Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

added seed_distance to parameters of mitochondria segmentation #93

Merged
merged 4 commits into from
Jan 9, 2025
Merged

added seed_distance to parameters of mitochondria segmentation #93

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
32438b2
added seed_distance to parameters of mitochondria segmentation
lufre1 Jan 8, 2025
583781e
added blockshape and halo for seeded watershed as well and removed ob…
lufre1 Jan 9, 2025
3e62c91
Apply suggestions from code review
constantinpape Jan 9, 2025
6c74bd7
Update environment.yaml
constantinpape Jan 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions synapse_net/inference/mitochondria.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,8 @@ def _run_segmentation(
foreground, boundaries, verbose, min_size,
# blocking shapes for parallel computation
block_shape=(128, 256, 256),
halo=(48, 48, 48)
halo=(48, 48, 48),
seed_distance=6
):
t0 = time.time()
boundary_threshold = 0.25
Expand All @@ -24,19 +25,11 @@ def _run_segmentation(

# Get the segmentation via seeded watershed.
t0 = time.time()
seed_distance = 6
seeds = np.logical_and(foreground > 0.5, dist > seed_distance)
seeds = parallel.label(seeds, block_shape=block_shape, verbose=verbose)
if verbose:
print("Compute connected components in", time.time() - t0, "s")

# import napari
# v = napari.Viewer()
# v.add_image(boundaries)
# v.add_image(dist)
# v.add_labels(seeds)
# napari.run()

t0 = time.time()
hmap = boundaries + ((dist.max() - dist) / dist.max())
mask = (foreground + boundaries) > 0.5
Expand Down Expand Up @@ -65,6 +58,9 @@ def segment_mitochondria(
return_predictions: bool = False,
scale: Optional[List[float]] = None,
mask: Optional[np.ndarray] = None,
seed_distance: int = 6,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You should add this to the doc string as well.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i added watershed tiling to the function's parameters, because i needed to adapt it for some data

ws_block_shape=(128, 256, 256),
constantinpape marked this conversation as resolved.
Show resolved Hide resolved
ws_halo=(48, 48, 48),
constantinpape marked this conversation as resolved.
Show resolved Hide resolved
) -> Union[np.ndarray, Tuple[np.ndarray, np.ndarray]]:
"""Segment mitochondria in an input volume.

Expand All @@ -79,6 +75,9 @@ def segment_mitochondria(
return_predictions: Whether to return the predictions (foreground, boundaries) alongside the segmentation.
scale: The scale factor to use for rescaling the input volume before prediction.
mask: An optional mask that is used to restrict the segmentation.
seed_distance: The distance threshold for the seeded watershed.
ws_block_shape: The block shape for the seeded watershed.
ws_halo: The halo for the seeded watershed.

Returns:
The segmentation mask as a numpy array, or a tuple containing the segmentation mask
Expand All @@ -97,7 +96,8 @@ def segment_mitochondria(

# Run segmentation and rescale the result if necessary.
foreground, boundaries = pred[:2]
seg = _run_segmentation(foreground, boundaries, verbose=verbose, min_size=min_size)
seg = _run_segmentation(foreground, boundaries, verbose=verbose, min_size=min_size, seed_distance=seed_distance,
block_shape=ws_block_shape, halo=ws_halo)
seg = scaler.rescale_output(seg, is_segmentation=True)

if return_predictions:
Expand Down
Loading