added new scaling based on uk biobank stats

solver.py

@@ -90,8 +90,6 @@ class Solver():
             self.loss_function = loss_function
             self.MSE = MSELoss()
 
-        # self.loss_function = loss_function
-
         self.model_name = model_name
         self.labels = labels
         self.number_epochs = number_epochs

utils/data_evaluation_utils.py

@@ -406,11 +406,14 @@ def _scale_input(volume, scaling_factors):
         scaled_volume (np.array): Scaled volume
     """
 
-    with open(scaling_factors, 'rb') as input_file:
-        min_value, max_value, _, _ = pickle.load(input_file)
+    # with open(scaling_factors, 'rb') as input_file:
+    #     min_value, max_value, _, _ = pickle.load(input_file)
 
     # Steve Scaling
-        min_value, max_value, _, _ = [0.0, 0.2, 0.0, 10.0]
+    # min_value, max_value, _, _ = [0.0, 0.2, 0.0, 10.0]
+
+    # Andrei Scaling
+    min_value, max_value, _, _ = [-0.0539, 0.0969, -12.094, 14.6319]
 
     # Eliminating outliers
     volume[volume > max_value] = max_value
@@ -419,8 +422,7 @@ def _scale_input(volume, scaling_factors):
     # Normalization to [0, 1]
     # scaled_volume = np.divide(np.subtract(volume, min_value), np.subtract(max_value, min_value))
     # Scaling between [-1, 1]
-    scaled_volume = np.add(-1.0, np.multiply(2.0, np.divide(
-        np.subtract(volume, min_value), np.subtract(max_value, min_value))))
+    scaled_volume = np.add(-1.0, np.multiply(2.0, np.divide(np.subtract(volume, min_value), np.subtract(max_value, min_value))))
 
     return scaled_volume
 
@@ -463,17 +465,19 @@ def _rescale_output(volume, scaling_factors):
         rescaled_volume (np.array): Rescaled volume
     """
 
-    with open(scaling_factors, 'rb') as input_file:
-        _, _, min_value, max_value = pickle.load(input_file)
+    # with open(scaling_factors, 'rb') as input_file:
+    #     _, _, min_value, max_value = pickle.load(input_file)
 
     # Steve Scaling
-        _, _, min_value, max_value = [0.0, 0.2, 0.0, 10.0]
+    # _, _, min_value, max_value = [0.0, 0.2, 0.0, 10.0]
+
+    # Andrei Scaling
+    _, _, min_value, max_value = [-0.0539, 0.0969, -12.094, 14.6319]
 
     # Normalization to [0, 1]
     # rescaled_volume = np.add(np.multiply(volume, np.subtract(max_value, min_value)), min_value)
     # Scaling between [-1, 1]
-    rescaled_volume = np.add(np.multiply(
-        np.divide(np.add(volume, 1), 2), np.subtract(max_value, min_value)), min_value)
+    rescaled_volume = np.add(np.multiply(np.divide(np.add(volume, 1), 2), np.subtract(max_value, min_value)), min_value)
 
     return rescaled_volume
 

utils/data_utils.py

@@ -486,12 +486,14 @@ class DataMapper(data.Dataset):
             scaled_volume (np.array): Scaled volume
         """
 
-        with open(self.scaling_factors, 'rb') as input_file:
-            min_input, max_input, min_target, max_target = pickle.load(
-                input_file)
+        # with open(self.scaling_factors, 'rb') as input_file:
+            # min_input, max_input, min_target, max_target = pickle.load(input_file)
 
-        # Steve Scaling
-        min_input, max_input, min_target, max_target = [0.0, 0.2, 0.0, 10.0]
+        # # Steve Scaling
+        # min_input, max_input, min_target, max_target = [0.0, 0.2, 0.0, 10.0]
+
+        # Andrei Scaling
+        min_input, max_input, min_target, max_target = [-0.0539, 0.0969, -12.094, 14.6319]
 
         if target_flag == False:
             min_value = min_input
@@ -501,15 +503,14 @@ class DataMapper(data.Dataset):
             max_value = max_target
 
         # Set all negative elements to 0
-        volume[volume < 0] = 0.0
+        # volume[volume < 0] = 0.0
 
         # Eliminating outliers
         volume[volume > max_value] = max_value
         volume[volume < min_value] = min_value
 
         # Normalization to [0, 1]
-        scaled_volume = np.divide(np.subtract(
-            volume, min_value), np.subtract(max_value, min_value))
+        scaled_volume = np.divide(np.subtract(volume, min_value), np.subtract(max_value, min_value))
         # Scaling between [-1, 1]
         # scaled_volume = np.add(-1.0, np.multiply(2.0, np.divide(np.subtract(volume, min_value), np.subtract(max_value, min_value))))