def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
problem_cls = CLASS_OBJSEG
with BiaflowsJob.from_cli(argv) as bj:
bj.job.update(status=Job.RUNNING, progress=0, statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(problem_cls, bj, is_2d=True, **bj.flags)
# 2. Run image analysis workflow
bj.job.update(progress=25, statusComment="Launching workflow...")
shArgs = ["python", "/app/deepcell_script.py", in_path, tmp_path, out_path, str(bj.parameters.nuclei_min_size), str(bj.parameters.boundary_weight)]
return_code = call(" ".join(shArgs), shell=True, cwd="/app/DeepCell/keras_version")
# 3. Upload data to BIAFLOWS
upload_data(problem_cls, bj, in_imgs, out_path, **bj.flags, monitor_params={
"start": 60, "end": 90, "period": 0.1,
"prefix": "Extracting and uploading polygons from masks"})
# 4. Compute and upload metrics
bj.job.update(progress=90, statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, bj, in_imgs, gt_path, out_path, tmp_path, **bj.flags)
# 5. Pipeline finished
bj.job.update(progress=100, status=Job.TERMINATED, status_comment="Finished.")
def main(argv):
# 0. Initialize Cytomine client and job if necessary and parse inputs
with BiaflowsJob.from_cli(argv) as nj:
nj.job.update(status=Job.RUNNING, progress=0, statusComment="Initialisation...")
problem_cls = CLASS_OBJSEG
is_2d = True
# 1. Create working directories on the machine
# 2. Download the images
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(problem_cls, nj, **nj.flags)
# 3. Call the image analysis workflow using the run script
nj.job.update(progress=25, statusComment="Launching workflow...")
command = "/usr/bin/xvfb-run java -Xmx1000m -cp /fiji/jars/ij.jar ij.ImageJ --headless --console " \
"-macro macro.ijm \"input={}, output={}, radius={}, threshold={}\"".format(in_path, out_path, nj.parameters.ij_radius, nj.parameters.ij_threshold)
return_code = call(command, shell=True, cwd="/fiji") # waits for the subprocess to return
if return_code != 0:
err_desc = "Failed to execute the ImageJ macro (return code: {})".format(return_code)
nj.job.update(progress=50, statusComment=err_desc)
raise ValueError(err_desc)
# 4. Upload the annotation and labels to Cytomine
upload_data(problem_cls, nj, in_images, out_path, **nj.flags, is_2d=is_2d, monitor_params={
"start": 60, "end": 90, "period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=90, statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path, **nj.flags)
# 6. End
nj.job.update(status=Job.TERMINATED, progress=100, statusComment="Finished.")
def main(argv):
# 0. Initialize Cytomine client and job
with BiaflowsJob.from_cli(argv) as nj:
nj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
problem_cls = CLASS_TRETRC
is_2d = False
# 1. Create working directories on the machine
# 2. Download the images
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, is_2d=is_2d, **nj.flags)
# 3. Call the image analysis workflow using the run script
nj.job.update(progress=25, statusComment="Launching workflow...")
workflow(in_images, out_path)
#if return_code != 0:
# err_desc = "Failed to execute the Vaa3D (return code: {})".format(return_code)
#nj.job.update(progress=50, statusComment=err_desc)
# raise ValueError(err_desc)
print('files in out_path ' + out_path + ': ')
for file in glob.glob(out_path + '/*'):
print(file)
#files = (glob.glob(in_path+"/*.tif"))
#print('Removing flipped images...')
#for i in range(0,len(files)):
# files[i] = files[i].replace('/in/','/out/')
# print(files[i])
#for out_file in files:
# os.remove(out_file)
# 4. Upload the annotation and labels to Cytomine (annotations are extracted from the mask using
# the AnnotationExporter module
upload_data(problem_cls,
nj,
in_images,
out_path,
**nj.flags,
projection=-1,
is_2d=is_2d,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1,
"prefix":
"Extracting and uploading polygons from masks"
})
#5. Compute and upload the metrics
nj.job.update(
progress=80,
statusComment="Computing and uploading metrics (if necessary)...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path,
**nj.flags)
nj.job.update(status=Job.TERMINATED,
progress=100,
statusComment="Finished.")
def main():
with BiaflowsJob.from_cli(sys.argv[1:]) as nj:
nj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
# 1. Create working directories on the machine:
# 2. Download (or read) data
problem_cls = get_discipline(nj, default=CLASS_SPTCNT)
is_2d = False
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, is_2d=False, **nj.flags)
# 3. Execute workflow
scale = nj.parameters.icy_scale
sensitivity = nj.parameters.icy_sensitivity
nj.job.update(progress=25, statusComment="Launching workflow...")
