforms.Transpose ## Only for Models Genesis
-                  indices: [2, 1, 0]
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [48, 48, 48]
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
\ No newline at end of file
diff --git a/experiments/baselines/models_genesis/supervised_training/get_predictions_task2.yaml b/experiments/baselines/models_genesis/supervised_training/get_predictions_task2.yaml
deleted file mode 100644
index 137e410..0000000
--- a/experiments/baselines/models_genesis/supervised_training/get_predictions_task2.yaml
+++ /dev/null
@@ -1,57 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 8
-    pin_memory: True
-    num_workers: 2
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: fmcib.models.ModelsGenesisUNet3D
-          decoder: False
-        heads: [4096, 2048, 1] # Note: Change to [4096, 2048, 1] for Task 2 and Task 3
-        weights_path: null
-    post_criterion_activation: "$torch.sigmoid" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    # cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "/home/suraj/Repositories/foundation-cancer-image-biomarker/data/csvs/luna16/luna16/test.csv" # Note: Change path to the CSV file to extract features from.
-        label: "malignancy" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 24
-        orient: False # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                - _target_: monai.transforms.Transpose ## Only for Models Genesis
-                  indices: [2, 1, 0]
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [48, 48, 48]
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
\ No newline at end of file
diff --git a/experiments/baselines/models_genesis/supervised_training/get_predictions_task3.yaml b/experiments/baselines/models_genesis/supervised_training/get_predictions_task3.yaml
deleted file mode 100644
index 1422b99..0000000
--- a/experiments/baselines/models_genesis/supervised_training/get_predictions_task3.yaml
+++ /dev/null
@@ -1,57 +0,0 @@
-trainer:
-    _target_: pytorch_lightning.Trainer
-    benchmark: True
-    max_epochs: 100
-    check_val_every_n_epoch: 4
-    accelerator: gpu
-    devices: 1
-    log_every_n_steps: 50
-    logger: False
-    callbacks:
-        - _target_: fmcib.callbacks.SavePredictions
-          path: "out.csv" # Note: Change path to the CSV file to save predictions to.
-          save_preview_samples: 5
-system:
-    _target_: lighter.LighterSystem
-    batch_size: 8
-    pin_memory: True
-    num_workers: 2
-    model:
-        _target_: fmcib.models.LoadModel
-        trunk:
-          _target_: fmcib.models.ModelsGenesisUNet3D
-          decoder: False
-        heads: [4096, 2048, 512, 256, 1] # Note: Change to [4096, 2048, 1] for Task 2 and Task 3
-        weights_path: null
-    post_criterion_activation: "$torch.sigmoid" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    # cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
-    criterion: null
-    optimizers: null
-    schedulers: null
-    train_dataset: null
-    val_dataset: null
-    test_dataset: null
-
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "/home/suraj/Repositories/foundation-cancer-image-biomarker/data/preprocessing/lung1/annotations.csv" # Note: Change path to the CSV file to extract features from.
-        label: "survival" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-        radius: 24
-        orient: False # Note: Set orient to False for task 2 and task 3
-        resample_spacing: [1, 1, 1]
-        enable_negatives: False
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:               
-                - _target_: monai.transforms.Transpose ## Only for Models Genesis
-                  indices: [2, 1, 0]
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [48, 48, 48]
-                - _target_: monai.transforms.ScaleIntensityRange
-                  a_min: -1000
-                  a_max: 1000
-                  b_min: 0.0
-                  b_max: 1.0
-                  clip: True
\ No newline at end of file
diff --git a/experiments/baselines/supervised_training/supervised_finetune.yaml b/experiments/baselines/supervised_training/supervised_finetune.yaml
index 5d0f073..8240b83 100644
--- a/experiments/baselines/supervised_training/supervised_finetune.yaml
+++ b/experiments/baselines/supervised_training/supervised_finetune.yaml
@@ -43,37 +43,45 @@ system:
         weights_path: "./models/supervised/task1_supervised.torch" 
         heads: [4096, 2048, 1]   # Note: Change to [4096, 2048, 512, 256, 1] for Task 3
 
