napari-tmidas 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- napari_tmidas/_file_conversion.py +1706 -0
- napari_tmidas/_file_selector.py +357 -60
- napari_tmidas/_label_inspection.py +87 -26
- napari_tmidas/_version.py +2 -2
- napari_tmidas/napari.yaml +9 -4
- napari_tmidas/processing_functions/basic.py +24 -42
- napari_tmidas/processing_functions/skimage_filters.py +60 -43
- {napari_tmidas-0.1.3.dist-info → napari_tmidas-0.1.5.dist-info}/METADATA +35 -12
- {napari_tmidas-0.1.3.dist-info → napari_tmidas-0.1.5.dist-info}/RECORD +13 -12
- {napari_tmidas-0.1.3.dist-info → napari_tmidas-0.1.5.dist-info}/WHEEL +1 -1
- {napari_tmidas-0.1.3.dist-info → napari_tmidas-0.1.5.dist-info}/entry_points.txt +0 -0
- {napari_tmidas-0.1.3.dist-info → napari_tmidas-0.1.5.dist-info/licenses}/LICENSE +0 -0
- {napari_tmidas-0.1.3.dist-info → napari_tmidas-0.1.5.dist-info}/top_level.txt +0 -0
napari_tmidas/_version.py
CHANGED
napari_tmidas/napari.yaml
CHANGED
|
@@ -20,10 +20,13 @@ contributions:
|
|
|
20
20
|
title: Load sample data from T-MIDAS
|
|
21
21
|
- id: napari-tmidas._label_inspection # hyphen!
|
|
22
22
|
python_name: napari_tmidas._label_inspection:label_inspector_widget # underscore!
|
|
23
|
-
title: Label
|
|
23
|
+
title: Label Inspector
|
|
24
24
|
- id: napari-tmidas.file_selector
|
|
25
25
|
python_name: napari_tmidas._file_selector:napari_experimental_provide_dock_widget
|
|
26
|
-
title:
|
|
26
|
+
title: Batch Image Processing
|
|
27
|
+
- id: napari-tmidas._file_conversion
|
|
28
|
+
python_name: napari_tmidas._file_conversion:napari_experimental_provide_dock_widget
|
|
29
|
+
title: Microscopy Image Converter
|
|
27
30
|
readers:
|
|
28
31
|
- command: napari-tmidas.get_reader
|
|
29
32
|
accepts_directories: false
|
|
@@ -41,6 +44,8 @@ contributions:
|
|
|
41
44
|
key: unique_id.1
|
|
42
45
|
widgets:
|
|
43
46
|
- command: napari-tmidas.file_selector
|
|
44
|
-
display_name:
|
|
47
|
+
display_name: Batch Image Processing
|
|
45
48
|
- command: napari-tmidas._label_inspection
|
|
46
|
-
display_name: Label
|
|
49
|
+
display_name: Batch Label inspection
|
|
50
|
+
- command: napari-tmidas._file_conversion
|
|
51
|
+
display_name: Batch Microscopy Image Conversion
|
|
@@ -8,53 +8,35 @@ from napari_tmidas._registry import BatchProcessingRegistry
|
|
|
8
8
|
|
|
9
9
|
|
|
10
10
|
@BatchProcessingRegistry.register(
|
|
11
|
-
name="
|
|
12
|
-
suffix="
|
|
13
|
-
description="
|
|
14
|
-
)
|
|
15
|
-
def normalize_image(image: np.ndarray) -> np.ndarray:
|
|
16
|
-
"""
|
|
17
|
-
Simple min-max normalization
|
|
18
|
-
"""
|
|
19
|
-
if image.min() == image.max():
|
|
20
|
-
return np.zeros_like(image, dtype=float)
|
|
21
|
-
return (image - image.min()) / (image.max() - image.min())