# Modify the parameters in the job.xml file
replaceScaleParameterCommand = "sed -i '/scale/c\\t<parameter name=\"scale\">{}</parameter>' job.xml".format(
scale)
replaceSensitivityParameterCommand = "sed -i '/sensitivity/c\\t<parameter name=\"sensitivity\">{}</parameter>' job.xml".format(
sensitivity)
replaceInputFolderParameterCommand = "sed -i '/inputFolder/c\\t<parameter name=\"inputFolder\">{}</parameter>' job.xml".format(
'"' + in_path + '"')
replaceOutputFolderParameterCommand = "sed -i '/outputFolder/c\\t<parameter name=\"outputFolder\">{}</parameter>' job.xml".format(
'"' + out_path + '"')
call(replaceScaleParameterCommand, shell=True, cwd="/icy")
call(replaceSensitivityParameterCommand, shell=True, cwd="/icy")
call(replaceInputFolderParameterCommand, shell=True, cwd="/icy")
call(replaceOutputFolderParameterCommand, shell=True, cwd="/icy")
# Run script in ICY
command = "java -jar icy.jar --headless --execute plugins.volker.commandlinescriptrunner.CommandLineScriptRunner"
call(command, shell=True, cwd="/icy")
# 4. Upload the annotation and labels to Cytomine
upload_data(problem_cls,
nj,
in_images,
out_path,
**nj.flags,
is_2d=is_2d,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path,
**nj.flags)
nj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")
def main():
with BiaflowsJob.from_cli(sys.argv[1:]) as nj:
nj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialization...")
# 1. Create working directories on the machine:
# 2. Download (or read) data
problem_cls = get_discipline(nj, default=CLASS_SPTCNT)
is_2d = True
nj.job.update(
progress=1,
statusComment="Execute workflow on problem class '{}'".format(
problem_cls))
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, is_2d=is_2d, **nj.flags)
# 3. Execute workflow
scale3sens = nj.parameters.icy_scale3sensitivity
nj.job.update(progress=25, statusComment="Launching workflow...")
call("java -cp /icy/lib/ -jar /icy/icy.jar -hl",
shell=True,
cwd="/icy")
call(
"java -cp /icy/lib/ -jar /icy/icy.jar -hl -x plugins.adufour.protocols.Protocols "
"protocol=\"/icy/protocols/protocol.protocol\" inputFolder=\"{}\" outputFolder=\"{}\" extension=tif "
"scale2enable=true scale2sensitivity={}".format(
in_path, out_path, scale3sens),
shell=True,
cwd="/icy")
# 3.5 Remove the xml-output files
for p in Path(out_path).glob("*.xml"):
p.unlink()
# 4. Upload the annotation and labels to Cytomine
upload_data(problem_cls,
nj,
in_images,
out_path,
**nj.flags,
is_2d=is_2d,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path,
**nj.flags)
nj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")
def main(argv):
# 0. Initialize Cytomine client and job if necessary and parse inputs
with BiaflowsJob.from_cli(argv) as nj:
nj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
problem_cls = CLASS_OBJSEG
is_2d = True
# 1. Create working directories on the machine
# 2. Download the images
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, is_2d=is_2d, **nj.flags)
# 3. Call the image analysis workflow using the run script
nj.job.update(progress=25, statusComment="Launching workflow...")
