diff --git a/monai/transforms/compose.py b/monai/transforms/compose.py
index 04fb12b463..45e706e143 100644
--- a/monai/transforms/compose.py
+++ b/monai/transforms/compose.py
@@ -221,7 +221,10 @@ def __init__(
         elif weights is None or isinstance(weights, float):
             weights = [1.0 / len(self.transforms)] * len(self.transforms)
         if len(weights) != len(self.transforms):
-            raise AssertionError("transforms and weights should be same size if both specified as sequences.")
+            raise ValueError(
+                "transforms and weights should be same size if both specified as sequences, "
+                f"got {len(weights)} and {len(self.transforms)}."
+            )
         self.weights = ensure_tuple(self._normalize_probabilities(weights))
 
     def _normalize_probabilities(self, weights):
@@ -229,9 +232,9 @@ def _normalize_probabilities(self, weights):
             return weights
         weights = np.array(weights)
         if np.any(weights < 0):
-            raise AssertionError("Probabilities must be greater than or equal to zero.")
+            raise ValueError(f"Probabilities must be greater than or equal to zero, got {weights}.")
         if np.all(weights == 0):
-            raise AssertionError("At least one probability must be greater than zero.")
+            raise ValueError(f"At least one probability must be greater than zero, got {weights}.")
         weights = weights / weights.sum()
         return list(weights)
 
@@ -278,7 +281,9 @@ def inverse(self, data):
                 if isinstance(data[key], monai.data.MetaTensor) or self.trace_key(key) in data:
                     index = self.pop_transform(data, key)[TraceKeys.EXTRA_INFO]["index"]
         else:
-            raise RuntimeError("Inverse only implemented for Mapping (dictionary) or MetaTensor data.")
+            raise RuntimeError(
+                f"Inverse only implemented for Mapping (dictionary) or MetaTensor data, got type {type(data)}."
+            )
         if index is None:
             # no invertible transforms have been applied
             return data
@@ -342,7 +347,9 @@ def inverse(self, data):
                 if isinstance(data[key], monai.data.MetaTensor) or self.trace_key(key) in data:
                     applied_order = self.pop_transform(data, key)[TraceKeys.EXTRA_INFO]["applied_order"]
         else:
-            raise RuntimeError("Inverse only implemented for Mapping (dictionary) or MetaTensor data.")
+            raise RuntimeError(
+                f"Inverse only implemented for Mapping (dictionary) or MetaTensor data, got type {type(data)}."
+            )
         if applied_order is None:
             # no invertible transforms have been applied
             return data
diff --git a/monai/transforms/croppad/batch.py b/monai/transforms/croppad/batch.py
index 095edbadf6..bd8e7bf50f 100644
--- a/monai/transforms/croppad/batch.py
+++ b/monai/transforms/croppad/batch.py
@@ -117,7 +117,7 @@ def __call__(self, batch: Any):
     @staticmethod
     def inverse(data: dict) -> dict[Hashable, np.ndarray]:
         if not isinstance(data, Mapping):
-            raise RuntimeError("Inverse can only currently be applied on dictionaries.")
+            raise RuntimeError(f"Inverse can only currently be applied on dictionaries, got type {type(data)}.")
 
         d = dict(data)
         for key in d:
diff --git a/monai/transforms/intensity/array.py b/monai/transforms/intensity/array.py
index 1980ef508b..c22eed3b65 100644
--- a/monai/transforms/intensity/array.py
+++ b/monai/transforms/intensity/array.py
@@ -206,12 +206,12 @@ def __call__(self, img: NdarrayOrTensor, randomize: bool = True) -> NdarrayOrTen
                 img[i] = self._add_noise(d, mean=_mean[i], std=_std[i] * d.std() if self.relative else _std[i])
         else:
             if not isinstance(self.mean, (int, float)):
-                raise RuntimeError("If channel_wise is False, mean must be a float or int number.")
+                raise RuntimeError(f"If channel_wise is False, mean must be a float or int, got {type(self.mean)}.")
             if not isinstance(self.std, (int, float)):
-                raise RuntimeError("If channel_wise is False, std must be a float or int number.")
+                raise RuntimeError(f"If channel_wise is False, std must be a float or int, got {type(self.std)}.")
             std = self.std * img.std().item() if self.relative else self.std
             if not isinstance(std, (int, float)):
-                raise RuntimeError("std must be a float or int number.")
+                raise RuntimeError(f"std must be a float or int number, got {type(std)}.")
             img = self._add_noise(img, mean=self.mean, std=std)
         return img
 
