Detecting dendritic spines (Segments)

ROI

Sets the processing and analysis target space.

–

Current View

The selected Z plane and the viewer area are processed.

–

Current Plane

The selected Z plane is processed (XY).

–

Current Time Point

The selected time point is processed (XYZ).

–

Current Image Set

The complete dataset (XYZ and time) is processed.

–

Custom

Allows to mix the previous methods.
Note: Use the Custom option during the pipeline setting and testing. Set a sub volume (XY, Planes, Time Points, channels) of your dataset on which perform the trial. This will speed up the setting process.

Channels

Sets the processing and analysis target channels. Selecting a single channel, all the operations in the pipeline will be forced to use it.

Scaling

Sets the scaling of the dataset, which reduces it size. The measurements will not be modified by the scaling factor

Crop input data

Sets the limitation of the data used for the calculation to only the cropped selection defined above. If this option is not selected, the entire image set is used for the calculation.

Bounds

Sets the analysis area edges. The whole XY bounds, the viewing area or a custom space can be applied.

Planes

Sets the analysis planes range. A single plane, a range of planes or the whole stack can be selected.

Time Points

Sets the analysis time points range. A single time pint, a range of time points or the whole movie can be selected.

Model source

Sets the type of model to be used. Each has a set of settings which need to be properly adjusted to get the best result.

–

ONNX or CZANN model

Option to use locally saved 2D ONNX-based Deep Learning models (semantic):

ONNX: any compatible ONNX model including ONNX zoo models which use ONNX opset version 12 and lower (opset 7).

Zeiss DL models: including CZMODEL and CZANN

–

arivis Cloud AI model store

Option to use a DL instance segmentation model from the list of downloaded models from arivis Cloud AI model store.

Model

Sets a DL model to be used. The operation will extract all necessary info from the loaded model and update the UI accordingly.

Note: To select an ONNX or CZANN model, click or paste the path in the text field

Note: To access the arivis Cloud AI model store, click . Download the models and click to refresh the list of models available.

Channels

Select the channels that will be used for analysis. Channels are available based on the selected model and its input shape

Outputs

Sets the output of the Operation.

Note: click on to select the desired output(s).

Normalization

Sets a normalization range to be applied on the data before inference.

–

Full range

Full range uses the intensity range of the input data pixel type, e.g. for 8bit it is [0,255].

–

Data range

Data range uses the minimum and maximum values of in-put data over all timepoints.

–

Data range per timepoint

Data range per timepoint, uses the minimum and maximum values of input data per timepoint.

–

Manual

Manual allows users to select any desired range using the picker to be used for all channels and timepoints.

Customize model settings

Select this checkbox to be able to modify specific model parameters. Otherwise, default values are used.

–

Min overlap

Sets a minimum voxel count for overlapping tiles used in the model. The default values are extracted from the loaded model and are zero if no value has been defined in the metadata.

–

Input range

Sets the intensity range. The default range is between 0 and 1. Change this range to match the trained model.

–

Prediction range

Sets the range to match the output of the trained model. The de-fault range is considered to be between 0 and 1.

Apply tile blending

Applies smoother transition between the results of two tiles and reduces the tiling artifacts.

Method

Sets the method for tracing spines. Each has a set of settings which need to be properly adjusted to get the best result.

–

AI-assisted

This method uses a pre-trained Deep Learning Model (DeepD3) to detect spine heads and then trace them to the neurite.

In details, the deep learning model processes the intensity channel to create a probability map of the spines on which the spine heads will be detected. The intensity data is then used to connect the found spine heads to the trace by going along the neck.

–

Use Segments

This method uses segments created by a previous operation as spines (e.g. Blob Finder, Deep Learning Segmenter or imported in the pipeline via Import Document Object Operation).

The provided objects are not modified by this operation or connected to the trace. Instead, they are used as starting points for the spine tracing to create new approximations of the spines. The intensity data is then used to connect the provided spine heads to the trace by going along the neck..

–

Use Probability Map

The method is very similar to the AI-assisted method, but instead of using the built-in deep learning model to create the probability map, you must provide a pre-calculated probability map. A probability map can be created with an Image Processing operation, for example Machine Learning Probability or Deep Learning Reconstruction.

Input

–

Traces

Select an already existing neuron or neurite traces of a preceding Operation, e.g. Neuron Tracer or Import Document Objects to which the spines will be connected.

–

Channel/ Trace channel

Sets Intensity data where neurons and spines (necks) are visible.

Note: Trace channel is only available if Use Segments and Use Probability Map is selected.

–

Spine Segments

Sets segments representing the spine heads to be connected to the traces. The segments can be created with any of preceding operations or imported.

Note: Spine Segments is only available if the Use Segments method is selected.

–

Probability map

Sets pre-calculated image data of the spine heads (probability Map). The image should have high intensity values where the spine heads are. A probability map can be created with an Image Processing operation, for example Machine Learning Probability or Deep Learning Reconstruction.

Note: Probability map is only available if the Use Probability Map method is selected.

Parameters

–

Max. spine length

Sets the maximum distance from the spine head center to the trace along the neck. Spines that are longer are discarded.

Note: Increasing this parameter will increase the runtime since a larger area is scanned for spines.

Note: You can use the Measurements tool to determine the value.

Head threshold

Sets Threshold to detect the spine heads on the probability map found by the deep learning model used.

Note: Higher values will result in fewer voxels being classified as spines and vice versa. This does not necessarily mean that lower values result in more spines, since two small spine heads can be merged into one by reducing the threshold, if they are close enough.

Note: Head threshold is only available if AI-assisted and Use Probability Map is selected.

Max. overlap

Sets max limit of overlap for the segments with the trace. Segments that have more overlap with the trace are discarded.

Note: Max. overlap is only available if the Use Segments method is selected.

Head size range

Sets the range by size of spine heads to be connected to the trace. Heads that do not fit into the range are discarded.

Note: Head size range is only available if AI-assisted and Use Probability Map is selected. For Use segments it is possible to use before Operations like Object Feature Filter.

Note: You can use the Measurements tool to determine the value.