diff --git a/adafruit_imageload/bmp/indexed.py b/adafruit_imageload/bmp/indexed.py
old mode 100644
new mode 100755
index 53e1b00..c277475
--- a/adafruit_imageload/bmp/indexed.py
+++ b/adafruit_imageload/bmp/indexed.py
@@ -17,6 +17,11 @@
 
 import sys
 
+try:
+    from bitmaptools import readinto as _bitmap_readinto
+except ImportError:
+    _bitmap_readinto = None  # pylint: disable=invalid-name
+
 
 def load(
     file,
@@ -57,7 +62,7 @@ def load(
             minimum_color_depth *= 2
 
         if sys.maxsize > 1073741823:
-            # pylint: disable=import-outside-toplevel
+            # pylint: disable=import-outside-toplevel, relative-beyond-top-level
             from .negative_height_check import negative_height_check
 
             # convert unsigned int to signed int when height is negative
@@ -81,18 +86,29 @@ def load(
             range3 = 1
 
         if compression == 0:
-            chunk = bytearray(line_size)
-            for y in range(range1, range2, range3):
-                file.readinto(chunk)
-                pixels_per_byte = 8 // color_depth
-                offset = y * width
-
-                for x in range(width):
-                    i = x // pixels_per_byte
-                    pixel = (
-                        chunk[i] >> (8 - color_depth * (x % pixels_per_byte + 1))
-                    ) & mask
-                    bitmap[offset + x] = pixel
+
+            if _bitmap_readinto:
+                _bitmap_readinto(
+                    bitmap,
+                    file,
+                    bits_per_pixel=color_depth,
+                    element_size=4,
+                    reverse_pixels_in_element=False,
+                    reverse_rows=True,
+                )
+            else:  # use the standard file.readinto
+                chunk = bytearray(line_size)
+                for y in range(range1, range2, range3):
+                    file.readinto(chunk)
+                    pixels_per_byte = 8 // color_depth
+                    offset = y * width
+
+                    for x in range(width):
+                        i = x // pixels_per_byte
+                        pixel = (
+                            chunk[i] >> (8 - color_depth * (x % pixels_per_byte + 1))
+                        ) & mask
+                        bitmap[offset + x] = pixel
         elif compression in (1, 2):
             decode_rle(
                 bitmap=bitmap,