-    post_criterion_activation: "$torch.sigmoid" 
-    cast_target_dtype_to: "$torch.float32"
+    postprocessing:
+      metrics:
+        pred:
+          - "$lambda x: torch.softmax(x, 1)" # Note: Change to $lambda x: torch.sigmoid(x) for Task 2 and Task 3    
+      criterion:
+        target: # Note: Uncomment for Task 2 and Task 3
+          - "$lambda x: x.float()"
+
+
     criterion:
         _target_: torch.nn.BCEWithLogitsLoss 
 
-    optimizers:
-        _target_: torch.optim.SGD
+    optimizer:
+        _target_: torch.optim.Adam
         params: "$@system#model.parameters()"
-        lr: "$((@system#batch_size * @trainer#devices)/256) * 0.1" # Compute LR dynamically for different batch sizes
-        weight_decay: 0.0
-        momentum: 0.9
+        # lr: "$((@system#batch_size * @trainer#devices)/256) * 0.1" # Compute LR dynamically for different batch sizes
+        # weight_decay: 0.0
+        # momentum: 0.9
 
-    schedulers:
-      scheduler:
-        _target_: torch.optim.lr_scheduler.StepLR
-        optimizer: "@system#optimizers"
-        step_size: 30
-      strict: True
+    scheduler:
+      _target_: torch.optim.lr_scheduler.StepLR
+      optimizer: "@system#optimizer"
+      step_size: 30
 
-    train_metrics: 
+    metrics:
+      train: 
         - _target_: torchmetrics.AveragePrecision
-          task: binary
-
+          task: multiclass # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
+          num_classes: 8 
         - _target_: torchmetrics.AUROC
-          task: binary 
+          task: multiclass # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
+          num_classes: 8
 
+      val: "%#train"
+      test: "%#train"
 
-    val_metrics: "%system#train_metrics"
-    test_metrics: "%system#train_metrics"
 
-    train_dataset:
+    datasets:
+      train:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: "./data/preprocessing/luna16/annotations/task2_train.csv"  # Note: Change path
         label: "malignancy" # Note: Change to appropriate label column, e.g.  "survival" for Task 3
@@ -101,7 +109,7 @@ system:
                   subtrahend: -1024
                   divisor: 3072
 
-    val_dataset:
+      val:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: "./data/preprocessing/luna16/annotations/task2_val.csv"  # Note: Change path
         label: "@system#train_dataset#label"
@@ -120,40 +128,5 @@ system:
                   subtrahend: -1024
                   divisor: 3072
                   
-    test_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/luna16/annotations/task2_test.csv"  # Note: Change path
-        label: "@system#train_dataset#label"
-        radius: "@system#train_dataset#radius"
-        orient: "@system#train_dataset#orient"
-        resample_spacing: "@system#train_dataset#resample_spacing"
-        enable_negatives: "@system#train_dataset#enable_negatives"
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
-                - _target_: monai.transforms.NormalizeIntensity
-                  subtrahend: -1024
-                  divisor: 3072        
-    
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/luna16/annotations/task2_test.csv"  # Note: Change path
-        label: "@system#train_dataset#label"
-        radius: "@system#train_dataset#radius"
-        orient: "@system#train_dataset#orient"
-        resample_spacing: "@system#train_dataset#resample_spacing"
-        enable_negatives: "@system#train_dataset#enable_negatives"
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
-                - _target_: monai.transforms.NormalizeIntensity
-                  subtrahend: -1024
-                  divisor: 3072      
\ No newline at end of file
+      test: null
+        
\ No newline at end of file
diff --git a/experiments/baselines/supervised_training/supervised_random_init.yaml b/experiments/baselines/supervised_training/supervised_random_init.yaml
index f766fed..1f7e4d2 100644
--- a/experiments/baselines/supervised_training/supervised_random_init.yaml
+++ b/experiments/baselines/supervised_training/supervised_random_init.yaml
@@ -42,39 +42,44 @@ system:
           feed_forward: False
         heads: [4096, 2048, 8] # Note: Change to [4096, 2048, 1] for Task 2 and [4096, 2048, 512, 256, 1] for Task 3
 
