The IN Carta® Image Analysis Software addresses complex image analysis challenges through its sophisticated artificial intelligence (AI) capabilities, transforming visual data into easy-to-understand outcomes. Intuitive processes enable quicker insights from the 2D, 3D, and 4D experimental setups.
Incorporating the Custom Module Editor application lets the user establish highly tailored image analysis procedures, ensuring dependable findings–even for challenging assays–followed by rapid visualization, examination, and engagement with the analytical outcomes. IN Carta software handles demanding tasks, freeing the user to concentrate on their scientific investigations.
Powerful
Structured processes and adaptable batch processing enhance output and reduce response time. Experimental setups are swift, and the examination of numerous wells proceeds concurrently.
Insightful
Machine learning helps leverage more data and improve precision in high-content screening data analysis, fostering confident new breakthroughs.
Intuitive
A contemporary user interface and advanced technology minimize the software's learning period and eliminate obstacles to efficiency.
IN Carta Image Analysis Software. Image Credit: Molecular Devices UK Ltd
Features
Deep learning
Enhance the precision of image analysis processes through the SINAP module. SINAP employs deep learning for image analysis, delivering dependable segmentation across nearly all biological structures.
Start with a worklist
Navigate to a main directory and fill the worklist with relevant image datasets, or just use the search function to locate them.
AI-powered data analytics
Harness machine learning's capabilities without needing to be a data scientist. For example, users can pinpoint and measure phenotypic alterations within an intuitive workflow; investigate data and uncover insights from intricate datasets; and discover new and unforeseen phenotypes with minimal mouse interaction.
Customization
View and examine images from experiments, develop image analysis protocols of varying complexity, and include on-demand data categorization. Display analysis outcomes using 360° data linking images, data tables, and charts.
3D analysis
The Custom Module Editor's 3D application offers unparalleled adaptability for segmenting intricate biological structures. Image datasets are acquirable in 3D or 4D (timelapse 3D), and customized image analysis routines can be crafted within a guided process.
Batch analysis and monitoring
Process multiple experiments using batch analysis mode with one or several analysis protocols. Track the status of all submitted tasks and supervise their advancement in real time.
Flexi-Protocol
The Flexi-Protocol application facilitates the development of tailored analysis protocols of any complexity by incorporating all necessary analysis stages. Each analysis stage can include image pre-processing and object mask post-processing operations to better suit a specific assay. Updated analysis and image viewer panes are expandable or collapsible, depending on the required area of focus.
Image Credit: Molecular Devices UK Ltd
- Simple or complex: Develop any analysis protocol needed for a specific assay. Segment and derive measurements from an unlimited number of channels.
- Customizable: Establish target hierarchy within the protocol through target linking. Utilize the Custom Measure feature to compute extra measurements for any biological target.
- Powerful: Leverage deep learning segmentation capabilities at each stage of analysis. Target masks can be combined using logical operations.
- User-friendly: The intuitive interface with dynamic panes facilitates concentrated protocol creation.
- Help is just a click away: Readily access contextual assistance via an interactive, searchable user guide.
IN Carta SINAP
SINAP, a deep learning module, enhances the accuracy and reliability of high-content screening assays during the initial segmentation step, offering superior object identification over conventional image analysis techniques.
Deep learning models are readily customizable via an intuitive interface, allowing efficient segmentation of novel biological objects. Accurate quantitative data from segmented objects prevents error propagation throughout the analysis workflow.
With SINAP, segmentation is not a problem!
Precise: Deep learning maintains accuracy across challenging samples, including confluent cells, low-signal-to-noise specimens, and transmitted-light imagery.
Dependable: SINAP models effectively manage significant phenotypic variation.
Adaptable: A singular workflow accommodates diverse applications and imaging techniques.
Accessible: A trained model learns segmentation from a scientist’s image annotations, removing the need for a deep learning expert to build and optimize new models.
Customized SINAP deep learning models segment specific regions (whole body, head, eyes, brain) of a zebrafish embryo in a transmitted-light image. Image Credit: Guo Lab, UCSF
IN Carta Phenoglyphs
The IN Carta® Phenoglyphs™ Software Module employs a distinct blend of unsupervised and supervised machine learning to quantify phenotypic alterations. By analyzing hundreds of cellular characteristics concurrently, a comprehensive phenotypic profile is generated that can then be used throughout the screening process.
This multi-variable classification method offers precise identification of object groups, enabling users to discern minute phenotypic shifts resulting from drug therapy or genetic alterations. It is well-suited to many biological targets, such as organoids, individual cells, spheroids, and more.
Extensive: A data-centric methodology that initiates with unsupervised clustering to identify data patterns and emphasize subpopulations, even without foreknowledge of potential phenotypes.
Resilient: A specialized machine learning algorithm determines the best collection of descriptive attributes to prevent the subsequent classification model from overfitting.
Streamlined process: Classification is accomplished through straightforward confirmation or adjustment of the algorithm’s forecasts until it acquires the desired performance.
Classification of spheroids formed from HCT116 cells. Spheroids were segmented based on brightfield images using SINAP. The sample was additionally counter-stained with Hoechst 33342, Calcein AM, and MitoTracker Red to visualize nuclei, live cells, and mitochondria, respectively. Image Credit: Molecular Devices UK Ltd
IN Carta Custom Module Editor 2D and 3D
- Design simple, step-by-step custom analysis
- Customize object segmentation and classification
- Identify objects located inside defined biological compartments
- Report only the specific measurements needed for an assay
- Evaluate live-cell imaging data
- True 3D segmentation (3D application only)
- Reconstruct 2D segmentations into volumes for 3D assays (3D application only)
Example segmentation of HCT116 cells forming a spheroid, segmented in the Custom Module Editor 3D and visualized in the 3D viewer. Image Credit: Molecular Devices UK Ltd
ImageXpress HCS.ai system
A fast, intuitive, and versatile system delivering deeper insights for every lab
Image Credit: Molecular Devices UK Ltd
- Suitable for a wide spectrum of imaging assays, spanning fundamental cell analysis to advanced multiplexed and 3D assays
- Fully configurable to current experimental demands, offering a straightforward upgrade route as research requirements expand
- Customizable with seven-channel high-intensity lasers, spinning-disk confocal technology for enhanced tissue penetration, environmental controls, water-immersion objectives, and related accessories
- Powered by the new MetaXpress Acquire software, delivering a user-friendly experience across all operator skill levels
Applications of the IN Carta Image Analysis Software
T-cells and 3D cell models for immunotherapy
Image Credit: Molecular Devices UK Ltd
Explore cancer therapy through T-cell capabilities combined with organoids and spheroids. Immunotherapy, a treatment approach that utilizes the body's immune system to precisely attack malignant cells, is increasingly recognized as a supplementary cancer therapy. Such treatments include chimeric antigen receptor (CAR) T-cells, tumor-infiltrating lymphocytes (TILs), and various other genetically altered T-cell types.
Improving the recruitment and cytotoxic capabilities of T-cells is vital for effective cancer immunotherapy outcomes. Within preclinical scientific studies, three-dimensional cell models provide benefits compared to two-dimensional monolayer cultures, as they more accurately simulate the immunosuppressive tumor microenvironment (TME).
For instance, patient-derived organoids (PDOs) outperform conventional 2D monolayer cultures due to their enhanced ability to reproduce the TME's physical and chemical signals.