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
@BatchProcessingRegistry.register(
|
|
25
|
-
name="Contrast Stretch",
|
|
26
|
-
suffix="_contrast",
|
|
27
|
-
description="Stretch the contrast by clipping percentiles and rescaling",
|
|
11
|
+
name="Gamma Correction",
|
|
12
|
+
suffix="_gamma",
|
|
13
|
+
description="Apply gamma correction to the image (>1: enhance bright regions, <1: enhance dark regions)",
|
|
28
14
|
parameters={
|
|
29
|
-
"
|
|
30
|
-
"type": float,
|
|
31
|
-
"default": 2.0,
|
|
32
|
-
"min": 0.0,
|
|
33
|
-
"max": 49.0,
|
|
34
|
-
"description": "Low percentile to clip",
|
|
35
|
-
},
|
|
36
|
-
"high_percentile": {
|
|
15
|
+
"gamma": {
|
|
37
16
|
"type": float,
|
|
38
|
-
"default":
|
|
39
|
-
"min":
|
|
40
|
-
"max":
|
|
41
|
-
"description": "
|
|
17
|
+
"default": 1.0,
|
|
18
|
+
"min": 0.1,
|
|
19
|
+
"max": 10.0,
|
|
20
|
+
"description": "Gamma correction factor",
|
|
42
21
|
},
|
|
43
22
|
},
|
|
44
23
|
)
|
|
45
|
-
def
|
|
46
|
-
image: np.ndarray,
|
|
47
|
-
low_percentile: float = 2.0,
|
|
48
|
-
high_percentile: float = 98.0,
|
|
49
|
-
) -> np.ndarray:
|
|
24
|
+
def gamma_correction(image: np.ndarray, gamma: float = 1.0) -> np.ndarray:
|
|
50
25
|
"""
|
|
51
|
-
|
|
26
|
+
Apply gamma correction to the image
|
|
52
27
|
"""
|
|
53
|
-
|
|
54
|
-
|
|
28
|
+
# Determine maximum value based on dtype
|
|
29
|
+
max_val = (
|
|
30
|
+
np.iinfo(image.dtype).max
|
|
31
|
+
if np.issubdtype(image.dtype, np.integer)
|
|
32
|
+
else 1.0
|
|
33
|
+
)
|
|
34
|
+
|
|
35
|
+
# Normalize image to [0, 1]
|
|
36
|
+
normalized = image.astype(np.float32) / max_val
|
|
37
|
+
|
|
38
|
+
# Apply gamma correction
|
|
39
|
+
corrected = np.power(normalized, gamma)
|
|
55
40
|
|
|
56
|
-
#
|
|
57
|
-
|
|
58
|
-
if p_high == p_low:
|
|
59
|
-
return np.zeros_like(image, dtype=float)
|
|
60
|
-
return (image_clipped - p_low) / (p_high - p_low)
|
|
41
|
+
# Scale back to original range and dtype
|
|
42
|
+
return (corrected * max_val).clip(0, max_val).astype(image.dtype)
|
|
@@ -7,6 +7,7 @@ import numpy as np
|
|
|
7
7
|
try:
|
|
8
8
|
import skimage.exposure
|
|
9
9
|
import skimage.filters
|
|
10
|
+
import skimage.morphology
|
|
10
11
|
|
|
11
12
|
SKIMAGE_AVAILABLE = True
|
|
12
13
|
except ImportError:
|
|
@@ -19,49 +20,38 @@ from napari_tmidas._registry import BatchProcessingRegistry
|
|
|
19
20
|
|
|
20
21
|
if SKIMAGE_AVAILABLE:
|
|
21
22
|
|
|
22
|
-
@BatchProcessingRegistry.register(
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
)
|
|
43
|
-
def adaptive_hist_eq(
|
|
44
|
-
|
|
45
|
-
) -> np.ndarray:
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
@BatchProcessingRegistry.register(
|
|
56
|
-
name="Edge Detection",
|
|
57
|
-
suffix="_edges",
|
|
58
|
-
