top of page
MicrosoftTeams-image (34).png
Aivia 13
Elevate your research with spatial insights powered by AI
2D Rendering Engine Overhaul

Visualize large, multiplexed 2D images with millions of detected objects

AI-Driven Cell Analysis

Accurate and faster cell segmentation using AI

Cell Phenotyping

Expert- and data-driven approach for cell clustering and phenotyping

Complex Spatial Data Exploration

Insight generation from interactive exploration of complex spatial data

2D Rendering Engine Overhaul
Sequence 004 - TileScans 001 - Mosaic001_Merged_raw.png

2D Rendering Engine Overhaul

Get more insights from large 2D images

In Aivia 13, we have overhauled our visualization engine enabling you to view large, multiplexed 2D images (85k x 57k in size with up to 100 channels) with millions of detected objects. New coloring schemes let you customize image display for up to 100 channels for stunning image visualization. The new Mini-Map helps you navigate to your region of interest from anywhere on your image. Automatic tissue detection enables users to automatically delineate regions of interest (ROI) based on any channels for efficient downstream analyses of large tissue sections and Tissue Micro Array (TMA) cores.

Our free viewer, Aivia Community, offers these visualization tools to share your raw or analyzed large 2D images with your collaborators on any workstation, anywhere in the world.

  • View large, multiplexed 2D images up to 85k x 57k in size and 100 channels with millions of detected objects
  • Mini-Map for navigating across large image
  • Automatic ROI detection
  • Free viewer for large, multiplexed 2D data with Aivia Community

Media Gallery
CellDIVE_SLIDE-1339_R0_detection results_cellSegment-2.png

AI-Driven Cell Analysis

AI-Driven Cell Analysis

Segment cells of all shapes and sizes with AI

To help you gain accurate understanding of your data, Aivia 13 includes two (2) new recipes for cell detection: Cell Analysis - Cellpose and Multiplexed Cell Detection. Both recipes incorporate an optimized version of the Cellpose generalist deep learning cell segmentation algorithm [1], which has been demonstrated to accurately segment cells with diverse morphological characteristics. Cellpose in Aivia 13 optimizes cell segmentation in larger, multiplexed 2D images - building upon the improvements for Cellpose in Aivia 11 (for 3D object segmentation) and Aivia 12 (for 3D soma detection in dense neuronal environment. You can utilize this powerful tool without the need to set up Python / CUDA environments, train your own deep learning model, or code your own solutions.

We have also improved our powerful machine learning-based Pixel Classifier and existing recipes (Cell Count, Nuclei Count, and Cell Count - Cellpose) to work with larger 2D images.

Achieve accurate cell detection in larger, multiplexed 2D images using the power of AI in Aivia 13.

  • Two (2) new AI-powered cell segmentation recipe for large, multiplexed 2D images - Cell Analysis - Cellpose and Multiplexed Cell Detection
  • Improved Pixel Classifier and recipes for larger 2D images

1.  Stringer C, Wang T, Michaelos M, and Pachitariu M. Cellpose: a generalist algorithm for cellular segmentation. Nature Methods. 18: 100-106. (2021)

Media Gallery
Cell Phenotyping
Pancreas Adenocarcinoma_output_r40148_clusters_v3.png

Cell Phenotyping

Expert- and data-driven phenotyping

Understanding the types of cells within your image is critical to gaining deep insights. Our AI-driven Phenotyper leverages your expert knowledge about the phenotypes present in your data to build a classifier. Simply select a few representative cells to train Aivia and Aivia will classify cells into different phenotypes automatically.

For data-driven phenotyping, Aivia now offers two (2) automatic clustering options: k-means clustering [2] and PhenoGraph-Leiden [3] unsupervised automatic clustering methods, which need only a few user-guided inputs to generate phenotypes incorporating intensity and morphological measurements for up to 30 biomarkers. 

  • Phenotyper leverages your expert knowledge about cell types in your data for AI-powered classification
  • Data-driven automatic clustering using k-means or PhenoGraph-Leiden methods

2.  MacQueen, J. Some methods for classification and analysis of multivariate observations. Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability. Vol. 1: Statistics. 281-297. (1967).

3.  Traag VA, Waltman L, and van Eck NJ. From Louvain to Leiden: guaranteeing well-connected communities. Scientific Reports. 9: 5233. (2019).

Media Gallery
Complex Spatial Data Exploration

Complex Spatial Data Exploration

Try Aivia

New ways to visualize complex data and spatial relationships

When working with millions of objects in large, multiplexed 2D images, it is crucially important to be able to quantitatively analyze different objects and phenotypes and compare them. Aivia 13 delivers new charts optimized for data exploration of millions of objects:

  • Summary Histogram for comparison between object groups or phenotypes

  • Violin Plot for comparing data distribution for millions of objects in different object groups or phenotypes

  • Marker-Cluster Dendrogram for viewing the relationship between intensity or morphological measurements and phenotypes

  • Pearson Correlation Heatmap for showing the correlation between two measurements for a given object set or phenotype

  • Binned Scatterplot for comparing data distribution of two different measurements for multiple object sets or phenotypes

  • Dimensionality Reduction Plot for transforming high-dimensional data into two-dimensional space to simplify data interpretation with three (3) dimensionality reduction methods: UMAP, t-SNE, and PacMAP

  • Scatterplot with multi-well support for plotting data per well, per experimental condition, or for all conditions on an entire wellplate

Additionally, you can achieve accurate vertex-to-vertex distance measurements between individual objects (of any type, or morphological complexity) or between phenotypes using our revamped Relation Tool. You can elucidate the spatial relationship between cells or phenotypes by interactively selecting objects or phenotypes on the image in charts and visualizing the selection using Spotlight.

  • Four (4) new charts to explore the data: Summary Histogram, Binned Scatterplot, Marker-Cluster Dendrogram, and Dimensionality Reduction
  • Three (3) revamped charts optimized for millions of objects: Violin Plot, Pearson Correlation Heatmap, and Multi-well Scatterplot
  • 2D and 3D spatial relational analysis for millions of objects
  • Interactive visualization of cells and phenotypes for charts and images

Media Gallery