diff --git a/monai/apps/detection/transforms/box_ops.py b/monai/apps/detection/transforms/box_ops.py
index d63a155e42..fb870c952e 100644
--- a/monai/apps/detection/transforms/box_ops.py
+++ b/monai/apps/detection/transforms/box_ops.py
@@ -242,6 +242,9 @@ def convert_box_to_mask(
     boxes_mask_np = np.ones((labels.shape[0],) + spatial_size, dtype=np.int16) * np.int16(bg_label)
 
     boxes_np: np.ndarray = convert_data_type(boxes, np.ndarray, dtype=np.int32)[0]
+    if np.any(boxes_np[:, spatial_dims:] > np.array(spatial_size)):
+        raise ValueError("Some boxes are larger than the image.")
+
     labels_np, *_ = convert_to_dst_type(src=labels, dst=boxes_np)
     for b in range(boxes_np.shape[0]):
         # generate a foreground mask
diff --git a/tests/test_box_transform.py b/tests/test_box_transform.py
index 94bd6ade52..e114f8869f 100644
--- a/tests/test_box_transform.py
+++ b/tests/test_box_transform.py
@@ -131,6 +131,24 @@ def test_value_3d_mask(self):
             assert_allclose(data_back["boxes"], data["boxes"], type_test=False, device_test=False, atol=1e-3)
             assert_allclose(data_back["labels"], data["labels"], type_test=False, device_test=False, atol=1e-3)
 
+    def test_shape_assertion(self):
+        test_dtype = torch.float32
+        image = np.zeros((1, 10, 10, 10))
+        boxes = np.array([[7, 8, 9, 10, 12, 13]])
+        data = {"image": image, "boxes": boxes, "labels": np.array((1,))}
+        data = CastToTyped(keys=["image", "boxes"], dtype=test_dtype)(data)
+        transform_to_mask = BoxToMaskd(
+            box_keys="boxes",
+            box_mask_keys="box_mask",
+            box_ref_image_keys="image",
+            label_keys="labels",
+            min_fg_label=0,
+            ellipse_mask=False,
+        )
+        with self.assertRaises(ValueError) as context:
+            transform_to_mask(data)
+        self.assertTrue("Some boxes are larger than the image." in str(context.exception))
+
     @parameterized.expand(TESTS_3D)
     def test_value_3d(
         self,