description="Detect edges using Sobel filter",
|
|
59
|
-
)
|
|
60
|
-
def edge_detection(image: np.ndarray) -> np.ndarray:
|
|
61
|
-
"""
|
|
62
|
-
Detect edges using Sobel filter
|
|
63
|
-
"""
|
|
64
|
-
return skimage.filters.sobel(image)
|
|
23
|
+
# @BatchProcessingRegistry.register(
|
|
24
|
+
# name="Adaptive Histogram Equalization",
|
|
25
|
+
# suffix="_clahe",
|
|
26
|
+
# description="Enhance contrast using Contrast Limited Adaptive Histogram Equalization",
|
|
27
|
+
# parameters={
|
|
28
|
+
# "kernel_size": {
|
|
29
|
+
# "type": int,
|
|
30
|
+
# "default": 8,
|
|
31
|
+
# "min": 4,
|
|
32
|
+
# "max": 64,
|
|
33
|
+
# "description": "Size of local region for histogram equalization",
|
|
34
|
+
# },
|
|
35
|
+
# "clip_limit": {
|
|
36
|
+
# "type": float,
|
|
37
|
+
# "default": 0.01,
|
|
38
|
+
# "min": 0.001,
|
|
39
|
+
# "max": 0.1,
|
|
40
|
+
# "description": "Clipping limit for contrast enhancement",
|
|
41
|
+
# },
|
|
42
|
+
# },
|
|
43
|
+
# )
|
|
44
|
+
# def adaptive_hist_eq(
|
|
45
|
+
# image: np.ndarray, kernel_size: int = 8, clip_limit: float = 0.01
|
|
46
|
+
# ) -> np.ndarray:
|
|
47
|
+
# """
|
|
48
|
+
# Apply Contrast Limited Adaptive Histogram Equalization
|
|
49
|
+
# """
|
|
50
|
+
# # CLAHE expects image in [0, 1] range
|
|
51
|
+
# img_norm = skimage.exposure.rescale_intensity(image, out_range=(0, 1))
|
|
52
|
+
# return skimage.exposure.equalize_adapthist(
|
|
53
|
+
# img_norm, kernel_size=kernel_size, clip_limit=clip_limit
|
|
54
|
+
# )
|
|
65
55
|
|
|
66
56
|
# simple otsu thresholding
|
|
67
57
|
@BatchProcessingRegistry.register(
|
|
@@ -110,4 +100,31 @@ if SKIMAGE_AVAILABLE:
|
|
|
110
100
|
"""
|
|
111
101
|
Threshold image using a fixed threshold
|
|
112
102
|
"""
|
|
103
|
+
# convert to 8-bit
|
|
104
|
+
image = skimage.img_as_ubyte(image)
|
|
113
105
|
return image > threshold
|
|
106
|
+
|
|
107
|
+
# remove small objects
|
|
108
|
+
@BatchProcessingRegistry.register(
|
|
109
|
+
name="Remove Small Objects",
|
|
110
|
+
suffix="_rm_small",
|
|
111
|
+
description="Remove small objects from the binary image",
|
|
112
|
+
parameters={
|
|
113
|
+
"min_size": {
|
|
114
|
+
"type": int,
|
|
115
|
+
"default": 100,
|
|
116
|
+
"min": 1,
|
|
117
|
+
"max": 100000,
|
|
118
|
+
"description": "Remove labels smaller than: ",
|
|
119
|
+
},
|
|
120
|
+
},
|
|
121
|
+
)
|
|
122
|
+
def remove_small_objects(
|
|
123
|
+
image: np.ndarray, min_size: int = 100
|
|
124
|
+
) -> np.ndarray:
|
|
125
|
+
"""
|
|
126
|
+
Remove small objects from the binary image
|
|
127
|
+
"""
|
|
128
|
+
return skimage.morphology.remove_small_objects(
|
|
129
|
+
image, min_size=min_size
|
|
130
|
+
)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
|
-
Metadata-Version: 2.