command = "python script.py --infld {} --outfld {} --blurad {} --radthr {} --intthr {} --spltnt {} --minsize {}".format(
in_path, out_path, nj.parameters.blurad, nj.parameters.radthr,
nj.parameters.intthr, nj.parameters.spltnt, nj.parameters.minsize)
return_code = call(command, shell=True,
cwd="/app") # waits for the subprocess to return
if return_code != 0:
err_desc = "Failed to execute the Python script (return code: {})".format(
return_code)
nj.job.update(progress=50, statusComment=err_desc)
raise ValueError(err_desc)
# 4. Upload the annotation and labels to Cytomine
upload_data(problem_cls,
nj,
in_images,
out_path,
**nj.flags,
is_2d=is_2d,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path,
**nj.flags)
# 6. End
nj.job.update(status=Job.TERMINATED,
progress=100,
statusComment="Finished.")
def main(argv):
with BiaflowsJob.from_cli(argv) as nj:
problem_cls = CLASS_PRTTRK
is_2d = False
nj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, is_2d=is_2d, **nj.flags)
# 2. Call the image analysis workflow
nj.job.update(progress=25, statusComment="Launching workflow...")
command = "/usr/bin/xvfb-run ./ImageJ-linux64 -macro macro.ijm " \
"\"input={}, output={}, laprad={}, thr={}, maxlnkdst={}\" -batch".format(
in_path, out_path, nj.parameters.laprad, nj.parameters.thr, nj.parameters.maxlnkdst)
return_code = call(command, shell=True,
cwd="/fiji") # waits for the subprocess to return
if return_code != 0:
err_desc = "Failed to execute the ImageJ macro (return code: {})".format(
return_code)
nj.job.update(progress=100, statusComment=err_desc)
raise ValueError(err_desc)
# 4. Create and upload annotations
nj.job.update(progress=70,
statusComment="Uploading extracted annotation...")
upload_data(problem_cls,
nj,
in_images,
out_path,
**nj.flags,
is_2d=is_2d,
monitor_params={
"start": 70,
"end": 90,
"period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(
progress=90,
statusComment="Computing and uploading metrics (if necessary)...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path,
**nj.flags)
# 6. End the job
nj.job.update(status=Job.TERMINATED,
progress=100,
statusComment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
problem_cls = CLASS_OBJSEG
with BiaflowsJob.from_cli(argv) as nj:
nj.job.update(status=Job.RUNNING, progress=0, statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(problem_cls, nj, **nj.flags)
temp_img = skimage.io.imread(os.path.join(in_path,"{}".format(in_imgs[0].filename)))
classification_project = "/app/PixelClassification3D.ilp"
# 2. Run ilastik prediction
nj.job.update(progress=25, statusComment="Launching workflow...")
shArgs = [
"/app/ilastik/run_ilastik.sh",
"--headless",
"--project="+classification_project,
"--export_source=Probabilities",
"--output_format='multipage tiff'",
'--output_filename_format='+os.path.join(tmp_path,'{nickname}.tiff')
]
shArgs += [image.filepath for image in in_imgs]
call_return = call(" ".join(shArgs), shell=True)
# Threshold probabilites
for image in in_imgs:
fn = os.path.join(tmp_path,"{}.tiff".format(image.filename[:-4]))
outfn = os.path.join(out_path,"{}".format(image.filename))
img = skimage.io.imread(fn)
img = label_objects(img, nj.parameters.probability_threshold)
skimage.io.imsave(outfn, img)
# 3. Upload data to Cytomine
upload_data(problem_cls, nj, in_imgs, out_path, is_2d=False, **nj.flags, monitor_params={
"start": 60, "end": 90, "period": 0.1,
"prefix": "Extracting and uploading polygons from masks"})
# 4. Compute and upload metrics
nj.job.update(progress=90, statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_imgs, gt_path, out_path, tmp_path, **nj.flags)
# 5. Pipeline finished
nj.job.update(progress=100, status=Job.TERMINATED, status_comment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
with BiaflowsJob.from_cli(argv) as bj:
# Change following to the actual problem class of the workflow
problem_cls = get_discipline(bj, default=CLASS_OBJSEG)
bj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, bj, is_2d=True, **bj.flags)
# 2. Run image analysis workflow
bj.job.update(progress=25, statusComment="Launching workflow...")
