Nikon Instruments Inc. | Américas
Artboard 1
pt Change Region

Global Site


Estamos acompanhando de perto a situação da COVID-19 (coronavirus), seguindo as orientações dos Centers for Disease Control and Prevention (Centros de Controle e Prevenção de Doenças) e das autoridades em saúde federais, estaduais e locais. Saiba mais sobre as medidas que estamos tomando.


Taking microscope imaging and analysis to the next level

Artificial Intelligence (AI) and deep learning methods are making seemingly impossible tasks now possible. Results only managed by challenging acquisition parameters or by painfully long or manual segmentation methods can now be automated thanks to AI.

The module expands the NIS-Elements platform by building in tailor-made solutions for acquisition, visualization and analysis.

Conventional Thresholding

AI Segmentation

Intensity measurements were desired to be made along the nuclear envelope of cells. Conventional segmentation could not differentiate the cellular structures and misses several cells. AI-trained segmentation recognizes and identifies the nuclear envelope successfully.

Características principais

No programming skills required employs convolutional neural networks (CNNs) to learn from labeled training data created by either conventional segmentation or human-assisted tracing of small subset of representative samples. When using the module, the software interface makes it easy to apply complex deep learning to sample data, eliminating the need to design a complex neural network and apply training data to it.

Automated tools take this training data and apply the neural network to recognize patterns. The result training recipe can then be applied repeatedly and reliably to similar samples to process or analyze huge volumes of data at significantly faster speed than traditional techniques.

Segmentation Task

By recognizing patterns present in two different imaging channels, can be trained to predict what the second channel would look like when only the first channel is acquired.

Commonly, this can be used as a segmentation tool for label-free approaches, or imaging without harmful near-UV excitation. Once the neural network learns the pattern common to two channels, then in subsequent experiments the second channel is no longer needed to be acquired. Throughput of acquisition as well as specimen viability both increase as a result.

DAPI staining of nuclei is a common method allowing cell counting and segmentation. can be trained to predict where the DAPI label is present in DIC or phase images. This predicted channel can then be used for segmentation and counting, without ever having to label the specimen with DAPI or acquire a fluorescence channel.

Photos courtesy of Dr. Kentaro Kobayashi, Division of Technical, Research Institute for Electronic Science, Hokkaido University

Some fluorescent samples express a very low signal and it is difficult to visualize or extract details for segmentation.

In addition, many of these samples are sensitive to light or photobleach very quickly and need to be imaged as fast as possible. can restore details by training the network what properly-exposed images look like. Then this recipe can be applied to underexposed images to restore detail that can be used for further analysis.

DAPI stained nuclei are purposefully underexposed to limit the specimen’s exposure to near-UV light. is used to restore the signal-to-noise ratio to normally exposed DAPI staining, for easy segmentation and counting.

HT1080 cell expressing CD63-mCherry was observed by fast time-lapse, 3D fluorescent imaging (95 slices/sec for 5 minutes). We could detect CD63-mCherry signal on plasma membrane, and in endosomes and vacuoles (multivesicular body), as dancing vesicles. NIS reduced shot noise and uneven illumination due to Spinning Disk Confocal rotation.

Dr. Yoshitaka Shirasaki (Grad. Sch. Sci., The Univ. of Tokyo) and Dr. Kiyotaka Shiba (Cancer Institute JFCR)

Some images are nearly impossible to segment by traditional intensity thresholding methods. A neural network can be trained by human classification of structures of interest that cannot easily be defined by classic thresholding and image processing by using

By tracing features of interest and training these compared to the underlying image, the neural network can learn and apply segmentation to similar images, recognizing features previously only identifiable by painstaking manual tracing approaches.

Neurites in phase-contrast were not possible to define accurately by traditional thresholding. was trained on hand-traced neurites (human recognized) and learned how to trace neurites in subsequent images.

All images contain shot noise, which is a Poisson-distributed noise related to discreetly sampling (acquiring images) of a continuous event. As signal levels decrease, the contribution of shot noise increases and noisy images result, following a square-root function. Such noise therefore is modeled in a neural network and doesn’t need to be further trained.

With new fluorescent techniques pushing intensities lower and acquisition speeds increasing, can recognize and remove the shot noise component of images, increasing clarity and allowing for shorter exposure times or more exposures of specimens while maintaining viability.
Original can be applied to remove the shot noise component of images while leaving the underlying structure and intensity values undisturbed.

GA3: an analysis pipeline with AI capabilities

Using NIS-Elements General Analysis (GA3), multiple conventional segmentation and AI tools can be combined to create data measurement routines customized for a specific experiment. These can be applied across multiple images, experiment runs, or high content data.

Because GA3 is freely customizable, it can be adapted to new experiment routines easily. Routines can be embedded as well during experiment acquisition runs.

General Analysis is used to apply to brightfield images to mark nuclei, and applied to a noisy fluorescence channels. The converted channels can then be tracked over time lapse to measure cell movements. This routine is then applied to multiple data sets for data measurement.

Use as part of an imaging pipeline tools can be combined with all other features of the NIS-Elements platform to develop imaging protocols and targeted analysis from basic counting through rare event or selective phenotype detection and analysis.

This can be incorporated post-acquisition, or more impactfully, as an integral part of an experimental protocol so that NIS-Elements Intelligent Acquisition analysis results obtained during the experiment run guide the experimental parameters in different directions.

Using the JOBS experiment wizard, customized experiments with embedded analysis tasks and branches based on analysis results can be created, allowing for higher throughput and more targeted acquisitions.

Example of utilizing in an experiment run to analyze XY positions as they are captured, and to search for specific phenotypes. When a target cell is found, a stimulation experiment is performed. If no target cell is found, the experiment proceeds to the next XY position.

Quantifiable Results

Artificial intelligence has become commonly accepted in diagnostic imaging and is an increasingly popular tool for a number of applications. Its appeal over traditional mathematical approaches is both its speed and incredible accuracy. However, it is important to be able to validate the results of AI computations, and to utilize these results appropriately for computational analysis.

NIS-Elements software provides feedback during training routines to indicate the confidence of the trained neural network to provide accurate results.