diff --git a/topics/imaging/tutorials/hela-screen-analysis/tutorial.md b/topics/imaging/tutorials/hela-screen-analysis/tutorial.md index 0a587539c46605..521803cb12e3d9 100644 --- a/topics/imaging/tutorials/hela-screen-analysis/tutorial.md +++ b/topics/imaging/tutorials/hela-screen-analysis/tutorial.md @@ -19,7 +19,7 @@ objectives: - "How to analyse extracted features from an imaging screen in Galaxy." key_points: - Galaxy workflows can be used to scale image analysis pipelines to whole screens. -- Segmented objects can be filtered using the **Filter segmentation** tool. +- Segmented objects can be filtered using the **Filter label map by rules** tool. - Galaxy charts can be used to compare features extracted from screens showing cells with different treatments. requirements: - @@ -79,7 +79,7 @@ The dataset required for this tutorial contains a screen of DAPI stained HeLa nu > > {% snippet faqs/galaxy/datasets_import_from_data_library.md %} > -> 3. **Unzip file** {% icon tool %} with the following parameters: +> 3. {% tool [Unzip](toolshed.g2.bx.psu.edu/repos/imgteam/unzip/unzip/6.0+galaxy0) %} with the following parameters: > - {% icon param-file %} *"input_file"*: `Zipped ` input file > - *"Extract single file"*: `Single file` > - *"Filepath"*: `B2--W00026--P00001--Z00000--T00000--dapi.tif` @@ -88,7 +88,7 @@ The dataset required for this tutorial contains a screen of DAPI stained HeLa nu > > {% snippet faqs/galaxy/datasets_rename.md %} > -> 5. **Unzip file** {% icon tool %} with the following parameters: +> 5. {% tool [Unzip](toolshed.g2.bx.psu.edu/repos/imgteam/unzip/unzip/6.0+galaxy0) %} with the following parameters: > - {% icon param-file %} *"input_file"*: `Zipped ` input file > - *"Extract single file"*: `All files` > @@ -106,7 +106,7 @@ The dataset required for this tutorial contains a screen of DAPI stained HeLa nu > > {% snippet faqs/galaxy/datasets_import_from_data_library.md %} > -> 8. **Unzip** {% icon tool %} to extract the zipped screen: +> 8. {% tool [Unzip](toolshed.g2.bx.psu.edu/repos/imgteam/unzip/unzip/6.0+galaxy0) %} to extract the zipped screen: > - {% icon param-file %} *"input_file"*: `Zipped ` input file > - *"Extract single file"*: `All files` > @@ -131,19 +131,19 @@ First, we will create and test a workflow which extracts mean DAPI intensity, ar > Create feature extraction workflow > -> 1. **Filter Image** {% icon tool %} with the following parameters to smooth the image: -> - *"Image type"*: `Gaussian Blur` +> 1. {% tool [Filter 2D image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3-3) %} with the following parameters to smooth the image: +> - *"Filter type"*: `Gaussian Blur` > - *"Radius/Sigma"*: `3` > - {% icon param-file %} *"Source file"*: `testinput.tif` file -> 2. **Auto Threshold** {% icon tool %} with the following parameters to segment the image: -> - {% icon param-file %} *"Source file"*: output of **Filter image** {% icon tool %} +> 2. {% tool [Threshold image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_auto_threshold/ip_threshold/0.0.5-2) %} with the following parameters to segment the image: +> - {% icon param-file %} *"Source file"*: output of {% tool [Filter 2D image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3-3) %} > - *"Threshold Algorithm"*: `Otsu` > - *"Dark Background"*: `Yes` -> 3. **Split objects** {% icon tool %} with the following parameters to split touching objects: -> - {% icon param-file %} *"Source file"*: output of **Auto Threshold** {% icon tool %} +> 3. {% tool [Split binary image using watershed transformation](toolshed.g2.bx.psu.edu/repos/imgteam/2d_split_binaryimage_by_watershed/ip_2d_split_binaryimage_by_watershed/0.0.1-2) %} with the following parameters to split touching objects: +> - {% icon param-file %} *"Source file"*: output of {% tool [Threshold image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_auto_threshold/ip_threshold/0.0.5-2) %} > - *"Minimum distance between two objects."*: `20` -> 4. **2D Feature Extraction** {% icon tool %} with the following parameters to extract features from the segmented objects: -> - {% icon param-file %} *"Label file"*: output of **Split objects** {% icon tool %} +> 4. {% tool [Extract 2D features](toolshed.g2.bx.psu.edu/repos/imgteam/2d_feature_extraction/ip_2d_feature_extraction/0.1.1-2) %} with the following parameters to extract features from the segmented objects: +> - {% icon param-file %} *"Label file"*: output of {% tool [Split binary image using watershed transformation](toolshed.g2.bx.psu.edu/repos/imgteam/2d_split_binaryimage_by_watershed/ip_2d_split_binaryimage_by_watershed/0.0.1-2) %} > - *"Use original image to compute additional features."