# Add here the code for running the analysis script
# 3. Upload data to BIAFLOWS
upload_data(problem_cls,
bj,
in_imgs,
out_path,
**bj.flags,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1,
"prefix":
"Extracting and uploading polygons from masks"
})
# 4. Compute and upload metrics
bj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, bj, in_imgs, gt_path, out_path, tmp_path,
**bj.flags)
# 5. Pipeline finished
bj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")
def main(argv):
# 0. Initialize Cytomine client and job
with BiaflowsJob.from_cli(argv) as nj:
nj.job.update(status=Job.RUNNING, progress=0, statusComment="Initialisation...")
problem_cls = CLASS_LOOTRC
is_2d = False
# 1. Create working directories on the machine
# 2. Download the images
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(problem_cls, nj,
**nj.flags)
# 3. Call the image analysis workflow using the run script
nj.job.update(progress=25, statusComment="Launching workflow...")
command = "/usr/bin/xvfb-run java -Xmx6000m -cp /fiji/jars/ij.jar ij.ImageJ --headless --console " \
"-macro macro.ijm \"input={}, output={}, gblur={}, rad={}, thr={}\"".format(in_path, out_path, nj.parameters.gblur, nj.parameters.rad, nj.parameters.thr)
return_code = call(command, shell=True, cwd="/fiji") # waits for the subprocess to return
if return_code != 0:
err_desc = "Failed to execute the ImageJ macro (return code: {})".format(return_code)
nj.job.update(progress=50, statusComment=err_desc)
raise ValueError(err_desc)
# 4. Upload the annotation and labels to Cytomine (annotations are extracted from the mask using
# the AnnotationExporter module)
upload_data(problem_cls, nj, in_images, out_path, **nj.flags, is_2d=is_2d, projection=-1, monitor_params={
"start": 60, "end": 90, "period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=80, statusComment="Computing and uploading metrics (if necessary)...")
upload_metrics(
problem_cls,
nj, in_images,
gt_path, out_path, tmp_path,
metric_params={
"gating_dist": 5
# ... put any metric specific parameters here
},
**nj.flags
)
nj.job.update(status=Job.TERMINATED, progress=100, statusComment="Finished.")
def main(argv):
with BiaflowsJob.from_cli(argv) as nj:
problem_cls = get_discipline(nj, default=CLASS_PIXCLA)
is_2d = True
print(nj.parameters)
nj.job.update(status=Job.RUNNING, progress=0, statusComment="Initialisation...")
in_images, gt_images, in_path, gt_path, out_path, tmp_path = prepare_data(problem_cls, nj, **nj.flags)
# 2. Call the image analysis workflow
nj.job.update(progress=10, statusComment="Load model...")
net = load_model("/app/CP58_dice_0.9373_loss_0.0265.pth")
for in_image in nj.monitor(in_images, start=20, end=75, period=0.05, prefix="Apply UNet to input images"):
img = imread(in_image.filepath, is_2d=is_2d)
mask = predict_img(
net=net, full_img=img,
scale_factor=0.5, # value used at training
out_threshold=nj.parameters.threshold
)
imwrite(
path=os.path.join(out_path, in_image.filename),
image=mask.astype(np.uint8),
is_2d=is_2d
)
# 4. Create and upload annotations
nj.job.update(progress=70, statusComment="Uploading extracted annotation...")
upload_data(problem_cls, nj, in_images, out_path, **nj.flags, is_2d=is_2d, monitor_params={
"start": 70, "end": 90, "period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=90, statusComment="Computing and uploading metrics (if necessary)...")
upload_metrics(problem_cls, nj, in_images, gt_path, out_path, tmp_path, **nj.flags)
# 6. End the job
nj.job.update(status=Job.TERMINATED, progress=100, statusComment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
problem_cls = CLASS_OBJSEG
with BiaflowsJob.from_cli(argv) as nj:
nj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, is_2d=True, **nj.flags)
# 2. Run image analysis workflow
nj.job.update(progress=25, statusComment="Launching workflow...")
