Merge pull request #306 from nanli-emory/export_geojson

New feature that save mask as geojson format

Readme.md

@@ -106,12 +106,14 @@ optional arguments:
   -f, --force           force overwriting of existing files
   -b BATCH, --batch BATCH
                         break results file into subsets of this size
-  -s SEED, --seed SEED,
+  -s SEED, --seed SEED
                         set a seed used to produce a random number in all modules                    
   -n NPROCESSES, --nprocesses NPROCESSES
                         number of processes to launch
   --symlink TARGET_DIR  create symlink to outdir in TARGET_DIR
 
+
+
 ```
 
 Installed or simply git-cloned, a typical command line for running the tool thus looks like:

histoqc/SaveModule.py

@@ -1,12 +1,14 @@
 import logging
 import os
+import cv2
+import uuid
+import json
+import numpy as np
 from skimage import io, img_as_ubyte
 from distutils.util import strtobool
-from skimage import color
-import numpy as np
-
-import matplotlib.pyplot as plt
-
+from skimage import color, measure
+from copy import deepcopy
+from geojson import Polygon, Feature, FeatureCollection, dump
 
 def blend2Images(img, mask):
     if (img.ndim == 3):
@@ -18,6 +20,62 @@ def blend2Images(img, mask):
     out = np.concatenate((mask, img, mask), 2)
     return out
 
+def binaryMask2Geojson(s, mask):
+    # get the dimension of slide
+    (dim_width, dim_height) = s['os_handle'].dimensions
+    # get the dimension of mask
+    (mask_height, mask_width) = mask.shape
+
+    # convert binary mask to contours
+    # contours = measure.find_contours(mask)
+    contours, hierarchy = cv2.findContours(img_as_ubyte(mask), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
+    children = [[] for i in range(len(contours))]
+    for i, cnt in enumerate(contours):
+        # first_child_idx = hier[0, i, 2]
+        parent_idx = hierarchy[0, i, 3]
+        if (parent_idx == -1):
+            continue
+        # add contour to parent's children node
+        children[parent_idx].append(cnt)    
+
+    # no contours detected
+    if not len(contours):
+        # set default format
+        ann_format = "xml"
+        # warning msg
+        msg = f"No contour detected at use mask image. Geojson annotation won't be generated."
+        logging.warning(f"{s['filename']} - {msg}")
+        s["warnings"].append(msg)
+        return None
+
+    features = []
+    for i, contour in enumerate(contours):
+        first_child_idx = hierarchy[0, i, 2]
+        parent_idx = hierarchy[0, i, 3]
+
+        if (parent_idx != -1):
+            continue
+
+        geometry = []
+        points = np.asarray(contour / [mask_height, mask_width] * [dim_height, dim_width],dtype="int")
+        points = np.append(points, [points[0]], axis=0)
+        points = points[:,0].tolist()
+        points = [tuple(p) for p in points]
+        geometry.append(points)
+        if first_child_idx != -1:
+            for child in children[i]:
+                child_points = np.asarray(child / [mask_height, mask_width] * [dim_height, dim_width],dtype="int")
+                child_points = np.append(child_points, [child_points[0]], axis=0)
+                child_points = child_points[:,0].tolist()
+                child_points = [tuple(p) for p in child_points]
+                geometry.append(child_points)
+        new_feature = Feature(id=uuid.uuid4().hex, geometry=Polygon(geometry),properties={"objectType": "annotation"})
+
+        features.append(new_feature)
+    feature_collection = FeatureCollection(features)
+
+    return feature_collection
+
 
 def saveFinalMask(s, params):
     logging.info(f"{s['filename']} - \tsaveUsableRegion")
@@ -28,6 +86,7 @@ def saveFinalMask(s, params):
 
     io.imsave(s["outdir"] + os.sep + s["filename"] + "_mask_use.png", img_as_ubyte(mask))
 
+
     if strtobool(params.get("use_mask", "True")):  # should we create and save the fusion mask?