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
2
|
Name: napari-tmidas
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.5
|
|
4
4
|
Summary: Tissue Microscopy Image Data Analysis Suite
|
|
5
5
|
Author: Marco Meer
|
|
6
6
|
Author-email: marco.meer@pm.me
|
|
@@ -65,6 +65,7 @@ Requires-Dist: pytest-cov; extra == "testing"
|
|
|
65
65
|
Requires-Dist: pytest-qt; extra == "testing"
|
|
66
66
|
Requires-Dist: napari; extra == "testing"
|
|
67
67
|
Requires-Dist: pyqt5; extra == "testing"
|
|
68
|
+
Dynamic: license-file
|
|
68
69
|
|
|
69
70
|
# napari-tmidas
|
|
70
71
|
|
|
@@ -74,15 +75,21 @@ Requires-Dist: pyqt5; extra == "testing"
|
|
|
74
75
|
[](https://github.com/macromeer/napari-tmidas/actions)
|
|
75
76
|
[](https://napari-hub.org/plugins/napari-tmidas)
|
|
76
77
|
<!-- [](https://codecov.io/gh/macromeer/napari-tmidas) -->
|
|
78
|
+
This Napari plugin allows you to perform batch image processing without a graphics processing unit (GPU). It will still be fast because computations will run in parallel on your central processing unit (CPU).
|
|
77
79
|
|
|
78
|
-
|
|
80
|
+
This plugin provides you with a growing collection of pipelines for batch image preprocessing, segmentation, regions-of-interest (ROI) analysis and other useful features.
|
|
81
|
+
|
|
82
|
+
`napari-tmidas` is a work in progress (WIP) and an evolutionary step away from the [terminal / command-line version of T-MIDAS](https://github.com/MercaderLabAnatomy/T-MIDAS).
|
|
79
83
|
|
|
80
84
|
## Installation
|
|
81
85
|
|
|
82
|
-
First install Napari in a virtual environment
|
|
86
|
+
First install Napari in a virtual environment:
|
|
83
87
|
|
|
88
|
+
mamba create -y -n napari-tmidas -c conda-forge python=3.11 tqdm
|
|
89
|
+
mamba activate napari-tmidas
|
|
90
|
+
python -m pip install "napari[all]"
|
|
84
91
|
|
|
85
|
-
|
|
92
|
+
Now you can install `napari-tmidas` via [pip]:
|
|
86
93
|
|
|
87
94
|
pip install napari-tmidas
|
|
88
95
|
|
|
@@ -90,31 +97,46 @@ To install the latest development version:
|
|
|
90
97
|
|
|
91
98
|
pip install git+https://github.com/macromeer/napari-tmidas.git
|
|
92
99
|
|
|
100
|
+
### Dependencies
|
|
101
|
+
For the File converter, we need some libraries to read some microscopy formats and to write ome-zarr:
|
|
102
|
+
|
|
103
|
+
pip install nd2 readlif tiffslide pylibCZIrw acquifer-napari ome-zarr
|
|
104
|
+
|
|
105
|
+
|
|
93
106
|
## Usage
|
|
94
107
|
|
|
95
108
|
You can find the installed plugin here:
|
|
96
|
-
|
|
109
|
+
|
|
97
110
|
|
|
98
111
|
|
|
112
|
+
|
|
113
|
+
### File converter
|
|
114
|
+
|
|
115
|
+
You might first want to batch convert microscopy image data. Currently, this plugin supports `.nd2, .lif, .ndpi, .czi` and acquifer data. After launching the file converter, you can scan a folder of your choice for microscopy image data. It will also detect series images that you can preview. Start by selecting an original image in the first column of the table. This allows you to preview or convert.