*: `No original image` > - *"Select features to compute"*: `Select features` > - *"Available features"*: @@ -151,12 +151,12 @@ First, we will create and test a workflow which extracts mean DAPI intensity, ar > - {% icon param-check %} `Area` > - {% icon param-check %} `Eccentricity` > - {% icon param-check %} `Major Axis Length` -> 5. **Filter segmentation** {% icon tool %} with the following parameters to filter the label map from 3. with the extracted features and a set of rules: -> - {% icon param-file %} *"Source file"*: output of **Split objects** {% icon tool %} -> - {% icon param-file %} *"Feature file"*: output of **2D Feature Extraction** {% icon tool %} +> 5. {% tool [Filter label map by rules](toolshed.g2.bx.psu.edu/repos/imgteam/2d_filter_segmentation_by_features/ip_2d_filter_segmentation_by_features/0.0.1) %} with the following parameters to filter the label map from 3. with the extracted features and a set of rules: +> - {% icon param-file %} *"Source file"*: output of {% tool [Split binary image using watershed transformation](toolshed.g2.bx.psu.edu/repos/imgteam/2d_split_binaryimage_by_watershed/ip_2d_split_binaryimage_by_watershed/0.0.1-2) %} +> - {% icon param-file %} *"Feature file"*: output of {% tool [Extract 2D features](toolshed.g2.bx.psu.edu/repos/imgteam/2d_feature_extraction/ip_2d_feature_extraction/0.1.1-2) %} > - {% icon param-file %} *"Rules file"*: rules file -> 6. **2D Feature Extraction** {% icon tool %} with the following parameters to extract features the final readout from the segmented objects: -> - {% icon param-file %} *"Label file"*: output of **Filter segmentation** {% icon tool %} +> 6. {% tool [Extract 2D features](toolshed.g2.bx.psu.edu/repos/imgteam/2d_feature_extraction/ip_2d_feature_extraction/0.1.1-2) %} with the following parameters to extract features the final readout from the segmented objects: +> - {% icon param-file %} *"Label file"*: output of {% tool [Filter label map by rules](toolshed.g2.bx.psu.edu/repos/imgteam/2d_filter_segmentation_by_features/ip_2d_filter_segmentation_by_features/0.0.1) %} > - *"Use original image to compute additional features."*: `Use original image` > - {% icon param-file %} *"Original image file"*: `testinput.tif` file > - *"Select features to compute"*: `Select features` @@ -166,13 +166,13 @@ First, we will create and test a workflow which extracts mean DAPI intensity, ar > - {% icon param-check %} `Major Axis Length` > 7. Now we can extract the workflow for batch processing > - Name it "feature_extraction". -> - Remember to exclude **Unzip** {% icon tool %} by unchecking the tool. +> - Remember to exclude {% tool [Unzip](toolshed.g2.bx.psu.edu/repos/imgteam/unzip/unzip/6.0+galaxy0) %} by unchecking the tool. > - Don't treat `B2.zip` and `B3.zip` as inputs (the workflow is supposed to be applied to the images directly). > > {% snippet faqs/galaxy/workflows_extract_from_history.md %} > > 8. Edit the workflow you just created -> - Add the tool **Input dataset** {% icon tool %} and name it `input image`. +> - Add the tool {% tool Input dataset %} and name it `input image`. > - Name the input for the rules file `filter rules`. > - Mark the results of steps 5 and 6 as outputs (by clicking on the asterisk next to the output name). > @@ -191,12 +191,12 @@ Now we want to apply our extracted workflow to `original data` and merge the res > 1. Create a new workflow in the workflow editor. > > {% snippet faqs/galaxy/workflows_create_new.md %} -> 2. Add a **Input dataset collection** node and name it `input images` -> 3. Add a **Input dataset** node and name it `rules` +> 2. Add a {% tool Input dataset collection %} node and name it `input images` +> 3. Add a {% tool Input dataset %} node and name it `rules` > 4. Add the **feature_extraction** workflow as node. -> - {% icon param-file %} *"input image"*: `input images` output of **Input dataset collection** {% icon tool %} -> - {% icon param-file %} *"filter rules"*: `rules` output of **Input dataset** {% icon tool %} -> 5. Add a **Collapse Collection** {% icon tool %} node. +> - {% icon param-file %} *"input image"*: `input images` output of {% tool Input dataset collection %} +> - {% icon param-file %} *"filter rules"*: `rules` output of {% tool Input dataset %} +> 5. Add a {% tool Collapse Collection %} node. > - {% icon param-file %} *"Collection of files to collapse into single dataset"*: output of **feature_extraction** workflow > - *"Keep one header line"*: `Yes` > - *"Append File name"*: `No` @@ -225,7 +225,7 @@ Finally, we want to plot the results for better interpretation. > Plot feature extraction results > -> 1. Click on the `Visualize this data` {% icon galaxy-barchart %} icon of the **Collapse Collection** {% icon tool %} results. +> 1. Click on the `Visualize this data` {% icon galaxy-barchart %} icon of the {% tool Collapse Collection %} results. > 2. Run `Box plot` with the following parameters: > - *"Provide a title"*: `Screen features` > - *"X-Axis label"*: diff --git a/topics/imaging/tutorials/imaging-introduction/tutorial.md b/topics/imaging/tutorials/imaging-introduction/tutorial.md index 7b94e3827aca36..9e9837e8b31fca 100644 --- a/topics/imaging/tutorials/imaging-introduction/tutorial.md +++ b/topics/imaging/tutorials/imaging-introduction/tutorial.md @@ -89,7 +89,7 @@ Now, we can extract metadata from an image. > Extract Image Metadata > -> 1. {% tool [Image Info](toolshed.g2.bx.psu.edu/repos/imgteam/image_info/ip_imageinfo/0.2) %} with the following parameters to extract metadata from the image: +> 1. {% tool [Show image info](toolshed.g2.bx.psu.edu/repos/imgteam/image_info/ip_imageinfo/0.2) %} with the following parameters to extract metadata from the image: > - {% icon param-file %} *"Input Image"*: `input.tif` file (output of the previous step) > 2. Click on the {% icon galaxy-eye %} (eye) icon next to the file name, to look at the file content and search for image acquisition information > @@ -113,10 +113,9 @@ Not all tools can handle all image formats. Especially proprietary microscope im > Convert Image > -> 1. {% tool [Convert image](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy0) %} with the following parameters to convert the image to PNG: +> 1. {% tool [Convert image format](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy2) %} with the following parameters to convert the image to PNG: > - {% icon param-file %} *"Input Image"*: `input.tif` file > - *"Output data type"*: `PNG` -> - *"Pyramid image"*: `No Pyramid` > 2. Rename {% icon galaxy-pencil %} the generated file to `viz_input` > 3. Click on the {% icon galaxy-eye %} (eye) icon next to the file name to look at the file content > @@ -142,12 +141,12 @@ Next we will normalize the histogram to improve the contrast. We do this using a > Normalize Histogram and Convert Image > -> 1. {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %} with the following parameters to normalize the histogram of the image: +> 1. {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %} with the following parameters to normalize the histogram of the image: > - {% icon param-file %} *"Source file"*: `input.tif` file > - *"Histogram Equalization Algorithm"*: `CLAHE` > 2. Rename {% icon galaxy-pencil %} the generated file to `input_normalized` -> 3. {% tool [Convert image](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy0) %} with the following parameters to convert the image to PNG: -> - {% icon param-file %} *"Input Image"*: `input_normalized` file (output of {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %}) +> 3. {% tool [Convert image format](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy2) %} with the following parameters to convert the image to PNG: +> - {% icon param-file %} *"Input Image"*: `input_normalized` file (output of {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %}) > - *"Output data type"*: `PNG` > 4. Rename {% icon galaxy-pencil %} the generated file to `viz_normalized` > 5. Click on the {% icon galaxy-eye %} (eye) icon next to the file name, to look at the file content @@ -165,17 +164,17 @@ Specific features of interest (e.g., edges, noise) can be enhanced or suppressed > Filter image > -> 1. {% tool [Filter Image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3) %} with the following parameters to smooth the image: -> - *"Image type"*: `Gaussian Blur` +> 1. {% tool [Filter 2D image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3-3) %} with the following parameters to smooth the image: +> - *"Filter type"*: `Gaussian Blur` > - *"Radius/Sigma"*: `3` > - {% icon param-file %} *"Source file"*: `input.tif` file > 2. Rename {% icon galaxy-pencil %} the generated file to `input_smoothed` -> 3. {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %} with the following parameters to normalize the histogram of the image: -> - {% icon