@@ -265,7 +265,7 @@ def __init__(self, offsets: tuple[float, float] | float, safe: bool = False, pro
         if isinstance(offsets, (int, float)):
             self.offsets = (min(-offsets, offsets), max(-offsets, offsets))
         elif len(offsets) != 2:
-            raise ValueError("offsets should be a number or pair of numbers.")
+            raise ValueError(f"offsets should be a number or pair of numbers, got {offsets}.")
         else:
             self.offsets = (min(offsets), max(offsets))
         self._offset = self.offsets[0]
@@ -381,7 +381,7 @@ def __init__(
         if isinstance(factors, (int, float)):
             self.factors = (min(-factors, factors), max(-factors, factors))
         elif len(factors) != 2:
-            raise ValueError("factors should be a number or pair of numbers.")
+            raise ValueError(f"factors should be a number or pair of numbers, got {factors}.")
         else:
             self.factors = (min(factors), max(factors))
         self.factor = self.factors[0]
@@ -488,7 +488,7 @@ def __init__(self, factors: tuple[float, float] | float, prob: float = 0.1, dtyp
         if isinstance(factors, (int, float)):
             self.factors = (min(-factors, factors), max(-factors, factors))
         elif len(factors) != 2:
-            raise ValueError("factors should be a number or pair of numbers.")
+            raise ValueError(f"factors should be a number or pair of numbers, got {factors}.")
         else:
             self.factors = (min(factors), max(factors))
         self.factor = self.factors[0]
@@ -545,7 +545,7 @@ def __init__(
     ) -> None:
         RandomizableTransform.__init__(self, prob)
         if degree < 1:
-            raise ValueError("degree should be no less than 1.")
+            raise ValueError(f"degree should be no less than 1, got {degree}.")
         self.degree = degree
         self.coeff_range = coeff_range
         self.dtype = dtype
@@ -725,7 +725,7 @@ class ThresholdIntensity(Transform):
 
     def __init__(self, threshold: float, above: bool = True, cval: float = 0.0) -> None:
         if not isinstance(threshold, (int, float)):
-            raise ValueError("threshold must be a float or int number.")
+            raise ValueError(f"threshold must be a float or int number, got {type(threshold)} {threshold}.")
         self.threshold = threshold
         self.above = above
         self.cval = cval
@@ -812,7 +812,7 @@ class AdjustContrast(Transform):
 
     def __init__(self, gamma: float) -> None:
         if not isinstance(gamma, (int, float)):
-            raise ValueError("gamma must be a float or int number.")
+            raise ValueError(f"gamma must be a float or int number, got {type(gamma)} {gamma}.")
         self.gamma = gamma
 
     def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
@@ -847,7 +847,7 @@ def __init__(self, prob: float = 0.1, gamma: Sequence[float] | float = (0.5, 4.5
         if isinstance(gamma, (int, float)):
             if gamma <= 0.5:
                 raise ValueError(
-                    "if gamma is single number, must greater than 0.5 and value is picked from (0.5, gamma)"
+                    f"if gamma is a number, must greater than 0.5 and value is picked from (0.5, gamma), got {gamma}"
                 )
             self.gamma = (0.5, gamma)
         elif len(gamma) != 2:
diff --git a/monai/transforms/io/array.py b/monai/transforms/io/array.py
index 5e7e3cff88..a91f21e220 100644
--- a/monai/transforms/io/array.py
+++ b/monai/transforms/io/array.py
@@ -289,7 +289,7 @@ def __call__(self, filename: Sequence[PathLike] | PathLike, reader: ImageReader
         img_array, meta_data = reader.get_data(img)
         img_array = convert_to_dst_type(img_array, dst=img_array, dtype=self.dtype)[0]
         if not isinstance(meta_data, dict):
-            raise ValueError("`meta_data` must be a dict.")
+            raise ValueError(f"`meta_data` must be a dict, got type {type(meta_data)}.")
         # make sure all elements in metadata are little endian
         meta_data = switch_endianness(meta_data, "<")
 
diff --git a/monai/transforms/io/dictionary.py b/monai/transforms/io/dictionary.py
index 407ca24716..9f75444dc6 100644
--- a/monai/transforms/io/dictionary.py
+++ b/monai/transforms/io/dictionary.py
@@ -142,7 +142,9 @@ def __init__(
             raise TypeError(f"meta_key_postfix must be a str but is {type(meta_key_postfix).__name__}.")
         self.meta_keys = ensure_tuple_rep(None, len(self.keys)) if meta_keys is None else ensure_tuple(meta_keys)
         if len(self.keys) != len(self.meta_keys):
-            raise ValueError("meta_keys should have the same length as keys.")
+            raise ValueError(
+                f"meta_keys should have the same length as keys, got {len(self.keys)} and {len(self.meta_keys)}."
+            )
         self.meta_key_postfix = ensure_tuple_rep(meta_key_postfix, len(self.keys))
         self.overwriting = overwriting
 