model = utils.model_builder.get_model_3_class(
unet_utils.IMAGE_SIZE[0], unet_utils.IMAGE_SIZE[1],
channels=3) # Create the model
model.load_weights('/app/weights.h5')
dataset = Dataset()
for img in in_imgs:
image_id = img.filename_no_extension
tiles = dataset.load_image(image_id, img.filepath, TILE_OVERLAP)
# orig_size = dataset.get_orig_size(image_id)
# mask_img = np.zeros(orig_size, dtype=np.uint8)
tile_stack = np.zeros((len(tiles), unet_utils.IMAGE_SIZE[0],
unet_utils.IMAGE_SIZE[1], 3))
for i, tile in enumerate(tiles):
tile_stack[i, :, :, :] = tile
tile_stack = tile_stack / 255
tile_masks = model.predict(tile_stack, batch_size=1)
probmap = dataset.merge_tiles(image_id,
tile_masks,
tile_overlap=TILE_OVERLAP)
labelimg = label_image(probmap, nj.parameters.boundary_weight,
nj.parameters.nuclei_min_size)
skimage.io.imsave(os.path.join(out_path, img.filename), labelimg)
# 3. Upload data to BIAFLOWS
upload_data(problem_cls,
nj,
in_imgs,
out_path,
**nj.flags,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1,
"prefix":
"Extracting and uploading polygons from masks"
})
# 4. Compute and upload metrics
nj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_imgs, gt_path, out_path, tmp_path,
**nj.flags)
# 5. Pipeline finished
nj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")
def main(argv):
# 0. Initialize Cytomine client and job if necessary and parse inputs
with BiaflowsJob.from_cli(argv) as nj:
problem_cls = get_discipline(nj, default=CLASS_OBJTRK)
is_2d = False
nj.job.update(
status=Job.RUNNING,
progress=0,
statusComment="Running workflow for problem class '{}'".format(
problem_cls))
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, nj, **nj.flags)
# 2. Run image analysis workflow
nj.job.update(progress=25, statusComment="Launching workflow...")
for in_img in in_imgs:
# convert the image data to the Cell Tracking Challenge format
img = io.imread(in_img.filepath)
T = img.shape[0]
Y = img.shape[1]
X = img.shape[2]
img_data = img.ravel()
index = 0
offset = Y * X
for t in range(T):
io.imsave(os.path.join(tmp_path, 't{0:03d}.tif'.format(t)),
img_data[index:index + offset].reshape((Y, X)))
index += offset
# do segmentation and tracking
process_dataset(tmp_path, tmp_path, '/app/model.h5')
# convert the tracking results to the required format
index = 0
res_img = np.zeros((T, Y, X), np.uint16)
res_data = res_img.ravel()
for t in range(T):
res = io.imread(
os.path.join(tmp_path, 'mask{0:03d}.tif'.format(t)))
res_data[index:index + offset] = res.ravel()
index += offset
io.imsave(os.path.join(out_path, in_img.filename), res_img)
os.rename(
os.path.join(tmp_path, 'res_track.txt'),
os.path.join(out_path, in_img.filename_no_extension + '.txt'))
# 4. Upload the annotation and labels to Cytomine
upload_data(problem_cls,
nj,
in_imgs,
out_path,
**nj.flags,
is_2d=is_2d,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1
})
# 5. Compute and upload the metrics
nj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, nj, in_imgs, gt_path, out_path, tmp_path,
**nj.flags)
# 6. End
nj.job.update(status=Job.TERMINATED,
progress=100,
statusComment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
problem_cls = CLASS_OBJSEG
with BiaflowsJob.from_cli(argv) as bj:
bj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, bj, is_2d=True, **bj.flags)
files = [image.filepath for image in in_imgs]
# 2. Run Mask R-CNN prediction
bj.job.update(progress=25, statusComment="Launching workflow...")