         img = s.getImgThumb(s["image_work_size"])
         out = blend2Images(img, mask)
@@ -70,7 +129,6 @@ def saveMacro(s, params):
 def saveMask(s, params):
     logging.info(f"{s['filename']} - \tsaveMaskUse")
     suffix = params.get("suffix", None)
-
     # check suffix param
     if not suffix:
         msg = f"{s['filename']} - \tPlease set the suffix for mask use."
@@ -80,6 +138,32 @@ def saveMask(s, params):
     # save mask
     io.imsave(f"{s['outdir']}{os.sep}{s['filename']}_{suffix}.png", img_as_ubyte(s["img_mask_use"]))
 
+
+def saveMask2Geojson(s, params):
+
+    mask_name = params.get('mask_name', 'img_mask_use')
+    suffix = params.get("suffix", None)
+    logging.info(f"{s['filename']} - \tsaveMaskUse2Geojson: {mask_name}")
+    # check suffix param
+    if not suffix:
+        msg = f"{s['filename']} - \tPlease set the suffix for mask use in geojson."
+        logging.error(msg)
+        return
+
+    # check if the mask name exists
+    if s.get(mask_name, None) is None: 
+        msg = f"{s['filename']} - \tThe `{mask_name}` mask dosen't exist. Please use correct mask name."
+        logging.error(msg)        
+        return
+    # convert mask to geojson
+    geojson = binaryMask2Geojson(s, s[mask_name])
+
+    # save mask as genjson file
+    with open(f"{s['outdir']}{os.sep}{s['filename']}_{suffix}.geojson", 'w') as f:
+        dump(geojson, f)
+
+
+
 def saveThumbnails(s, params):
     logging.info(f"{s['filename']} - \tsaveThumbnail")
     # we create 2 thumbnails for usage in the front end, one relatively small one, and one larger one

histoqc/__main__.py

@@ -65,7 +65,10 @@ def main(argv=None):
     parser.add_argument('--symlink', metavar="TARGET_DIR",
                         help="create symlink to outdir in TARGET_DIR",
                         default=None)
+
     parser.add_argument('--debug', action='store_true', help="trigger debugging behavior")
+
+
     args = parser.parse_args(argv)
 
     # --- multiprocessing and logging setup -----------------------------------
@@ -75,7 +78,6 @@ def main(argv=None):
     lm = MultiProcessingLogManager('histoqc', manager=mpm)
 
     # --- parse the pipeline configuration ------------------------------------
-
     config = configparser.ConfigParser()
     if not args.config:
         lm.logger.warning(f"Configuration file not set (--config), using default")

histoqc/config/config_clinical.ini

@@ -6,10 +6,12 @@ steps= BasicModule.getBasicStats
     LightDarkModule.getIntensityThresholdPercent:darktissue
     BubbleRegionByRegion.detectSmoothness
     SaveModule.saveMask:first
+    SaveModule.saveMask2Geojson:geo_first
     MorphologyModule.removeFatlikeTissue
     MorphologyModule.fillSmallHoles
     MorphologyModule.removeSmallObjects
     SaveModule.saveMask:second
+    SaveModule.saveMask2Geojson:geo_second
     BlurDetectionModule.identifyBlurryRegions
     BasicModule.finalProcessingSpur
     BasicModule.finalProcessingArea
@@ -20,6 +22,7 @@ steps= BasicModule.getBasicStats
     BrightContrastModule.getBrightnessByChannelinColorSpace:RGB
     BrightContrastModule.getBrightnessByChannelinColorSpace:YUV
     SaveModule.saveMask:third
+    SaveModule.saveMask2Geojson:geo_third
     DeconvolutionModule.separateStains
     SaveModule.saveFinalMask
     SaveModule.saveMacro
@@ -206,5 +209,18 @@ suffix: first
 [SaveModule.saveMask:second]
 suffix: second
 
+
 [SaveModule.saveMask:third]
-suffix: third
+suffix: third
+
+
+[SaveModule.saveMask2Geojson:geo_first]
+suffix: geo_first
+mask_name: img_mask_flat
+
+[SaveModule.saveMask2Geojson:geo_second]
+suffix: geo_second
+mask_name: img_mask_small_filled
+
+[SaveModule.saveMask2Geojson:geo_third]
+suffix: geo_third

requirements.txt

@@ -15,5 +15,5 @@ Pillow~=9.4.0
 setuptools~=65.6.3
 shapely~=2.0.1
 flask~=2.3.2
-
+geojson~=3.1.0 
 cohortfinder==1.0.1