(requires: 2D Deconvolution)(requires: 3D Deconvolution)
This function removes out of focus blur from the source images using neural networks. It is intended for widefield images and works best for thick samples. It is a preferred choice for under-sampled images, whereas deconvolution is a preferred method for well-sampled images.
See Deconvolution.
Clarify.ai requires valid image metadata (similar to deconvolution). It is a parameterless method which does not increase the resolution and does not denoise the image however it can be combined with NIS.ai > Denoise.ai. Check the Denoise.ai check box next to a channel to perform denoising first before clarifying. Check this check box only for very noisy images with SNR value smaller than 20.
To handle the out-of-focus planes correctly, it is important to know how exactly the image sequence has been acquired. Select the proper microscopic modality from the combo box.
Depending on the Modality setting, set the pinhole/slit size value and choose the proper units.
Specify magnification of the objective used to capture the image sequence.
Enter the numerical aperture of the objective.
Enter the refraction index of the immersion medium used. Predefined refraction indexes of different media can be selected from the pull-down menu.
Enter the image calibration in Ξm/px.
Check if you need to create new document. Otherwise the clarifying is applied to the original image.
Select which channels will be clarified and which will be denoised. You can also adjust the emission wavelength. To revert the changes, click 
.
If checked, the clarifying preview is shown in the original image.
Confirms the settings and performs the clarifying.
Closes the window without executing any process.
(requires: Local Option)(requires: 2D Deconvolution)(requires: 3D Deconvolution)
Opens the Restore.ai dialog window. This function is designed to be used when denoise and deconvolution processes are combined. It can be applied on all types of fluorescence images (widefield, confocal, 2D/3D, etc.).
To handle the out-of-focus planes correctly, it is important to know how exactly the image sequence has been acquired. Select the proper microscopic modality from the combo box.
Specify magnification of the objective used to capture the image sequence.
Enter the numerical aperture of the objective.
Enter refraction index of the immersion medium used. There are some predefined refraction indexes of different media in the nearby pull down menu.
Enter the image calibration in Ξm/px.
Image channels produced by your camera are listed within this table. You can decide which channel(s) shall be processed by checking the check boxes next to the channel names. The emission wavelength value may be edited (except the Live De-Blur method).
Note
Brightfield channels are omitted automatically.
Performs image denoising with the use of neural networks. It can be used on a timelapse or on a single frame. This function is used especially for static scenes because moving objects may get blurred.
Select on which channels the denoising will be performed.
Check this item if creating a new document after denoising is required. Otherwise the denoising is applied to the original image.
If checked, the denoising preview is shown in the original image.
Confirms the settings and performs the clarifying.
Closes the window without executing any process.
(requires: NIS.ai)
Opens the Enhance.ai dialog window. For more information please see NIS.ai.
Channels on which the neural network will be run.
Selects the trained network - either from a file (From File, click to locate the *.eai file) or from a database (From Explorer).
Lists channels on which the network was trained (also shown in ). If a â - â symbol is shown and Trained AI is highlighted red, it indicates that the path to the neural network is incorrect or the network is corrupt. If both the Source channels and Original source channels are highlighted red, there is a mismatch in the channel selection (i.e. less or more channels are selected or there is an RGB / standard channel mismatch).
Opens metadata associated with training of the currently selected neural network.
Shows a preview of the current settings applied to the opened image.
Confirms the settings and runs the process.
Closes the window without executing the process.
(requires: NIS.ai)
Opens the Convert.ai dialog window. For more information please see NIS.ai.
Channels on which the neural network will be run.
Selects the trained network - either from a file (From File, click to locate the *.cai file) or from a database (From Explorer).
Lists channels on which the network was trained (also shown in ). If a â - â symbol is shown and Trained AI is highlighted red, it indicates that the path to the neural network is incorrect or the network is corrupt. If both the Source channels and Original source channels are highlighted red, there is a mismatch in the channel selection (i.e. less or more channels are selected or there is an RGB / standard channel mismatch).
Opens metadata associated with training of the currently selected neural network.
Shows a preview of the current settings applied to the opened image.
Confirms the settings and runs the process.
Closes the window without executing the process.
(requires: NIS.ai)
Opens the Segment.ai dialog window. For more information please see NIS.ai.
Channels on which the neural network will be run.
Selects the trained network - either from a file (From File, click to locate the *.sai file) or from a database (From Explorer).
