IN Carta Image Analysis Software

IN Carta SINAP

SINAP is a module that uses deep learning algorithms to improve accuracy and reliability of high-content screening assays at the first step in the analysis pipeline—segmentation. It provides better object detection than traditional image analysis methods. Quantitative information extracted at this step is more accurate so errors are notcontent-section propagated down the analysis pipeline.

With SINAP, Segmentation Is Not A Problem!

• Accurate – deep learning can maintain accuracy across difficult to segment samples including highly confluent cells and low signal-to-noise samples
• Reliable – SINAP models can account for high phenotypic variability
• Flexible – a single workflow can deal with a variety of applications and imaging modalities, including challenging fluorescent and transmitted light assays
• Accessible – trained model learns to segment from users drawing on the image rather than asking the user to develop an image processing pipeline and optimize multiple parameters

IN Carta Phenoglyphs

IN Carta® Phenoglyphs™ Software Module uses advanced machine learning to classify segmented objects. Using many hundreds of cellular features that can be analyzed simultaneously, a comprehensive phenotypic profile is created and can be applied throughout an entire screening workflow. This multivariate approach to classification provides accurate characterization of object populations allowing users to resolve subtle phenotypic changes induced by drug treatment or genetic modification. It can be utilized across many biological targets including organoids, cells, spheroids, and more.

• Robust – the novel unsupervised step in the workflow quickly builds a large unbiased training set that captures the variance in a class and produces models that are less subject to overfitting and misclassification
• Comprehensive – a data driven approach that starts with an unsupervised clustering to find patterns in the data and highlight subpopulations without prior knowledge of what phenotypes may exist
• Optimized workflow – machine learning automatically chooses the optimal set of descriptive features to form a complex set of rules to stratify classes. Classification is achieved by simply confirming or correcting the algorithm’s predictions until it learns the right behavior.

IN Carta VoluMetrics

3D biological models that more accurately mimic in vivo organs and tissues show great potential as tools to improve the understanding of disease and probe for potential therapies. IN Carta VoluMetrics is a 3D image analysis module that extends IN Carta software’s functionality with the ability to segment and quantify biological structures in 3D.

IN Carta VoluMetrics provides algorithms that operate on voxels when segmenting objects and extracting informative measures. This provides a better representation of the sample morphology and intensity distributions compared to individual Z-plane analysis where the relationship between objects in adjacent Z-planes is a rough approximation.