Package qupath.ext.biop.spotiflow
Class SpotiflowBuilder
java.lang.Object
qupath.ext.biop.spotiflow.SpotiflowBuilder
Spot detection based on the following method:
Albert Dominguez Mantes et al. "Spotiflow: accurate and efficient spot detection for fluorescence microscopy with deep stereographic flow regression" Cold Spring Harbor Laboratory - bioRxiv, 2024. doi: 10.1101/2024.02.01.578426See the main repo at https://github.com/weigertlab/spotiflow
Very much inspired by qupath-extension-cellpose at https://github.com/BIOP/qupath-extension-cellpose
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionaddParameter
(String flagName) Generic means of adding a spotiflow parameteraddParameter
(String flagName, String flagValue) Generic means of adding a spotiflow parameterbuild()
Create aSpotiflow
, all ready for detection.channels
(int... channels) Specify channels.Specify channels by name.doSubpixel
(boolean doSubpixel) Allows to go subpixel resolutionprocess3d
(boolean process3d) Allows to process all slicessavePredictionImages
(boolean savePredictionImages) Set input folder to predict spotsAllows to go subpixel resolutionAllows to go subpixel resolutionsetMinDistance
(double minDistance) Set minimum distance between spots for NMSsetModelDir
(File modelDir) Set model directory to use for predictionsetPretrainedModelName
(String modelName) Set pre-trained model to use for predictionsetProbabilityThreshold
(double probabilityThreshold) Set probability threshold for peak detectionsetTrainingInputDir
(File inputDir) Set input folder to train a new modelsetTrainingOutputDir
(File outputDir) Set output folder to save a new modeltempDirectory
(File inputDir) Set input folder to predict spotsuseGPU
(boolean useGPU) Enable CPU / GPU usage
-
Constructor Details
-
SpotiflowBuilder
protected SpotiflowBuilder()Build a spotiflow model
-
-
Method Details
-
tempDirectory
Set input folder to predict spots- Parameters:
inputDir
- path to prediction input dir- Returns:
- this builder
-
savePredictionImages
Set input folder to predict spots- Parameters:
savePredictionImages
- overwrite variable- Returns:
- this builder
-
setPretrainedModelName
Set pre-trained model to use for prediction- Parameters:
modelName
- name of the pre-trained model- Returns:
- this builder
-
setProbabilityThreshold
Set probability threshold for peak detection- Parameters:
probabilityThreshold
-- Returns:
- this builder
-
setMinDistance
Set minimum distance between spots for NMS- Parameters:
minDistance
-- Returns:
- this builder
-
setModelDir
Set model directory to use for prediction- Parameters:
modelDir
- path to the custom model- Returns:
- this builder
-
channels
Specify channels. Useful for detecting nuclei for one channel within a multi-channel image, or potentially for trained models that support multi-channel input.- Parameters:
channels
- 0-based indices of the channels to use- Returns:
- this builder
-
channels
Specify channels by name. Useful for detecting nuclei for one channel within a multi-channel image, or potentially for trained models that support multi-channel input.- Parameters:
channels
- channels names to use- Returns:
- this builder
-
setTrainingInputDir
Set input folder to train a new model- Parameters:
inputDir
- path to the training input dir- Returns:
- this builder
-
setTrainingOutputDir
Set output folder to save a new model- Parameters:
outputDir
- path to the training input dir- Returns:
- this builder
-
useGPU
Enable CPU / GPU usage- Parameters:
useGPU
- override useGPU- Returns:
- this builder
-
process3d
Allows to process all slices- Parameters:
process3d
- override process3d- Returns:
- this builder
-
doSubpixel
Allows to go subpixel resolution- Parameters:
doSubpixel
- override doSubpixel- Returns:
- this builder
-
setClassChannelName
Allows to go subpixel resolution- Returns:
- this builder
-
setClass
Allows to go subpixel resolution- Returns:
- this builder
-
addParameter
Generic means of adding a spotiflow parameter- Parameters:
flagName
- the name of the flag, eg. "save_every"flagValue
- the value that is linked to the flag, eg. "20". Can be an empty string or null if it is not needed- Returns:
- this builder
-
addParameter
Generic means of adding a spotiflow parameter- Parameters:
flagName
- the name of the flag, eg. "save_every" * @param flagName the name of the flag, eg. "save_every"- Returns:
- this builder
-
build
Create aSpotiflow
, all ready for detection.- Returns:
- a new
Spotiflow
instance
-