Lists channels on which the network was trained (also shown in ). If a â - â symbol is shown and Trained AI is highlighted red, it indicates that the path to the neural network is incorrect or the network is corrupt. If both the Source channels and Original source channels are highlighted red, there is a mismatch in the channel selection (i.e. less or more channels are selected or there is an RGB / standard channel mismatch).
Opens metadata associated with training of the currently selected neural network.
Reveals post-processing tools and restrictions used for enhancing the results of the neural network.
For more information about how each feature works, please see Measurement Features.
Shows a preview of the current settings applied to the opened image.
Confirms the settings and runs the process.
Closes the window without executing the process.
(requires: NIS.ai)
Opens the Segment Objects.ai dialog window. For more information please see NIS.ai.
Channels on which the neural network will be run.
Selects the trained network - either from a file (From File, click to locate the *.oai file) or from a database (From Explorer).
Also, Pre-trained AI networks are available:
AI classifier for nuclei detection of all cells (standard).
AI classifier for nuclei detection of all cells (apoptotic and dead analysis).
AI classifier for detection of apoptotic and dead nuclei of cells.
Lists channels on which the network was trained (also shown in ). If a â - â symbol is shown and Trained AI is highlighted red, it indicates that the path to the neural network is incorrect or the network is corrupt. If both the Source channels and Original source channels are highlighted red, there is a mismatch in the channel selection (i.e. less or more channels are selected or there is an RGB / standard channel mismatch).
Opens metadata associated with training of the currently selected neural network.
Reveals post-processing tools and restrictions used for enhancing the results of the neural network. For more information about how each feature works, please see Measurement Features.
Shows a preview of the current settings applied to the opened image.
Confirms the settings and runs the process.
Closes the window without executing the process.
(requires: NIS.ai)
Opens the Train Enhance.ai dialog window. For more information please see NIS.ai.
Training data
Opens a dialog where you can choose a dataset train image file or change the path to a different file.
Removes the path to the dataset train image.
Opens a dialog where you can add another dataset train image file.
Channels
Low light signal channels used for neural training.
High light signal channels used for neural training. AI will be trained to reconstruct the ground truth channels using information in source channels.
Options
You can use an existing AI as a base for the current training. Select this option and browse for the *.eai AI file. See Continue Training.
Number of AI training iterations.
Output
Input the name for your AI used in the Explorer.ai.
Specify the output file where the AI will be stored.
Saves a screenshot of the training graph, so that it can be examined after the training is finished and the progress window is closed. This is useful when training multiple networks by a macro.
Adds the current training into a queue so that it can be executed later ( 
Train Queued) via NIS.ai Explorer on the current workstation. These 
symbols are shown before the training name indicating the queued training.
Sends the current training to the computer cluster system running HTCondor. System automatically selects a suitable computer which is turned on and ready to process the job. If such a computer is not available, the job will wait until such computer is available. When there are more suitable computers, the system chooses the most powerful one. Then it will start processing the task (âRunningâ is indicated in NIS.ai Explorer). When the task is finished, âCompleteâ is shown. If your computer is not involved in the cluster, it can be turned off during the cluster processing. These 
symbols are shown in NIS.ai Explorer before the training name indicating the clustered training.
Note
Make sure that the image being processed is located on a shared storage and not your local hard drive.
Executes the AI training.
Closes the window without executing the AI training.
Opens this help page.
(requires: NIS.ai)
Opens the Train Convert.ai dialog window. For more information please see NIS.ai.
Training data
Opens a dialog where you can choose a dataset train image file or change the path to a different file.
Removes the path to the dataset train image.
Opens a dialog where you can add another dataset train image file.
Channels
Source channels used for AI training.
Ground truth channels for AI training. AI will be trained to convert the source channels into the ground truth channels.
Options
You can use an existing AI as a base for the current training. Select this option and browse for the *.cai AI file. See Continue Training.
Number of AI training iterations.
Output
Input the name for your AI used in the Explorer.ai.
Specify the output file where the AI will be stored.
Saves a screenshot of the training graph, so that it can be examined after the training is finished and the progress window is closed. This is useful when training multiple networks by a macro.
Adds the current training into a queue so that it can be executed later ( Train Queued) via NIS.ai Explorer on the current workstation. These 
symbols are shown before the training name indicating the queued training.