param-file %} *"Source file"*: `input_smoothed` file (output of {% tool [Filter Image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3) %}) +> 3. {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %} with the following parameters to normalize the histogram of the image: +> - {% icon param-file %} *"Source file"*: `input_smoothed` file (output of {% tool [Filter 2D image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3-3) %}) > - *"Histogram Equalization Algorithm"*: `CLAHE` > 4. Rename {% icon galaxy-pencil %} the generated file to `input_smoothed_normalized` -> 5. {% tool [Convert image](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy0) %} with the following parameters to convert the image to PNG: -> - {% icon param-file %} *"Input Image"*: `input_smoothed_normalized` file (output of {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %}) +> 5. {% tool [Convert image format](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy2) %} with the following parameters to convert the image to PNG: +> - {% icon param-file %} *"Input Image"*: `input_smoothed_normalized` file (output of {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %}) > - *"Output data type"*: `PNG` > 6. Rename {% icon galaxy-pencil %} the generated file to `viz_smoothed_normalized` > 7. Click on the {% icon galaxy-eye %} (eye) icon next to the file name, to look at the file content and compare the result with `viz_normalized`. You can observe that `viz_smoothed_normalized` has significant reduced noise. @@ -192,41 +191,41 @@ Objects of interest like nuclei can be segmented by using a smoothed image and t > Segment image > -> 1. {% tool [Auto Threshold](toolshed.g2.bx.psu.edu/repos/imgteam/2d_auto_threshold/ip_threshold/0.0.5) %} with the following parameters to segment the image: -> - {% icon param-file %} *"Source file"*: `input_smoothed` file (output of {% tool [Filter Image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3) %}) +> 1. {% tool [Threshold image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_auto_threshold/ip_threshold/0.0.5-2) %} with the following parameters to segment the image: +> - {% icon param-file %} *"Source file"*: `input_smoothed` file (output of {% tool [Filter 2D image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_simple_filter/ip_filter_standard/0.0.3-2) %}) > - *"Threshold Algorithm"*: `Otsu` > - *"Dark Background"*: `Yes` > 2. Rename {% icon galaxy-pencil %} the generated file to `input_segmented` -> 3. {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %} with the following parameters to segment the image: -> - {% icon param-file %} *"Binary Image File"*: `input_segmented` file (output of {% tool [Auto Threshold](toolshed.g2.bx.psu.edu/repos/imgteam/2d_auto_threshold/ip_threshold/0.0.5) %}) +> 3. {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %} with the following parameters to segment the image: +> - {% icon param-file %} *"Binary Image File"*: `input_segmented` file (output of {% tool [Threshold image](toolshed.g2.bx.psu.edu/repos/imgteam/2d_auto_threshold/ip_threshold/0.0.5-2) %}) > 4. Rename {% icon galaxy-pencil %} the generated file to `input_segmented_labeled` -> 5. {% tool [Convert image](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy0) %} with the following parameters to convert the image to PNG: -> - {% icon param-file %} *"Input Image"*: `input_segmented_labeled` file (output of {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %}) +> 5. {% tool [Convert image format](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy2) %} with the following parameters to convert the image to PNG: +> - {% icon param-file %} *"Input Image"*: `input_segmented_labeled` file (output of {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %}) > - *"Output data type"*: `PNG` > 6. Rename {% icon galaxy-pencil %} the converted image to `viz_segmented` > > > > > -> > 1. What does {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %} do? (Hint: check the tool help section) +> > 1. What does {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %} do? (Hint: check the tool help section) > > 2. View the `viz_segmented` image from the last step, what do you see? > > - Can you explain this result? -> > 3. Exercise: Try to make the information in this image better visible (Hint: {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %}) +> > 3. Exercise: Try to make the information in this image better visible (Hint: {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %}) > > > > > > > > 