4540 Add example in the doc of metrics

monai/metrics/confusion_matrix.py

@@ -32,6 +32,8 @@ class ConfusionMatrixMetric(CumulativeIterationMetric):
     segmentations are small compared to the total image size they can get overwhelmed by the signal from the
     background.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         include_background: whether to skip metric computation on the first channel of
             the predicted output. Defaults to True.

monai/metrics/generalized_dice.py

@@ -29,6 +29,8 @@ class GeneralizedDiceScore(CumulativeIterationMetric):
     The inputs `y_pred` and `y` are expected to be one-hot, binarized channel-first
     or batch-first tensors, i.e., CHW[D] or BCHW[D].
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         include_background (bool, optional): whether to include the background class (assumed to be in channel 0), in the
             score computation. Defaults to True.

monai/metrics/hausdorff_distance.py

@@ -39,6 +39,8 @@ class HausdorffDistanceMetric(CumulativeIterationMetric):
     `y_preds` and `y` can be a list of channel-first Tensor (CHW[D]) or a batch-first Tensor (BCHW[D]).
     The implementation refers to `DeepMind's implementation <https://github.com/deepmind/surface-distance>`_.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         include_background: whether to include distance computation on the first channel of
             the predicted output. Defaults to ``False``.

monai/metrics/meandice.py

@@ -31,6 +31,8 @@ class DiceMetric(CumulativeIterationMetric):
     background.
     `y_preds` and `y` can be a list of channel-first Tensor (CHW[D]) or a batch-first Tensor (BCHW[D]).
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         include_background: whether to skip Dice computation on the first channel of
             the predicted output. Defaults to ``True``.

monai/metrics/meaniou.py

@@ -31,6 +31,8 @@ class MeanIoU(CumulativeIterationMetric):
     background.
     `y_pred` and `y` can be a list of channel-first Tensor (CHW[D]) or a batch-first Tensor (BCHW[D]).
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         include_background: whether to skip IoU computation on the first channel of
             the predicted output. Defaults to ``True``.

monai/metrics/regression.py

@@ -30,6 +30,8 @@ class RegressionMetric(CumulativeIterationMetric):
     Both `y_pred` and `y` are expected to be real-valued, where `y_pred` is output from a regression model.
     `y_preds` and `y` can be a list of channel-first Tensor (CHW[D]) or a batch-first Tensor (BCHW[D]).
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         reduction: define mode of reduction to the metrics, will only apply reduction on `not-nan` values,
             available reduction modes: {``"none"``, ``"mean"``, ``"sum"``, ``"mean_batch"``, ``"sum_batch"``,
@@ -90,6 +92,8 @@ class MSEMetric(RegressionMetric):
     Input `y_pred` is compared with ground truth `y`.
     Both `y_pred` and `y` are expected to be real-valued, where `y_pred` is output from a regression model.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         reduction: define the mode to reduce metrics, will only execute reduction on `not-nan` values,
             available reduction modes: {``"none"``, ``"mean"``, ``"sum"``, ``"mean_batch"``, ``"sum_batch"``,
@@ -122,6 +126,8 @@ class MAEMetric(RegressionMetric):
     Input `y_pred` is compared with ground truth `y`.
     Both `y_pred` and `y` are expected to be real-valued, where `y_pred` is output from a regression model.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         reduction: define the mode to reduce metrics, will only execute reduction on `not-nan` values,
             available reduction modes: {``"none"``, ``"mean"``, ``"sum"``, ``"mean_batch"``, ``"sum_batch"``,
@@ -155,6 +161,8 @@ class RMSEMetric(RegressionMetric):
     Input `y_pred` is compared with ground truth `y`.
     Both `y_pred` and `y` are expected to be real-valued, where `y_pred` is output from a regression model.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         reduction: define the mode to reduce metrics, will only execute reduction on `not-nan` values,
             available reduction modes: {``"none"``, ``"mean"``, ``"sum"``, ``"mean_batch"``, ``"sum_batch"``,
@@ -192,6 +200,8 @@ class PSNRMetric(RegressionMetric):
     Input `y_pred` is compared with ground truth `y`.
     Both `y_pred` and `y` are expected to be real-valued, where `y_pred` is output from a regression model.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         max_val: The dynamic range of the images/volumes (i.e., the difference between the
             maximum and the minimum allowed values e.g. 255 for a uint8 image).

monai/metrics/rocauc.py

@@ -27,6 +27,8 @@ class ROCAUCMetric(CumulativeIterationMetric):
     sklearn.metrics.roc_auc_score.html#sklearn.metrics.roc_auc_score>`_.
     The input `y_pred` and `y` can be a list of `channel-first` Tensor or a `batch-first` Tensor.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         average: {``"macro"``, ``"weighted"``, ``"micro"``, ``"none"``}
             Type of averaging performed if not binary classification.

monai/metrics/surface_dice.py

@@ -30,6 +30,8 @@ class SurfaceDiceMetric(CumulativeIterationMetric):
 
     The class- and batch sample-wise NSD values can be aggregated with the function `aggregate`.
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         class_thresholds: List of class-specific thresholds.
             The thresholds relate to the acceptable amount of deviation in the segmentation boundary in pixels.

monai/metrics/surface_distance.py

@@ -36,6 +36,8 @@ class SurfaceDistanceMetric(CumulativeIterationMetric):
     You can use suitable transforms in ``monai.transforms.post`` first to achieve binarized values.
     `y_preds` and `y` can be a list of channel-first Tensor (CHW[D]) or a batch-first Tensor (BCHW[D]).
 
+    Example of the typical execution steps of this metric class follows :py:class:`monai.metrics.metric.Cumulative`.
+
     Args:
         include_background: whether to skip distance computation on the first channel of
             the predicted output. Defaults to ``False``.