Sends the current training to the computer cluster system running HTCondor. System automatically selects a suitable computer which is turned on and ready to process the job. If such a computer is not available, the job will wait until such computer is available. When there are more suitable computers, the system chooses the most powerful one. Then it will start processing the task (âRunningâ is indicated in NIS.ai Explorer). When the task is finished, âCompleteâ is shown. If your computer is not involved in the cluster, it can be turned off during the cluster processing. These 
symbols are shown in NIS.ai Explorer before the training name indicating the clustered training.
Note
Make sure that the image being processed is located on a shared storage and not your local hard drive.
Executes the AI training.
Closes the window without executing the AI training.
Opens this help page.
(requires: NIS.ai)
Opens the Train Segment.ai dialog window. For more information please see NIS.ai.
Training data
Opens a dialog where you can choose a dataset train image file or change the path to a different file.
Removes the path to the dataset train image.
Opens a dialog where you can add another dataset train image file.
Channels
Source channels used for AI training.
Binary layers used as a ground truth for AI training. AI will be trained to segment the source channels as in the ground truth binary layers.
Options
You can use an existing AI as a base for the current training. Select this option and browse for the *.sai AI file. See Continue Training.
Specifies a binary layer, resulting in the exclusion of pixels marked as âtrueâ in the layer from the training process. This is typically used in cases where the user does not want to train the network on a certain part of the data - either because the user does not know how to do it himself, or does not want to annotate the whole image.
Number of AI training iterations.
Output
Input the name for your AI used in the Explorer.ai.
Specify the output file where the AI will be stored.
Saves a screenshot of the training graph, so that it can be examined after the training is finished and the progress window is closed. This is useful when training multiple networks by a macro.
Adds the current training into a queue so that it can be executed later ( Train Queued) via NIS.ai Explorer on the current workstation. These 
symbols are shown before the training name indicating the queued training.
Sends the current training to the computer cluster system running HTCondor. System automatically selects a suitable computer which is turned on and ready to process the job. If such a computer is not available, the job will wait until such computer is available. When there are more suitable computers, the system chooses the most powerful one. Then it will start processing the task (âRunningâ is indicated in NIS.ai Explorer). When the task is finished, âCompleteâ is shown. If your computer is not involved in the cluster, it can be turned off during the cluster processing. These 
symbols are shown in NIS.ai Explorer before the training name indicating the clustered training.
Note
Make sure that the image being processed is located on a shared storage and not your local hard drive.
Executes the AI training.
Closes the window without executing the AI training.
Opens this help page.
(requires: NIS.ai)
Opens the Train Segment Objects.ai dialog window. For more information please see NIS.ai.
Training data
Opens a dialog where you can choose a dataset train image file or change the path to a different file.
Removes the path to the dataset train image.
Opens a dialog where you can add another dataset train image file.
Channels
Source channels used for AI training.
Binary layers used as a ground truth for AI training. AI will be trained to segment the source channels as in the ground truth binary layers.
Options
You can use an existing AI as a base for the current training. Select this option and browse for the *.oai AI file. See Continue Training.
Specifies a binary layer, resulting in the exclusion of pixels marked as âtrueâ in the layer from the training process. This is typically used in cases where the user does not want to train the network on a certain part of the data - either because the user does not know how to do it himself, or does not want to annotate the whole image.
Number of AI training iterations.
Output
Input the name for your AI used in the Explorer.ai.
Specify the output file where the AI will be stored.
Saves a screenshot of the training graph, so that it can be examined after the training is finished and the progress window is closed. This is useful when training multiple networks by a macro.
Adds the current training into a queue so that it can be executed later ( Train Queued) via NIS.ai Explorer on the current workstation. These symbols are shown before the training name indicating the queued training.
Sends the current training to the computer cluster system running HTCondor. System automatically selects a suitable computer which is turned on and ready to process the job. If such a computer is not available, the job will wait until such computer is available. When there are more suitable computers, the system chooses the most powerful one. Then it will start processing the task (âRunningâ is indicated in NIS.ai Explorer). When the task is finished, âCompleteâ is shown. If your computer is not involved in the cluster, it can be turned off during the cluster processing. These symbols are shown in NIS.ai Explorer before the training name indicating the clustered training.
Note
Make sure that the image being processed is located on a shared storage and not your local hard drive.
Executes the AI training.
Closes the window without executing the AI training.
Opens this help page.
(requires: NIS.ai)
Opens the Explorer.ai dialog window. For more information please see NIS.ai Explorer.