Based on 20 years of in-house R&D, Aivia is an innovative and complete 2-to-5D image visualization, analysis and interpretation platform. Using state-of-the-art algorithm and software architecture, Aivia delivers top performance on critical tasks such as display of large images and analysis of complex biological phenomena. Aivia is powered by a range of machine learning technology for both image segmentation, object classification and novelty detection. With Aivia, you are the analysis expert.
Artificial intelligence
Enhance, segment and predict with state-of-the-art deep learning and machine learning tools tailored to your data
Teravoxel 3D rendering
Visualize trillions of voxels and thousands of objects in real time
Virtual reality
Interactively explore 3D/4D dataset in an immersive environment
Neuron tracing
Fast neuron reconstructions using intelligent tracing tools
3D tracking
Analyze object motion and explore cell division, differentiation and fate
Unrivaled support
Free upgrade and technical support for the duration of your subscription means one less thing to worry about
Artificial Intelligence
Software That Learns
The development team behind Aivia has over 20 years of experience applying artificial intelligence (AI) solutions for tackling challenging analysis and classification problems.
Aivia can learn to identify specific cell phenotypes (or more generally, specific classes of objects) based on dozens of complex features. In addition, Aivia can suggest new phenotypes / classes that have not yet been identified by the user - thus aiding discovery.
In November 2017, Aivia became the first commercial software to harnesses cutting edge deep learning technology for automated neuron segmentation in 3D electron microscopy images. You can augment Aivia's standard deep learning model using transfer learning to optimize detection on your datasets.
Complete deep learning workflow from ground truth generation to model training to apply and analysis is possible with Aivia 8 and Aivia Cloud. Use the intuitive tools in Aivia 8 to create ground truths; upload the training data to Aivia Cloud to train deep learning model in minutes; and review the results anywhere - all within Aivia's environment.
In Aivia 8.8, we have further enhanced the machine learning-enabled Pixel Classifier. By painting a few sections (in 2D or 3D) of an image, Aivia enhances and segments objects automatically. Users can get high quality results quickly without needing to specify image processing functions or to adjust parameters.
Browse our library of pre-trained deep learning models and apply them to your data. You can integrate deep learning into your image analysis workflow on any recipe in Aivia 9.5, opening up a whole new world of possibilities to process your images.
With Aivia 10, we took another leap in providing AI access for all with the launch of Aivia That Learns. Aivia That Learns predicts suitable image analysis parameters for 3D Object Analysis and 3D Neuron Analysis recipes for your data. This enables a reduction of 74% in analysis time by streamlining the process to optimizing the analysis parameters.
-
First commercial software package with deep learning
-
Use the latest convolutional neural network architecture (U-NET, GAN and RCAN)
-
End-to-end deep learning analysis pipeline within Aivia
-
Choose from 20 pre-trained deep models and apply the model as part of the recipe workflow
-
Content-aware image enhancement by painting
-
Parameter-free object detection
-
GPU-accelerated apply
-
Trainable object classification using random forest algorithm
-
Apply species specific pre-trained model for neuron classification
-
Identify new phenotypes in your data with Novelty Detection
-
Aivia That Learns predicts image analysis parameters
Visualization
Terabyte Ready
-
Display and interact with teravoxel 3D/4D volumes in seconds
-
Multi-resolution, multi-block architecture for volume rendering
-
Real time interaction with hundreds of thousands of objects per time point
-
Optimized data flow (disk to GPU) and object generation
-
Navigate instantaneously to any time point with intelligent caching
-
Interactive data exploration in immersive VR environment
Aivia introduces a revolutionary new way to display super-large datasets and interact with hundreds of thousands of 3D objects in real-time. We accomplished this by implementing an innovative multi-resolution, multi-block file architecture for volume rendering; and an efficient memory management system with optimized GPU usage for surface rendering. In Aivia 8.5, volume rendering is further refined - allowing you to display large teravoxel datasets in seconds and interact with individual objects in real-time without lag.
Aivia is also pioneering the latest virtual reality (VR) technology to bring you immersive image exploration. You can view and interact with your 3D and 4D datasets in the VR space to examine and compare objects.
Image Analysis
Advanced Solutions For Complex Problems
Aivia currently features 17 application-specific image analysis pipelines called "recipes" for 2 to 5D microscopy images. The recipes incorporate the latest high performance algorithms for image enhancement, segmentation and tracking (where applicable) thus enabling you to accurately detect all objects of interests on your images. Go from raw image to results in as little as one click. You can also optimize the detection parameters using the Recipe Console. You do not need prior background in image processing to get good results.
-
Complete portfolio of image analysis pipelines for 2D to 5D datasets
-
Accurate detection of hundreds of thousands of objects per time point; up to billions per dataset
-
State-of-the-art algorithms for image analysis
-
Easy to use package, no image processing background needed
-
Optimized for processing large datasets quickly
