Merge pull request #959 from benmalef/change_lib_from_tiffslide_to_op…

…enslide

Add support for DICOM WSI by using OpenSlide

Dockerfile-CPU

@@ -32,7 +32,7 @@ CMD run
 # See https://github.com/hexops/dockerfile as a best practices guide.
 #RUN addgroup --gid 10001 --system nonroot \
 # && adduser  --uid 10000 --system --ingroup nonroot --home /home/nonroot nonroot
-# 
+#
 #USER nonroot
 
 # Prepare the container for possible model embedding later.

Dockerfile-ROCm

@@ -36,7 +36,7 @@ CMD run
 # See https://github.com/hexops/dockerfile as a best practices guide.
 #RUN addgroup --gid 10001 --system nonroot \
 # && adduser  --uid 10000 --system --ingroup nonroot --home /home/nonroot nonroot
-# 
+#
 #USER nonroot
 
 # Prepare the container for possible model embedding later.

GANDLF/compute/inference_loop.py

@@ -15,7 +15,7 @@
 from skimage.io import imsave
 from tqdm import tqdm
 from torch.cuda.amp import autocast
-import tiffslide as openslide
+import openslide
 from GANDLF.data import get_testing_loader
 from GANDLF.utils import (
     best_model_path_end,
@@ -344,11 +344,13 @@ def inference_loop(
                         )
                         cv2.imwrite(file_to_write, heatmaps[key])
 
-                        os_image_array = os_image.read_region(
-                            (0, 0),
-                            parameters["slide_level"],
-                            (level_width, level_height),
-                            as_array=True,
+                        # this is needed because openslide returns an RGBA image
+                        os_image_array = np.asarray(
+                            os_image.read_region(
+                                (0, 0),
+                                parameters["slide_level"],
+                                (level_width, level_height),
+                            ).convert("RGB")
                         )
                         blended_image = cv2.addWeighted(
                             os_image_array,

GANDLF/data/inference_dataloader_histopath.py

@@ -1,7 +1,7 @@
 import os
 from typing import Optional
 import numpy as np
-import tiffslide
+import openslide
 from GANDLF.data.patch_miner.opm.utils import get_patch_size_in_microns, tissue_mask
 from skimage.transform import resize
 from torch.utils.data.dataset import Dataset
@@ -51,7 +51,7 @@ def __init__(
         self._stride_size = get_patch_size_in_microns(wsi_path, self._stride_size)
         self._selected_level = selected_level
         self._mask_level = mask_level
-        self._os_image = tiffslide.open_slide(os.path.join(self._wsi_path))
+        self._os_image = openslide.open_slide(os.path.join(self._wsi_path))
         self._points = []
         self._basic_preprocessing()
 
@@ -61,11 +61,13 @@ def _basic_preprocessing(self):
         try:
             mask_xdim, mask_ydim = self._os_image.level_dimensions[self._mask_level]
             mask = get_tissue_mask(
-                self._os_image.read_region(
-                    (0, 0), self._mask_level, (mask_xdim, mask_ydim), as_array=True
+                # this is needed because openslide returns an RGBA image
+                np.asarray(
+                    self._os_image.read_region(
+                        (0, 0), self._mask_level, (mask_xdim, mask_ydim)
+                    ).convert("RGB")
                 )
             )
-
             if self._selected_level != self._mask_level:
                 mask = resize(mask, (height, width))
             mask = (mask > 0).astype(np.ubyte)
@@ -134,9 +136,10 @@ def __getitem__(self, idx):
             (x_loc, y_loc),
             self._selected_level,
             (self._patch_size[0], self._patch_size[1]),
-            as_array=True,
-        )
+            # as_array=True, openslide-python returns an RGBA PIL image
+        ).convert("RGB")
 
+        patch = np.asarray(patch)  # convert the image to ndarray
         # this is to ensure that channels come at the beginning
         patch = patch.transpose([2, 0, 1])
         # this is to ensure that we always have a z-stack before applying any torchio transforms

GANDLF/data/patch_miner/opm/patch.py

@@ -46,7 +46,9 @@ def read_patch(self):
         return np.asarray(
             self.slide_object.read_region(
                 (self.coordinates[1], self.coordinates[0]), self.level, self.size
-            )
+            ).convert(
+                "RGB"
+            )  # openslide-python returns an RGBA PIL image
         )
 
     def copy(self):

