cell stats notebook + docs

Author: C-Achard

docs/res/code/model_instance_seg.rst

@@ -13,6 +13,10 @@ binary_watershed
 **************************************
 .. autofunction:: napari_cellseg3d.model_instance_seg::binary_watershed
 
+volume_stats
+**************************************
+.. autofunction:: napari_cellseg3d.model_instance_seg::volume_stats
+
 clear_small_objects
 **************************************
 .. autofunction:: napari_cellseg3d.model_instance_seg::clear_small_objects

docs/res/guides/inference_module_guide.rst

@@ -75,6 +75,25 @@ Interface and functionalities
 .. _connected components: https://scikit-image.org/docs/dev/api/skimage.measure.html#skimage.measure.label
 
 
+* **Computing objects statistics** :
+
+You can choose to compute various stats from the labels and save them to a csv for later use.
+This includes, for each object :
+
+* Object volume (pixels)
+* :math:`X,Y,Z` coordinates of the centroid
+* Sphericity
+
+And more general statistics :
+
+* Image size
+* Total image volume (pixels)
+* Total object (labeled) volume (pixels)
+* Filling ratio (fraction of the volume that is labeled)
+* The number of labeled objects
+
+In the ``notebooks`` folder you can find an example of plotting cell statistics using the result csv.
+
 * **Viewing results** :
 
   | You can also select whether you'd like to **see the results** in napari afterwards.

napari_cellseg3d/model_instance_seg.py

@@ -172,6 +172,24 @@ def to_semantic(image, is_file_path=False):
 
 
 def volume_stats(volume_image):
+    """Computes various statistics from instance labels and returns them in a dict.
+    Currently provided :
+
+        * "Volume": volume of each object
+        * "Centroid": x,y,z centroid coordinates for each object
+        * "Sphericity (axes)": sphericity computed from semi-minor and semi-major axes
+        * "Image size": size of the image
+        * "Total image volume": volume in pixels of the whole image
+        * "Total object volume (pixels)": total labeled volume in pixels
+        * "Filling ratio": ratio of labeled over total pixel volume
+        * "Number objects": total number of unique labeled objects
+
+    Args:
+        volume_image: instance labels image
+
+    Returns:
+        dict: Statistics described above
+        """
 
     properties = regionprops(volume_image)
     number_objects = np.amax(volume_image)