-    post_criterion_activation: "$torch.nn.functional.softmax" # Note: Change to $torch.sigmoid for Task 2 and Task 3
-    # cast_target_dtype_to: "$torch.float32" # Note: Uncomment for Task 2 and Task 3
+
+    postprocessing:
+      metrics:
+        pred:
+          - "$lambda x: torch.softmax(x, 1)" # Note: Change to $lambda x: torch.sigmoid(x) for Task 2 and Task 3    
+      # criterion:
+      #   target: # Note: Uncomment for Task 2 and Task 3
+      #     - "$lambda x: x.float()" 
+
     criterion:
         _target_: torch.nn.CrossEntropyLoss # Note: Change to torch.nn.BCEWithLogitsLoss for Task 2 and Task 3
-
-    optimizers:
-        _target_: torch.optim.SGD
+    
+    optimizer:
+        _target_: torch.optim.Adam
         params: "$@system#model.parameters()"
-        lr: "$((@system#batch_size * @trainer#devices)/256) * 0.1" # Compute LR dynamically for different batch sizes
-        weight_decay: 0.0
-        momentum: 0.9
+        # lr: "$((@system#batch_size * @trainer#devices)/256) * 0.1" # Compute LR dynamically for different batch sizes
+        # weight_decay: 0.0
+        # momentum: 0.9
 
-    schedulers:
-      scheduler:
-        _target_: torch.optim.lr_scheduler.StepLR
-        optimizer: "@system#optimizers"
-        step_size: 30
-      strict: True
+    scheduler:
+      _target_: torch.optim.lr_scheduler.StepLR
+      optimizer: "@system#optimizer"
+      step_size: 30
 
-    train_metrics: 
+    metrics:
+      train: 
         - _target_: torchmetrics.AveragePrecision
-          task: multiclass
-          num_classes: 8 # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
-
-        - _target_: torchmetrics.AUROC
           task: multiclass # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
           num_classes: 8 
+        - _target_: torchmetrics.AUROC
+          task: multiclass # Note: Change to `binary` for Task 2 and Task 3 and remove num_classes below
+          num_classes: 8
 
+      val: "%#train"
+      test: "%#train"
 
-    val_metrics: "%system#train_metrics"
-    test_metrics: "%system#train_metrics"
-
-    train_dataset:
+    datasets:
+      train:
         _target_: fmcib.datasets.SSLRadiomicsDataset
         path: "./data/preprocessing/deeplesion/annotations/task1_train.csv" # Note: Change path
         label: "Coarse_lesion_type" # Note: Change to appropriate label column, e.g. "malignancy" for Task 2 and "survival" for Task 3
@@ -102,59 +107,25 @@ system:
                   subtrahend: -1024
                   divisor: 3072
 