GANDLF/data/patch_miner/opm/patch_manager.py

@@ -7,7 +7,7 @@
 from tqdm import tqdm
 from pathlib import Path
 import pandas as pd
-import tiffslide
+import openslide
 
 
 class PatchManager:
@@ -41,7 +41,7 @@ def set_subjectID(self, subjectID):
     def set_slide_path(self, filename):
         self.img_path = filename
         self.img_path = convert_to_tiff(self.img_path, self.output_dir, "img")
-        self.slide_object = tiffslide.open_slide(self.img_path)
+        self.slide_object = openslide.open_slide(self.img_path)
         self.slide_dims = self.slide_object.dimensions
 
     def set_label_map(self, path):
@@ -50,7 +50,7 @@ def set_label_map(self, path):
         @param path: path to label map.
         """
         self.label_map = convert_to_tiff(path, self.output_dir, "mask")
-        self.label_map_object = tiffslide.open_slide(self.label_map)
+        self.label_map_object = openslide.open_slide(self.label_map)
 
         assert all(
             x == y for x, y in zip(self.label_map_object.dimensions, self.slide_dims)

GANDLF/data/patch_miner/opm/utils.py

@@ -17,7 +17,7 @@
 
 # import matplotlib.pyplot as plt
 import yaml
-import tiffslide
+import openslide
 
 # RGB Masking (pen) constants
 RGB_RED_CHANNEL = 0
@@ -428,7 +428,7 @@ def generate_initial_mask(slide_path: str, scale: int) -> Tuple[np.ndarray, tupl
         Tuple[np.ndarray, tuple]: The valid mask and the real scale.
     """
     # Open slide and get properties
-    slide = tiffslide.open_slide(slide_path)
+    slide = openslide.open_slide(slide_path)
     slide_dims = slide.dimensions
 
     # Call thumbnail for effiency, calculate scale relative to whole slide
@@ -505,26 +505,26 @@ def get_patch_size_in_microns(
                         "Using mpp to calculate patch size for dimension {}".format(i)
                     )
                 # only enter if "m" is present in patch size
-                input_slide = tiffslide.open_slide(input_slide_path)
+                input_slide = openslide.open_slide(input_slide_path)
                 metadata = input_slide.properties
                 if i == 0:
                     for _property in [
-                        tiffslide.PROPERTY_NAME_MPP_X,
+                        openslide.PROPERTY_NAME_MPP_X,
                         "tiff.XResolution",
                         "XResolution",
                     ]:
                         if _property in metadata:
-                            magnification = metadata[_property]
+                            magnification = float(metadata[_property])
                             magnification_prev = magnification
                             break
                 elif i == 1:
                     for _property in [
-                        tiffslide.PROPERTY_NAME_MPP_Y,
+                        openslide.PROPERTY_NAME_MPP_Y,
                         "tiff.YResolution",
                         "YResolution",
                     ]:
                         if _property in metadata:
-                            magnification = metadata[_property]
+                            magnification = float(metadata[_property])
                             break
                     if magnification == -1:
                         # if y-axis data is missing, use x-axis data

GANDLF/entrypoints/run.py

@@ -5,9 +5,7 @@
 import argparse
 import ast
 
-# import traceback
 from typing import Optional
-
 from deprecated import deprecated
 import click
 

setup.py

@@ -6,14 +6,14 @@
 import sys, re, os
 from setuptools import setup, find_packages
 
+
 try:
     with open("README.md") as readme_file:
         readme = readme_file.read()
 except Exception as error:
     readme = "No README information found."
     sys.stderr.write("Warning: Could not open '%s' due %s\n" % ("README.md", error))
 
-
 try:
     filepath = "GANDLF/version.py"
     version_file = open(filepath)
@@ -52,7 +52,6 @@
     "setuptools",
     "seaborn",
     "pyyaml==6.0.1",
-    "tiffslide",
     "matplotlib",
     "gdown==5.1.0",
     "pytest",
@@ -83,6 +82,8 @@
     "colorlog",
     "opacus==1.5.2",
     "huggingface-hub==0.25.1",
+    "openslide-bin",
+    "openslide-python==1.4.1",
 ]
 
 if __name__ == "__main__":