fix: resolve all mypy and CodeRabbit issues

Signed-off-by: Rusheel Sharma <rusheelhere@gmail.com>

Author: Rusheel86

monai/metrics/generalized_dice.py

@@ -74,7 +74,8 @@ def _compute_tensor(self, y_pred: torch.Tensor, y: torch.Tensor) -> torch.Tensor
             y_pred (torch.Tensor): Binarized segmentation model output. It must be in one-hot format and in the NCHW[D] format,
                 where N is the batch dimension, C is the channel dimension, and the remaining are the spatial dimensions.
             y (torch.Tensor): Binarized ground-truth. It must be in one-hot format and have the same shape as `y_pred`.
-            ignore_index: class index to ignore from the metric computation.
+        Note:
+            The ignore_index for this computation is taken from self.ignore_index if set during initialization.
 
         Returns:
             torch.Tensor: Generalized Dice Score averaged across batch and class

monai/metrics/utils.py

@@ -318,7 +318,7 @@ def get_surface_distance(
 
     dis = convert_to_dst_type(dis, seg_pred, dtype=lib.float32)[0]
     if isinstance(seg_pred, torch.Tensor):
-        return dis[seg_pred.bool()]  # type: ignore[union-attr]
+        return dis[seg_pred.bool()]  # type: ignore[union-attr,no-any-return]
     else:
         # NumPy array
         return dis[seg_pred.astype(bool)]  # type: ignore[union-attr,no-any-return]
@@ -352,7 +352,6 @@ def get_edge_surface_distance(
             This will return the areas of the edges.
         symmetric: whether to compute the surface distance from `y_pred` to `y` and from `y` to `y_pred`.
         class_index: The class-index used for context when warning about empty ground truth or prediction.
-        mask: optional boolean mask indicating valid pixels.
 
     Returns:
         (edges_pred, edges_gt), (distances_pred_to_gt, [distances_gt_to_pred]), (areas_pred, areas_gt) | tuple()
@@ -365,14 +364,6 @@ def get_edge_surface_distance(
     edge_results = get_mask_edges(y_pred, y, crop=True, spacing=edges_spacing, always_return_as_numpy=False)
     edges_pred, edges_gt = edge_results[0], edge_results[1]
 
-    if mask is not None:
-        if len(edge_results) > 2 and isinstance(edge_results[2], tuple):
-            slices = edge_results[2]
-            mask = mask[slices]
-            mask = torch.as_tensor(mask, device=edges_pred.device, dtype=torch.bool)
-            edges_pred = edges_pred & mask
-            edges_gt = edges_gt & mask
-
     distances_raw: tuple[torch.Tensor, torch.Tensor] | tuple[torch.Tensor]
     if symmetric:
         distances_raw = (
@@ -382,7 +373,7 @@ def get_edge_surface_distance(
     else:
         distances_raw = (get_surface_distance(edges_pred, edges_gt, distance_metric, spacing),)  # type: ignore
 
-    distances_list = [d if d is not None else edges_pred.new_empty((0,)) for d in distances_raw]
+    distances_list = list(distances_raw)
     distances: tuple[torch.Tensor, torch.Tensor] | tuple[torch.Tensor] = (
         tuple(distances_list) if len(distances_list) == 2 else (distances_list[0],)  # type: ignore[assignment]
     )