diff --git a/cvat-ui/src/utils/dextr-utils.ts b/cvat-ui/src/utils/dextr-utils.ts
index 9e815374201e..2a0b1e03ec80 100644
--- a/cvat-ui/src/utils/dextr-utils.ts
+++ b/cvat-ui/src/utils/dextr-utils.ts
@@ -199,7 +199,9 @@ const plugin: DEXTRPlugin = {
                                     // eslint-disable-next-line no-param-reassign
                                     self.data.canceled = false;
                                     antModalButton.disabled = true;
-                                    document.body.removeChild(antModalRoot);
+                                    if (antModalRoot.parentElement === document.body) {
+                                        document.body.removeChild(antModalRoot);
+                                    }
                                 }
                             },
                         },
diff --git a/cvat/apps/dextr_segmentation/dextr.py b/cvat/apps/dextr_segmentation/dextr.py
index c51eeaba134b..9bb3f3ba3112 100644
--- a/cvat/apps/dextr_segmentation/dextr.py
+++ b/cvat/apps/dextr_segmentation/dextr.py
@@ -50,7 +50,7 @@ def handle(self, db_data, frame, points):
         points = np.asarray([[int(p["x"]), int(p["y"])] for p in points], dtype=int)
 
         # Padding mustn't be more than the closest distance to an edge of an image
-        [width, height] = numpy_image.shape[:2]
+        [height, width] = numpy_image.shape[:2]
         x_values = points[:, 0]
         y_values = points[:, 1]
         [min_x, max_x] = [np.min(x_values), np.max(x_values)]
@@ -59,8 +59,8 @@ def handle(self, db_data, frame, points):
         bounding_box = (
             max(min(points[:, 0]) - padding, 0),
             max(min(points[:, 1]) - padding, 0),
-            min(max(points[:, 0]) + padding, numpy_image.shape[1] - 1),
-            min(max(points[:, 1]) + padding, numpy_image.shape[0] - 1)
+            min(max(points[:, 0]) + padding, width - 1),
+            min(max(points[:, 1]) + padding, height - 1)
         )
 
         # Prepare an image