model_dir = "/app"
dataset = Dataset()
dataset.load_files(files)
dataset.prepare()
inference_config = InferenceConfig()
model = modellib.MaskRCNN(mode="inference",
config=inference_config,
model_dir=model_dir)
model.load_weights(os.path.join(model_dir, 'weights.h5'), by_name=True)
for i, image_id in enumerate(dataset.image_ids):
tiles = dataset.load_image(image_id,
bj.parameters.nuclei_major_axis)
tile_masks = []
for image in tiles:
mask = model.detect([image], verbose=0)[0]
tile_masks.append(mask)
mask_img = dataset.merge_tiles(image_id, tile_masks)
skimage.io.imsave(
os.path.join(out_path, os.path.basename(files[i])), mask_img)
# 3. Upload data to BIAFLOWS
upload_data(problem_cls,
bj,
in_imgs,
out_path,
**bj.flags,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1,
"prefix":
"Extracting and uploading polygons from masks"
})
# 4. Compute and upload metrics
bj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, bj, in_imgs, gt_path, out_path, tmp_path,
**bj.flags)
# 5. Pipeline finished
bj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
with BiaflowsJob.from_cli(argv) as bj:
# Change following to the actual problem class of the workflow
problem_cls = get_discipline(bj, default=CLASS_OBJSEG)
bj.job.update(status=Job.RUNNING, progress=0, statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(problem_cls, bj, is_2d=True, **bj.flags)
# Make sure all images have at least 224x224 dimensions
# and that minshape / maxshape * minshape >= 224
# 0 = Grayscale (if input RGB, convert to grayscale)
# 1,2,3 = rgb channel
nuc_channel = bj.parameters.nuc_channel
resized = {}
for bfimg in in_imgs:
fn = os.path.join(in_path, bfimg.filename)
img = imageio.imread(fn)
if len(img.shape) > 2 and nuc_channel == 0:
gray_rgb = False
if np.array_equal(img[:,:,0],img[:,:,1]) and np.array_equal(img[:,:,0],img[:,:,2]):
gray_rgb = True
img = skimage.color.rgb2gray(img) * 255
img = img.astype(np.uint8)
# Invert intensity if not grayscale img ie. expect the image
# to be H&E stained image with dark nuclei
if not gray_rgb:
img = np.invert(img)
minshape = min(img.shape[:2])
maxshape = max(img.shape[:2])
if minshape != maxshape or minshape < 224:
resized[bfimg.filename] = img.shape
padshape = []
for i in range(2):
if img.shape[i] < max(224,maxshape):
padshape.append((0,max(224,maxshape)-img.shape[i]))
else:
padshape.append((0,0))
if len(img.shape) == 3:
padshape.append((0,0))
img = np.pad(img, padshape, 'constant', constant_values=0)
imageio.imwrite(os.path.join(tmp_path, bfimg.filename), img)
# 2. Run image analysis workflow
bj.job.update(progress=25, statusComment="Launching workflow...")
# Add here the code for running the analysis script
#"--chan", "{:d}".format(nuc_channel)
cmd = ["python", "-m", "cellpose", "--dir", tmp_path, "--pretrained_model", "nuclei", "--save_tif", "--no_npy", "--chan", "{:d}".format(nuc_channel), "--diameter", "{:f}".format(bj.parameters.diameter), "--cellprob_threshold", "{:f}".format(bj.parameters.prob_threshold)]
status = subprocess.run(cmd)
if status.returncode != 0:
print("Running Cellpose failed, terminate")
sys.exit(1)
# Crop to original shape
for bimg in in_imgs:
shape = resized.get(bimg.filename, None)
if shape:
img = imageio.imread(os.path.join(tmp_path,bimg.filename_no_extension+"_cp_masks.tif"))
img = img[0:shape[0], 0:shape[1]]
imageio.imwrite(os.path.join(out_path,bimg.filename), img)
else:
shutil.copy(os.path.join(tmp_path,bimg.filename_no_extension+"_cp_masks.tif"), os.path.join(out_path,bimg.filename))
# 3. Upload data to BIAFLOWS
upload_data(problem_cls, bj, in_imgs, out_path, **bj.flags, monitor_params={
"start": 60, "end": 90, "period": 0.1,
"prefix": "Extracting and uploading polygons from masks"})
# 4. Compute and upload metrics
bj.job.update(progress=90, statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, bj, in_imgs, gt_path, out_path, tmp_path, **bj.flags)
# 5. Pipeline finished
bj.job.update(progress=100, status=Job.TERMINATED, status_comment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME"))
problem_cls = CLASS_OBJSEG
with BiaflowsJob.from_cli(argv) as bj:
bj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialization...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, bj, is_2d=True, **bj.flags)
list_imgs = [image.filepath for image in in_imgs]
# 2. Run Stardist model on input images
bj.job.update(progress=25, statusComment="Launching workflow...")