1. The tool assigns each connected component (e.g., segmented cell) in the image an object id and stores it as the intensity value. > > > 2. The image looks completely black. -> > > The object IDs generated by {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %} are relatively low. +> > > The object IDs generated by {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %} are relatively low. > > > Since the IDs are stored as intensity values, these are too low to be visible in this case. Nevertheless, there is more > > > information in this image than meets the eye. > > > 3. To make labeled objects visible, the values have to be stretched to a larger range of visible intensity values. We > > > can do that by equalizing the histogram again: > > > -> > > - {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %} with the following parameters to normalize the intensity values: -> > > - {% icon param-file %} *"Source file"*: `input_segmented_labeled` file (output of {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %}) +> > > - {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %} with the following parameters to normalize the intensity values: +> > > - {% icon param-file %} *"Source file"*: `input_segmented_labeled` file (output of {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %}) > > > - *"Histogram Equalization Algorithm"*: `CLAHE` > > > -> > > - {% tool [Convert image](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy0) %} with the following parameters to convert the image to PNG: -> > > - {% icon param-file %} *"Input Image"*: output of {% tool [Histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1) %} +> > > - {% tool [Convert image format](toolshed.g2.bx.psu.edu/repos/imgteam/bfconvert/ip_convertimage/6.7.0+galaxy2) %} with the following parameters to convert the image to PNG: +> > > - {% icon param-file %} *"Input Image"*: output of {% tool [Perform histogram equalization](toolshed.g2.bx.psu.edu/repos/imgteam/2d_histogram_equalization/ip_histogram_equalization/0.0.1-2) %} > > > - *"Output data type"*: `PNG` > > > > > > The information contained in the original image has now become visible to the human eye: @@ -236,24 +235,24 @@ Objects of interest like nuclei can be segmented by using a smoothed image and t > {: .question} > > -> 7. {% tool [Overlay Images](toolshed.g2.bx.psu.edu/repos/imgteam/overlay_images/ip_overlay_images/0.0.3) %} with the following parameters to convert the image to PNG: +> 7. {% tool [Overlay images](toolshed.g2.bx.psu.edu/repos/imgteam/overlay_images/ip_overlay_images/0.0.3-3) %} with the following parameters to convert the image to PNG: > - *"How to visualize the overlay?"*: `Segmentation mask over image` > - {% icon param-file %} *"Image"*: `viz_normalized` file -> - {% icon param-file %} *"Label image"*: `input_segmented_labeled` file (output of {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %}) +> - {% icon param-file %} *"Label image"*: `input_segmented_labeled` file (output of {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %}) > - *"Contour thickness"*: `2` > - *"Contour color"*: `red` > - *"Show labels"*: `yes` > - *"Label color"*: `yellow` > 8. Click on the {% icon galaxy-eye %} (eye) icon next to the file name, to look at the file content and assess the segmentation performance -> 9. {% tool [Count Objects](toolshed.g2.bx.psu.edu/repos/imgteam/count_objects/ip_count_objects/0.0.5) %} with the following parameters to count the segmented objects in the image: -> - {% icon param-file %} *"Source file"*: `input_segmented_labeled` file (output of {% tool [Binary 2 Label](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4) %}) +> 9. {% tool [Count objects in label map](toolshed.g2.bx.psu.edu/repos/imgteam/count_objects/ip_count_objects/0.0.5-2) %} with the following parameters to count the segmented objects in the image: +> - {% icon param-file %} *"Source file"*: `input_segmented_labeled` file (output of {% tool [Convert binary image to label map](toolshed.g2.bx.psu.edu/repos/imgteam/binary2labelimage/ip_binary_to_labelimage/0.4-2) %}) > > > > > > > How many objects were segmented? > > > > > -> > > The {% tool [Count Objects](toolshed.g2.bx.psu.edu/repos/imgteam/count_objects/ip_count_objects/0.0.5) %} tool counted 425 objects. +> > > The {% tool [Count objects in label map](toolshed.g2.bx.psu.edu/repos/imgteam/count_objects/ip_count_objects/0.0.5-2) %} tool counted 425 objects. > > {: .solution } > {: .question} {: .hands_on}