-    val_dataset:
+      val:
         _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_val.csv"  # Note: Change path
-        label: "@system#train_dataset#label"
-        radius: "@system#train_dataset#radius"
-        orient: "@system#train_dataset#orient"
-        resample_spacing: "@system#train_dataset#resample_spacing"
-        enable_negatives: "@system#train_dataset#enable_negatives"
+        path: null # Note: Change path
+        label: "@system#datasets#train#label"
+        radius: "@system#datasets#train#radius"
+        orient: "@system#datasets#train#orient"
+        resample_spacing: "@system#datasets#train#resample_spacing"
+        enable_negatives: "@system#datasets#train#enable_negatives"
         transform:
             _target_: monai.transforms.Compose
             transforms:
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
                 - _target_: monai.transforms.NormalizeIntensity
                   subtrahend: -1024
-                  divisor: 3072
-                  
-    test_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_test.csv"  # Note: Change path
-        label: "@system#train_dataset#label"
-        radius: "@system#train_dataset#radius"
-        orient: "@system#train_dataset#orient"
-        resample_spacing: "@system#train_dataset#resample_spacing"
-        enable_negatives: "@system#train_dataset#enable_negatives"
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:
+                  divisor: 3072            
                 - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
+                - _target_: monai.transforms.EnsureChannelFirst
+                  channel_dim: no_channel
                 - _target_: monai.transforms.SpatialPad
                   spatial_size: [50, 50, 50]
-                - _target_: monai.transforms.NormalizeIntensity
-                  subtrahend: -1024
-                  divisor: 3072        
-    
-    predict_dataset:
-        _target_: fmcib.datasets.SSLRadiomicsDataset
-        path: "./data/preprocessing/deeplesion/annotations/task1_test.csv"  # Note: Change path
-        label: "@system#train_dataset#label"
-        radius: "@system#train_dataset#radius"
-        orient: "@system#train_dataset#orient"
-        resample_spacing: "@system#train_dataset#resample_spacing"
-        enable_negatives: "@system#train_dataset#enable_negatives"
-        transform:
-            _target_: monai.transforms.Compose
-            transforms:
-                - _target_: monai.transforms.ToTensor
-                - _target_: monai.transforms.AddChannel
-                - _target_: monai.transforms.SpatialPad
-                  spatial_size: [50, 50, 50]
-                - _target_: monai.transforms.NormalizeIntensity
-                  subtrahend: -1024
-                  divisor: 3072
\ No newline at end of file
+
+                  
+      test: null
\ No newline at end of file
diff --git a/experiments/inference/extract_features.yaml b/experiments/inference/extract_features.yaml
index c6d61d7..4526673 100644
--- a/experiments/inference/extract_features.yaml
+++ b/experiments/inference/extract_features.yaml
@@ -25,6 +25,26 @@ system:
             feed_forward: False
         weights_path: "./model_weights.torch" # Note: Change path to the model weights file.
 
+        #### Note: Use the below config for Med3D
+        # trunk:
+        #   _target_: monai.networks.nets.resnet50
+        #   widen_factor: 1
+        #   bias_downsample: False
+        #   n_input_channels: 1
+        #   conv1_t_stride: 1
+        #   feed_forward: False
+        #   pretrained: False
+        # weights_path: "./models/pretrained/med3d/resnet_50.pth"
+
+
+        #### Note: Use the below config for Models Genesis
+        # trunk:
+        #   _target_: fmcib.models.ModelsGenesisUNet3D
+        #   decoder: False
+        # weights_path: ./models/pretrained/models_genesis/Genesis_Chest_CT.pt
+
+
+
     criterion: null
     optimizer: null
     scheduler: null
@@ -36,7 +56,7 @@ system:
             _target_: fmcib.datasets.SSLRadiomicsDataset
             path: "./data/preprocessing/deeplesion/annotations/task1_test.csv" # Note: Change path to the CSV file to extract features from.
             label: "Coarse_lesion_type" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-            radius: 25
+            radius: 25 # Note: Change to 24 for Models Genesis
             orient: True # Note: Set orient to False for task 2 and task 3
             resample_spacing: [1, 1, 1]
             enable_negatives: False
@@ -50,4 +70,30 @@ system:
                       subtrahend: -1024
                       divisor: 3072
                     - _target_: monai.transforms.SpatialPad
-                      spatial_size: [50, 50, 50]
\ No newline at end of file
+                      spatial_size: [50, 50, 50]
+
+            # transforms: #### Note: Uncomment this `transforms` and comment the above `transforms` for Med3D
+            #     - _target_: monai.transforms.ScaleIntensityRange
+            #       a_min: -1000
+            #       a_max: 1000
+            #       b_min: 0.0
+            #       b_max: 1.0
+            #       clip: True
+            #     - _target_: monai.transforms.ToTensor
+            #     - _target_: monai.transforms.AddChannel
+            #     - _target_: monai.transforms.SpatialPad
+            #       spatial_size: [50, 50, 50]
+
+            # transforms: #### Note: Uncomment this `transforms` and comment the above `transforms` for Models Genesis
+            #     - _target_: monai.transforms.Transpose ## Only for Models Genesis
+            #       indices: [2, 1, 0]
+            #     - _target_: monai.transforms.ToTensor
+            #     - _target_: monai.transforms.AddChannel
+            #     - _target_: monai.transforms.SpatialPad
+            #       spatial_size: [48, 48, 48]
+            #     - _target_: monai.transforms.ScaleIntensityRange
+            #       a_min: -1000
+            #       a_max: 1000
+            #       b_min: 0.0
+            #       b_max: 1.0
+            #       clip: True                                                           
\ No newline at end of file
diff --git a/experiments/inference/get_predictions.yaml b/experiments/inference/get_predictions.yaml
index ee4189e..c32f871 100644
--- a/experiments/inference/get_predictions.yaml
+++ b/experiments/inference/get_predictions.yaml
@@ -23,6 +23,25 @@ system:
             widen_factor: 2
             n_input_channels: 1
             feed_forward: False
+
+
+        #### Note: Use the below config for Med3D
+        # trunk:
+        #   _target_: monai.networks.nets.resnet50
+        #   widen_factor: 1
+        #   bias_downsample: False
+        #   n_input_channels: 1
+        #   conv1_t_stride: 1
+        #   feed_forward: False
+        #   pretrained: False
+        # heads: [4096, 2048, 8]  # Note: Change to [4096, 2048, 1] for Task 2 and [4096, 2048, 512, 256, 1] for Task 3
+
+
+        #### Note: Use the below config for Models Genesis
+        #   _target_: fmcib.models.ModelsGenesisUNet3D
+        #   decoder: False
+        # heads: [4096, 2048, 8]  # Note: Change to [4096, 2048, 1] for Task 2 and [4096, 2048, 512, 256, 1] for Task 3
+
         weights_path: "./models/baselines/task1/supervised.torch" # Download the models folder from HF
         heads: [4096, 2048, 8] # Note: Change to [4096, 2048, 2] for Task 2 and [4096, 2048, 512, 256, 2] for Task 3
 
