Hii,
I am intending to use dask-image to preprocess a lightsheet microscopy data. To optimize various steps, I am working on a subvolume of shape (170,600,900). After performing segmentation and labeling (using dask_image.ndmeasure.label), I want to get the area/volume of each label so that I can remove labels below a certain area/volume threshold. In skimage, I was using regionprops for this task however in dask I thought I would use dask_image.ndmeasure.area. However, when I use this I get the following error:
Cannot block reusing for graphs including a P2PBarrierTask. This may cause unexpected results. This typically happens when converting a dask DataFrame to delayed objects.
I am using the following commands at this step:
gfp_labels = da.from_zarr(‘dask_temp/TEMP_gfp_labels.zarr’)
n_labels = gfp_labels.max().compute()
gfp_area = ndmeasure.area(image_da,gfp_labels,index=da.arange(1,int(n_labels)+1))
Also, is there a better way to filter out the labels? In this subvolume, I am getting ~80k labels before filtering.
Thanks,