@@ -162,10 +164,12 @@ def __call__(self, data, reader: ImageReader | None = None):
                 d[key] = data
             else:
                 if not isinstance(data, (tuple, list)):
-                    raise ValueError("loader must return a tuple or list (because image_only=False was used).")
+                    raise ValueError(
+                        f"loader must return a tuple or list (because image_only=False was used), got {type(data)}."
+                    )
                 d[key] = data[0]
                 if not isinstance(data[1], dict):
-                    raise ValueError("metadata must be a dict.")
+                    raise ValueError(f"metadata must be a dict, got {type(data[1])}.")
                 meta_key = meta_key or f"{key}_{meta_key_postfix}"
                 if meta_key in d and not self.overwriting:
                     raise KeyError(f"Metadata with key {meta_key} already exists and overwriting=False.")
diff --git a/monai/transforms/post/array.py b/monai/transforms/post/array.py
index a514c43536..8e0c642d8b 100644
--- a/monai/transforms/post/array.py
+++ b/monai/transforms/post/array.py
@@ -216,7 +216,7 @@ def __call__(
         to_onehot = self.to_onehot if to_onehot is None else to_onehot
         if to_onehot is not None:
             if not isinstance(to_onehot, int):
-                raise ValueError("the number of classes for One-Hot must be an integer.")
+                raise ValueError(f"the number of classes for One-Hot must be an integer, got {type(to_onehot)}.")
             img_t = one_hot(
                 img_t, num_classes=to_onehot, dim=self.kwargs.get("dim", 0), dtype=self.kwargs.get("dtype", torch.float)
             )
diff --git a/monai/transforms/spatial/array.py b/monai/transforms/spatial/array.py
index 947ef05650..e26a15e1dc 100644
--- a/monai/transforms/spatial/array.py
+++ b/monai/transforms/spatial/array.py
@@ -1639,7 +1639,9 @@ def __init__(
         self.min_zoom = ensure_tuple(min_zoom)
         self.max_zoom = ensure_tuple(max_zoom)
         if len(self.min_zoom) != len(self.max_zoom):
-            raise AssertionError("min_zoom and max_zoom must have same length.")
+            raise ValueError(
+                f"min_zoom and max_zoom must have same length, got {len(self.min_zoom)} and {len(self.max_zoom)}."
+            )
         self.mode: InterpolateMode = look_up_option(mode, InterpolateMode)
         self.padding_mode = padding_mode
         self.align_corners = align_corners
diff --git a/monai/transforms/transform.py b/monai/transforms/transform.py
index 470f72566c..9dd87ecf83 100644
--- a/monai/transforms/transform.py
+++ b/monai/transforms/transform.py
@@ -329,7 +329,7 @@ def lazy_evaluation(self):
     @lazy_evaluation.setter
     def lazy_evaluation(self, lazy_evaluation: bool):
         if not isinstance(lazy_evaluation, bool):
-            raise TypeError("'lazy_evaluation must be a bool but is of " f"type {type(lazy_evaluation)}'")
+            raise TypeError(f"lazy_evaluation must be a bool but is of type {type(lazy_evaluation)}")
         self.lazy_evaluation = lazy_evaluation
 
 
diff --git a/monai/transforms/utility/array.py b/monai/transforms/utility/array.py
index d1e07f7b88..44aecb94d9 100644
--- a/monai/transforms/utility/array.py
+++ b/monai/transforms/utility/array.py
@@ -161,7 +161,7 @@ class AsChannelFirst(Transform):
 
     def __init__(self, channel_dim: int = -1) -> None:
         if not (isinstance(channel_dim, int) and channel_dim >= -1):
-            raise AssertionError("invalid channel dimension.")
+            raise ValueError(f"invalid channel dimension ({channel_dim}).")
         self.channel_dim = channel_dim
 
     def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
@@ -191,7 +191,7 @@ class AsChannelLast(Transform):
 
     def __init__(self, channel_dim: int = 0) -> None:
         if not (isinstance(channel_dim, int) and channel_dim >= -1):
-            raise AssertionError("invalid channel dimension.")
+            raise ValueError(f"invalid channel dimension ({channel_dim}).")
         self.channel_dim = channel_dim
 
