Update README.md

README.md

@@ -115,4 +115,10 @@ mlo_images = [crop_mammo(_, crop_model, device), for _ in mlo_images]
 input_dict = [{"cc": cc_img, "mlo": mlo_img} for cc_img, mlo_img in zip(cc_images, mlo_images)]
 with torch.inference_mode():
   output = model(input_dict, device=device)
+```
+
+Note that if you are converting images from DICOM to 8-bit PNG/JPEG, it is important to apply the lookup table to the pixel values, which can be done using `pydicom.pixels.apply_voi_lut`. 
+If you have `pydicom` installed, you can also load a DICOM image directly, which handles the proper 8-bit conversion for you:
+```
+img = model.load_image_from_dicom(path_to_dicom)
 ```