From 5ee20572a1cb0cc0219ca3cbd86559162fb0f3c9 Mon Sep 17 00:00:00 2001
From: Christopher Rhodes <christopher.rhodes@embl.de>
Date: Mon, 30 Oct 2023 14:09:05 +0100
Subject: [PATCH] Implemented check for multiple connected objects in mask
frame, and optional restriction to the largest-area one; inference on
autogenerated model now works with 100% accuracy when passing on training
data
---
...fer_labels_to_ilastik_object_classifier.py | 36 +++++++++----------
extensions/chaeo/workflows.py | 26 +++++++++-----
2 files changed, 36 insertions(+), 26 deletions(-)
diff --git a/extensions/chaeo/examples/transfer_labels_to_ilastik_object_classifier.py b/extensions/chaeo/examples/transfer_labels_to_ilastik_object_classifier.py
index c69b9b96..9975f4cc 100644
--- a/extensions/chaeo/examples/transfer_labels_to_ilastik_object_classifier.py
+++ b/extensions/chaeo/examples/transfer_labels_to_ilastik_object_classifier.py
@@ -58,7 +58,7 @@ def infer_and_compare(classifier: PatchStackObjectClassifier, prefix, raw, mask,
if __name__ == '__main__':
- root = Path('c:/Users/rhodes/projects/proj0011-plankton-seg/exp0009/output/labeled_patches-20231030-0002')
+ root = Path('c:/Users/rhodes/projects/proj0011-plankton-seg/exp0009/output/labeled_patches-20231030-0007')
template_ilp = Path('c:/Users/rhodes/projects/proj0011-plankton-seg/exp0014/template_obj.ilp')
df_labels = pd.read_csv(root / 'labels_key.csv')
@@ -78,21 +78,21 @@ if __name__ == '__main__':
)
classifier = PatchStackObjectClassifier({'project_file': classifier_file})
- # # verify self-consistency of training set
- # infer_and_compare(
- # classifier,
- # 'train',
- # MonoPatchStackFromFile(root / 'zstack_train_raw.tif'),
- # MonoPatchStackFromFile(root / 'zstack_train_mask.tif'),
- # MonoPatchStackFromFile(root / 'zstack_train_label.tif')
- # )
- #
- # # run test set
- # infer_and_compare(
- # classifier,
- # 'test',
- # MonoPatchStackFromFile(root / 'zstack_test_raw.tif'),
- # MonoPatchStackFromFile(root / 'zstack_test_mask.tif'),
- # MonoPatchStackFromFile(root / 'zstack_test_label.tif'),
- # )
+ # verify self-consistency of training set
+ infer_and_compare(
+ classifier,
+ 'train',
+ MonoPatchStackFromFile(root / 'zstack_train_raw.tif'),
+ MonoPatchStackFromFile(root / 'zstack_train_mask.tif'),
+ MonoPatchStackFromFile(root / 'zstack_train_label.tif')
+ )
+
+ # run test set
+ infer_and_compare(
+ classifier,
+ 'test',
+ MonoPatchStackFromFile(root / 'zstack_test_raw.tif'),
+ MonoPatchStackFromFile(root / 'zstack_test_mask.tif'),
+ MonoPatchStackFromFile(root / 'zstack_test_label.tif'),
+ )
diff --git a/extensions/chaeo/workflows.py b/extensions/chaeo/workflows.py
index 3847d5e2..1a67984b 100644
--- a/extensions/chaeo/workflows.py
+++ b/extensions/chaeo/workflows.py
@@ -4,6 +4,7 @@ from uuid import uuid4
import numpy as np
import pandas as pd
+from skimage.measure import label, regionprops_table
from skimage.morphology import dilation
from sklearn.model_selection import train_test_split
@@ -292,14 +293,15 @@ def infer_object_map_from_zstack(
def transfer_ecotaxa_labels_to_patch_stacks(
- where_masks: str,
- where_patches: str,
- object_csv: str,
- ecotaxa_tsv: str,
- where_output: str,
- patch_size: tuple = (256, 256),
- tr_split=0.6,
- dilate_label_mask: bool = True, # to mitigate connected components error in ilastik
+ where_masks: str,
+ where_patches: str,
+ object_csv: str,
+ ecotaxa_tsv: str,
+ where_output: str,
+ patch_size: tuple = (256, 256),
+ tr_split=0.6,
+ dilate_label_mask: bool = True, # to mitigate connected components error in ilastik
+ allow_multiple_objects: bool = False,
) -> Dict:
assert tr_split > 0.5 # reduce chance that low-probability objects are omitted from training
@@ -381,6 +383,14 @@ def transfer_ecotaxa_labels_to_patch_stacks(
mask = acc_bm.data[:, :, 0, 0]
if dilate_label_mask:
mask = dilation(mask)
+ if not allow_multiple_objects:
+ ob_id = label(acc_bm.data[:, :, 0, 0])
+ num_obj = len(np.unique(ob_id)) - 1
+ if num_obj > 1:
+ print(f'Found multiple nonzero unique values in mask {fi}; keeping the one with largest area')
+ pr = regionprops_table(ob_id, properties=['label', 'area'])
+ idx_max_area = pr['area'].argmax()
+ mask = 255 * (ob_id == pr['label'][idx_max_area])
zstacks[dfk + '_mask'][:, :, 0, fi] = mask
zstacks[dfk + '_label'][:, :, 0, fi] = (mask == 255) * aci
--
GitLab