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
|
|
119
|
+
|
|
120
|
+
|
|
99
121
|
### File inspector
|
|
100
122
|
|
|
101
123
|
1. After opening `Plugins > T-MIDAS > File selector`, enter the path to the folder containing the images to be processed (currently supports TIF, later also ZARR). You can also filter for filename suffix.
|
|
102
|
-
|
|
124
|
+
|
|
103
125
|
|
|
104
126
|
|
|
105
127
|
2. As a result, a table appears with the found images.
|
|
106
|
-
|
|
128
|
+
|
|
107
129
|
|
|
108
130
|
|
|
109
131
|
3. Next, select a processing function, set parameters if applicable and `Start Batch Processing`.
|
|
110
|
-
|
|
132
|
+
|
|
111
133
|
|
|
112
134
|
|
|
113
|
-
4. You can click on the images in the table to show them in the viewer. For example first click on one of the `Original Files`, and then the corresponding `Processed File` to see an overlay.
|
|
114
|
-
|
|
135
|
+
4. You can click on the images in the table to show them in the viewer. For example first click on one of the `Original Files`, and then the corresponding `Processed File` to see an overlay.
|
|
136
|
+
|
|
115
137
|
|
|
116
138
|
|
|
117
|
-
Note that whenever you click on an `Original File` or `Processed File` in the table, it will replace the one that is currently shown in the viewer. So naturally, you'd first select the original image, and then the processed image to correctly see the image pair that you want to inspect.
|
|
139
|
+
Note that whenever you click on an `Original File` or `Processed File` in the table, it will replace the one that is currently shown in the viewer. So naturally, you'd first select the original image, and then the processed image to correctly see the image pair that you want to inspect.
|
|
118
140
|
|
|
119
141
|
### Label inspector
|
|
120
142
|
If you have already segmented a folder full of images and now you want to maybe inspect and edit each label image, you can use the `Plugins > T-MIDAS > Label inspector`, which automatically saves your changes to the existing label image once you click the `Save Changes and Continue` button (bottom right).
|
|
@@ -122,6 +144,7 @@ If you have already segmented a folder full of images and now you want to maybe
|
|
|
122
144
|
|
|
123
145
|
|
|
124
146
|
|
|
147
|
+
|
|
125
148
|
## Contributing
|
|
126
149
|
|
|
127
150
|
Contributions are very welcome. Tests can be run with [tox], please ensure
|
|
@@ -1,25 +1,26 @@
|
|
|
1
1
|
napari_tmidas/__init__.py,sha256=Z9mznblUlUsRyH3d4k8SxUo4iXLMwJXURbq41QzhPpo,459
|
|
2
|
-
napari_tmidas/
|
|
3
|
-
napari_tmidas/
|
|
2
|
+
napari_tmidas/_file_conversion.py,sha256=Al59izNadYiqYmG-JT4TxXNifMt796x5yrvQbLc-8Eo,62547
|
|
3
|
+
napari_tmidas/_file_selector.py,sha256=XLbqeQ4fG86gLHgmPZzrcmMTir5gpneO32KumJY8ZbM,27369