     def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
@@ -303,7 +303,7 @@ class RepeatChannel(Transform):
 
     def __init__(self, repeats: int) -> None:
         if repeats <= 0:
-            raise AssertionError("repeats count must be greater than 0.")
+            raise ValueError(f"repeats count must be greater than 0, got {repeats}.")
         self.repeats = repeats
 
     def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
@@ -328,7 +328,7 @@ class RemoveRepeatedChannel(Transform):
 
     def __init__(self, repeats: int) -> None:
         if repeats <= 0:
-            raise AssertionError("repeats count must be greater than 0.")
+            raise ValueError(f"repeats count must be greater than 0, got {repeats}.")
 
         self.repeats = repeats
 
@@ -337,7 +337,7 @@ def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
         Apply the transform to `img`, assuming `img` is a "channel-first" array.
         """
         if img.shape[0] < 2:
-            raise AssertionError("Image must have more than one channel")
+            raise ValueError(f"Image must have more than one channel, got {img.shape[0]} channels.")
 
         out: NdarrayOrTensor = convert_to_tensor(img[:: self.repeats, :], track_meta=get_track_meta())
         return out
@@ -718,7 +718,7 @@ def __init__(
 
         """
         if not isinstance(prefix, str):
-            raise AssertionError("prefix must be a string.")
+            raise ValueError(f"prefix must be a string, got {type(prefix)}.")
         self.prefix = prefix
         self.data_type = data_type
         self.data_shape = data_shape
diff --git a/monai/transforms/utils.py b/monai/transforms/utils.py
index e2cc7ed905..6560899318 100644
--- a/monai/transforms/utils.py
+++ b/monai/transforms/utils.py
@@ -401,7 +401,7 @@ def weighted_patch_samples(
 
     """
     if w is None:
-        raise ValueError("w must be an ND array.")
+        raise ValueError("w must be an ND array, got None.")
     if r_state is None:
         r_state = np.random.RandomState()
     img_size = np.asarray(w.shape, dtype=int)
@@ -447,7 +447,10 @@ def correct_crop_centers(
     spatial_size = fall_back_tuple(spatial_size, default=label_spatial_shape)
     if any(np.subtract(label_spatial_shape, spatial_size) < 0):
         if not allow_smaller:
-            raise ValueError("The size of the proposed random crop ROI is larger than the image size.")
+            raise ValueError(
+                "The size of the proposed random crop ROI is larger than the image size, "
+                f"got ROI size {spatial_size} and label image size {label_spatial_shape} respectively."
+            )
         spatial_size = tuple(min(l, s) for l, s in zip(label_spatial_shape, spatial_size))
 
     # Select subregion to assure valid roi
@@ -555,12 +558,14 @@ def generate_label_classes_crop_centers(
         rand_state = np.random.random.__self__  # type: ignore
 
     if num_samples < 1:
-        raise ValueError("num_samples must be an int number and greater than 0.")
+        raise ValueError(f"num_samples must be an int number and greater than 0, got {num_samples}.")
     ratios_: list[float | int] = ([1] * len(indices)) if ratios is None else ratios
     if len(ratios_) != len(indices):
-        raise ValueError("random crop ratios must match the number of indices of classes.")
+        raise ValueError(
+            f"random crop ratios must match the number of indices of classes, got {len(ratios_)} and {len(indices)}."
+        )
     if any(i < 0 for i in ratios_):
-        raise ValueError("ratios should not contain negative number.")
+        raise ValueError(f"ratios should not contain negative number, got {ratios_}.")
 
     for i, array in enumerate(indices):
         if len(array) == 0:
@@ -925,7 +930,7 @@ def generate_spatial_bounding_box(
     margin = ensure_tuple_rep(margin, ndim)
     for m in margin:
         if m < 0:
-            raise ValueError("margin value should not be negative number.")
+            raise ValueError(f"margin value should not be negative number, got {margin}.")
 
     box_start = [0] * ndim
     box_end = [0] * ndim
@@ -1065,7 +1070,7 @@ def get_unique_labels(img: NdarrayOrTensor, is_onehot: bool, discard: int | Iter
         applied_labels = {i for i, s in enumerate(img) if s.sum() > 0}
     else:
         if n_channels != 1:
-            raise ValueError("If input not one-hotted, should only be 1 channel.")
+            raise ValueError(f"If input not one-hotted, should only be 1 channel, got {n_channels}.")
         applied_labels = set(unique(img).tolist())
     if discard is not None:
         for i in ensure_tuple(discard):