@@ -46,7 +65,7 @@ system:
             _target_: fmcib.datasets.SSLRadiomicsDataset
             path: "./data/preprocessing/deeplesion/annotations/task1_test.csv" # Note: Change path to the CSV file to extract features from.
             label: "Coarse_lesion_type" # Note: Change the label to "malignancy" for task 2 and "survival" for task 3
-            radius: 25
+            radius: 25 # Note: Change to 24 for Models Genesis
             orient: True # Note: Set orient to False for task 2 and task 3
             resample_spacing: [1, 1, 1]
             enable_negatives: False
@@ -60,4 +79,30 @@ system:
                       subtrahend: -1024
                       divisor: 3072
                     - _target_: monai.transforms.SpatialPad
-                      spatial_size: [50, 50, 50]                  
\ No newline at end of file
+                      spatial_size: [50, 50, 50]   
+
+                # transforms: #### Note: Uncomment this `transforms` and comment the above `transforms` for Med3D
+                #     - _target_: monai.transforms.ScaleIntensityRange
+                #       a_min: -1000
+                #       a_max: 1000
+                #       b_min: 0.0
+                #       b_max: 1.0
+                #       clip: True
+                #     - _target_: monai.transforms.ToTensor
+                #     - _target_: monai.transforms.AddChannel
+                #     - _target_: monai.transforms.SpatialPad
+                #       spatial_size: [50, 50, 50]
+
+                # transforms: #### Note: Uncomment this `transforms` and comment the above `transforms` for Models Genesis
+                #     - _target_: monai.transforms.Transpose ## Only for Models Genesis
+                #       indices: [2, 1, 0]
+                #     - _target_: monai.transforms.ToTensor
+                #     - _target_: monai.transforms.AddChannel
+                #     - _target_: monai.transforms.SpatialPad
+                #       spatial_size: [48, 48, 48]
+                #     - _target_: monai.transforms.ScaleIntensityRange
+                #       a_min: -1000
+                #       a_max: 1000
+                #       b_min: 0.0
+                #       b_max: 1.0
+                #       clip: True                                     
\ No newline at end of file