#Loading pre-trained Stardist model
np.random.seed(17)
lbl_cmap = random_label_cmap()
model_fluo = StarDist2D(None,
name='2D_versatile_fluo',
basedir='/models/')
model_he = StarDist2D(None, name='2D_versatile_he', basedir='/models/')
#Go over images
for img_path in list_imgs:
fluo = True
img = imageio.imread(img_path)
n_channel = 3 if img.ndim == 3 else 1
if n_channel == 3:
# Check if 3-channel grayscale image or actually an RGB image
if np.array_equal(img[:, :, 0],
img[:, :, 1]) and np.array_equal(
img[:, :, 0], img[:, :, 2]):
img = skimage.color.rgb2gray(img)
else:
fluo = False
# normalize channels independently (0,1,2) normalize channels jointly (0,1)
axis_norm = (0, 1)
img = normalize(img,
bj.parameters.stardist_norm_perc_low,
bj.parameters.stardist_norm_perc_high,
axis=axis_norm)
#Stardist model prediction with thresholds
if fluo:
labels, details = model_fluo.predict_instances(
img,
prob_thresh=bj.parameters.stardist_prob_t,
nms_thresh=bj.parameters.stardist_nms_t)
else:
labels, details = model_he.predict_instances(
img,
prob_thresh=bj.parameters.stardist_prob_t,
nms_thresh=bj.parameters.stardist_nms_t)
# Convert labels to uint16 for BIAFLOWS
labels = labels.astype(np.uint16)
imageio.imwrite(os.path.join(out_path, os.path.basename(img_path)),
labels)
# 3. Upload data to BIAFLOWS
upload_data(problem_cls,
bj,
in_imgs,
out_path,
**bj.flags,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1,
"prefix":
"Extracting and uploading polygons from masks"
})
# 4. Compute and upload metrics
bj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, bj, in_imgs, gt_path, out_path, tmp_path,
**bj.flags)
# 5. Pipeline finished
bj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")
def main(argv):
base_path = "{}".format(os.getenv("HOME")) # Mandatory for Singularity
problem_cls = CLASS_OBJSEG
with BiaflowsJob.from_cli(argv) as bj:
bj.job.update(status=Job.RUNNING,
progress=0,
statusComment="Initialisation...")
# 1. Prepare data for workflow
in_imgs, gt_imgs, in_path, gt_path, out_path, tmp_path = prepare_data(
problem_cls, bj, is_2d=True, **bj.flags)
plugindir = "/app/plugins"
pipeline = "/app/CP_detect_nuclei.cppipe"
file_list = os.path.join(tmp_path, "file_list.txt")
fh = open(file_list, "w")
for image in in_imgs:
fh.write(image.filepath + "\n")
fh.close()
# 2. Run CellProfiler pipeline
bj.job.update(progress=25, statusComment="Launching workflow...")
mod_pipeline = parseCPparam(bj, pipeline, tmp_path)
shArgs = [
"python", "/app/CellProfiler/CellProfiler.py", "-c", "-r", "-b",
"--do-not-fetch", "-p", mod_pipeline, "-i", in_path, "-o",
out_path, "-t", tmp_path, "--plugins-directory", plugindir,
"--file-list", file_list
]
return_code = call(" ".join(shArgs),
shell=True,
cwd="/app/CellProfiler")
if return_code != 0:
err_desc = "Failed to execute the CellProfiler pipeline (return code: {})".format(
return_code)
bj.job.update(progress=50, statusComment=err_desc)
raise ValueError(err_desc)
# 3. Upload data to BIAFLOWS
upload_data(problem_cls,
bj,
in_imgs,
out_path,
**bj.flags,
monitor_params={
"start": 60,
"end": 90,
"period": 0.1,
"prefix":
"Extracting and uploading polygons from masks"
})
# 4. Compute and upload metrics
bj.job.update(progress=90,
statusComment="Computing and uploading metrics...")
upload_metrics(problem_cls, bj, in_imgs, gt_path, out_path, tmp_path,
**bj.flags)
# 5. Pipeline finished
bj.job.update(progress=100,
status=Job.TERMINATED,
status_comment="Finished.")