|
|
4
|
+
napari_tmidas/_label_inspection.py,sha256=5p0heCX1xCQVYDGHe_R2gPwbZpl6sXIqLBwqbZLJKqo,6983
|
|
4
5
|
napari_tmidas/_reader.py,sha256=A9_hdDxtVkVGmbOsbqgnARCSvpEh7GGPo7ylzmbnu8o,2485
|
|
5
6
|
napari_tmidas/_registry.py,sha256=Oz9HFJh41MKRLeKxRuc7x7yzc-OrmoTdRFnfngFU_XE,2007
|
|
6
7
|
napari_tmidas/_sample_data.py,sha256=khuv1jemz_fCjqNwEKMFf83Ju0EN4S89IKydsUMmUxw,645
|
|
7
|
-
napari_tmidas/_version.py,sha256=
|
|
8
|
+
napari_tmidas/_version.py,sha256=Y4jy4bEMmwl_qNPCmiMFnlQ2ofMoqyG37hp8uwI3m10,511
|
|
8
9
|
napari_tmidas/_widget.py,sha256=u9uf9WILAwZg_InhFyjWInY4ej1TV1a59dR8Fe3vNF8,4794
|
|
9
10
|
napari_tmidas/_writer.py,sha256=wbVfHFjjHdybSg37VR4lVmL-kdCkDZsUPDJ66AVLaFQ,1941
|
|
10
|
-
napari_tmidas/napari.yaml,sha256=
|
|
11
|
+
napari_tmidas/napari.yaml,sha256=mY40xnwVygEjHpYGVVtGT2rkoUj-lNHsAg5y51yZbfE,2135
|
|
11
12
|
napari_tmidas/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
12
13
|
napari_tmidas/_tests/test_reader.py,sha256=gN_2StATLZYUL56X27ImJTVru_qSoFiY4vtgajcx3H0,975
|
|
13
14
|
napari_tmidas/_tests/test_sample_data.py,sha256=D1HU_C3hWpO3mlSW_7Z94xaYHDtxz0XUrMjQoYop9Ag,104
|
|
14
15
|
napari_tmidas/_tests/test_widget.py,sha256=I_d-Cra_CTcS0QdMItg_HMphvhj0XCx81JnFyCHk9lg,2204
|
|
15
16
|
napari_tmidas/_tests/test_writer.py,sha256=4_MlZM9a5So74J16_4tIOJc6pwTOw9R0-oAE_YioIx4,122
|
|
16
17
|
napari_tmidas/processing_functions/__init__.py,sha256=osXY9jSgDsrwFaS6ShPHP0wGRxMuX1mHRN9EDa9l41g,1891
|
|
17
|
-
napari_tmidas/processing_functions/basic.py,sha256=
|
|
18
|
+
napari_tmidas/processing_functions/basic.py,sha256=m_Q1LwwmQ8Nto2eM7SbMw2o1wolbTr9ZqCnYzxEZy7I,1182
|
|
18
19
|
napari_tmidas/processing_functions/scipy_filters.py,sha256=kKpDAlQQ0ZNbkt77QUWi-Bwolk6MMDvtG_bZJV3MjOo,1612
|
|
19
|
-
napari_tmidas/processing_functions/skimage_filters.py,sha256=
|
|
20
|
-
napari_tmidas-0.1.
|
|
21
|
-
napari_tmidas-0.1.
|
|
22
|
-
napari_tmidas-0.1.
|
|
23
|
-
napari_tmidas-0.1.
|
|
24
|
-
napari_tmidas-0.1.
|
|
25
|
-
napari_tmidas-0.1.
|
|
20
|
+
napari_tmidas/processing_functions/skimage_filters.py,sha256=IsfMJTtd9Vwb47UlTEcLlXYv2CX6uTARV1CZCHY0HBw,4094
|
|
21
|
+
napari_tmidas-0.1.5.dist-info/licenses/LICENSE,sha256=tSjiOqj57exmEIfP2YVPCEeQf0cH49S6HheQR8IiY3g,1485
|
|
22
|
+
napari_tmidas-0.1.5.dist-info/METADATA,sha256=mum4W9WKXGGPzDN1rP5SFrB_wnTdf3VrtahIYEx2zoA,9114
|
|
23
|
+
napari_tmidas-0.1.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
|
|
24
|
+
napari_tmidas-0.1.5.dist-info/entry_points.txt,sha256=fbVjzbJTm4aDMIBtel1Lyqvq-CwXY7wmCOo_zJ-jtRY,60
|
|
25
|
+
napari_tmidas-0.1.5.dist-info/top_level.txt,sha256=63ybdxCZ4SeT13f_Ou4TsivGV_2Gtm_pJOXToAt30_E,14
|
|
26
|
+
napari_tmidas-0.1.5.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|