Metaphase Detection
Building Imaging Workflows in High-Throughput Laboratories
You may benefit most from the following customizations:
- Automated pre-classification of metaphases and image capture with no manual intervention.
- Deep Neural Networks (DNNs) assist in metaphase detection and may help tackle challenging preparations.
- Successfully implemented with various preparation techniques, including G-banding, R-banding, Q-banding, and DAPI banding.
- Real-time image gallery for convenient display of detected metaphases.
- Easy one-click relocation of detected metaphases.
- Scalable to process up to 800 slides in a single session, fully unattended.
- Efficient management of cases and images with Neon, installed with Ikaros and Metafer.
At the convergence of precision and automation, MetaSystems' Metafer Platform Software manages microscope and accessory hardware to acquire digital images automatically. Through the help of our specialists, included in the Metaphase Detection Customization Package, users can tailor their Metafer-based workflows to automatically detect metaphases and capture their images by integrating advanced software tools with high-performance microscopy hardware.
Recognized objects, e.g. metaphases, are automatically displayed in a real-time gallery during the search process. They can be easily relocated by clicking on the corresponding gallery image for detailed examination. To capture high-resolution images, metaphases can be selected either interactively or automatically, based on the user’s workflow settings. In the interactive method, the user simply selects metaphases of choice using the mouse. Alternatively, search parameters can be configured to assign user-defined quality values to the metaphases, allowing for the automatic selection of the top-rated objects. Additionally, a few randomly selected objects can also be captured. Once acquired, the images are immediately accessible to any connected workstation.
DNN-based Metaphase Detection
With support from MetaSystems application specialists, users can tailor their installations to include Deep Neural Networks (DNNs), an advanced form of artificial intelligence, to address challenging scenarios such as poorly prepared cells or suboptimal cell cultures. DNN functionality is provided alongside the basic software and is customized to align with individual workflows, meeting specific customer requirements. These customized DNNs are stored locally within the institution's IT infrastructure. When integrating AI into a customized workflow, users are responsible for validating the DNN as part of their workflow validation process. For example, using DNNs for metaphase detection can improve detection rates, thereby reducing the number of objects requiring capture as high-resolution images. This method has the potential to significantly accelerate result review within a user-defined workflow, ultimately shortening overall case processing time.
Once the Metafer Platform Software is installed in your lab, you can configure workflows to detect metaphases on slides automatically. Metafer offers two object detection methods. The first is based on classic machine learning algorithms, which quickly identify metaphases and display them as gallery images after the search. This method is fast and commonly used by many customers. More recently, the platform has also incorporated Deep Neural Networks (DNN), which can be trained to identify metaphases from images classified by the users. Although this method is a bit slower than the traditional algorithms, our customers report that it provides more accurate and specific results. The choice between these two methods depends on various factors, and during the customization process, our application specialists will assist you in developing the most appropriate workflow for your laboratory.
Yes, Metafer saves the positions of the detected objects and associates them with the respective gallery image. The coordinates are transferred to the high-resolution images, allowing them to be viewed in Ikaros. Additionally, if needed, other coordinate systems, such as the verniers from different manual microscopes, can be stored in Metafer. Metafer can convert all coordinates into the new system upon request, enabling objects to be located manually on external microscopes.
Users can customize their workflow using the Metafer Platform Software toolbox, allowing them to decide which steps to automate and which to leave manual. For instance, the search and image acquisition processes can be linked, eliminating the need for manual intervention between them. Installing an automatic immersion oil dispenser (AutoOiler) ensures the preparations receive the correct amount of immersion oil when switching to a high-resolution objective.
Additionally, a barcode reader can automate the management of preparations, either fully or partially, including the creation of automatically generated search protocols that track and document the entire process.
As case volumes grow, Metafer can be upgraded with the automatic SlideFeeder x80, which feeds slides into the microscope. The search capacity can be expanded from 8 slides (without the SlideFeeder x80) to 80, 160, 240, or up to 800 slides. Depending on the automation settings, these slides can be scanned automatically with no need for manual intervention.
Yes, that is possible. Metafer, together with Neon, offers extensive options for exchanging case data, scan tasks, and other information with external databases. This data exchange can be highly automated to minimize unnecessary interactions and reduce the risk of human error. For example, if your LIMS supports it, barcode labels can be generated upon case creation; Metafer and Neon can then read and interpret these barcodes. Combined with a file generated by the LIMS that defines the search parameters, the barcode can automatically trigger the metaphase search and image capture process. When case data is imported simultaneously, evaluators at their workstations receive all relevant information alongside the images to facilitate case assessment.
Chromosome analysis with the help of karyograms is central to cytogenetics, and Ikaros enhances this process, allowing the users to set up a versatile digital workflow. The software supports various banding techniques, specimen types, and advanced image processing tools, all within an intuitive, customizable interface.
The latest versions of Ikaros offer the option of implementing Deep Neural Networks (DNN) in user workflows, which help reduce segmentation errors, minimize manual corrections, and save time in metaphase processing. The DNN technology optimizes chromosome segmentation and classification and provides an initial karyogram draft as a basis for expert review. Delivering these innovative features while maintaining backward compatibility, Ikaros ensures that long-time users can seamlessly transition to the latest version and decide how much of this functionality they want to implement in their workflows. Read more about Ikaros here.
- Metafer (5.0MB)
Metafer, MetaSystems' scanning and imaging software, controls microscope and accessory hardware to acquire digital images, and to assist the operator in the detection, classification, and counting of cells of human or other origin and other objects in microscopic specimen.
- Case and Image Data Management (1.3MB)
Neon is a technology for the flexible and consistent management of image and case data. It is designed to collect data from a variety of sources and integrate them into an efficient and well-structured workflow. The technology integrated in all MetaSystems installations ensures that all relevant information is available wherever it is needed.
- Leaflet: Metafer Customization Package Metaphase Detection DNN (357.1kB)
The DNN-based metaphase detection can be added to any Metafer-based metaphase finder as a Customization Package. The approach typically yields metaphases of superior quality compared to those identified by traditional algorithms. The method has the potential to not only boost the overall count of detected metaphases but to also decrease the need for recording metaphases at high resolutions.
MetaSystems software provides, among other functions, features to assist users with image processing. These include, but are not limited to, the use of machine and deep learning algorithms for pattern recognition. The output generated in this process should be regarded as preliminary suggestions and, in any case, mandatorily requires review and assessment by trained experts.
MetaSystems offers Customization Packages for application workflows that have been successfully implemented for customer labs using standard Metafer platform functionality. It is expected that they can be implemented for other customer labs using similar workflows and slide preparation procedures. If a Customization Package is purchased, MetaSystems product specialists will – based on their experience from other similar application cases - support the customer lab in adapting the Metafer software configuration to their needs. The performance of the solution will depend on the quality of the customer slides and the expertise of the users, MetaSystems cannot specify or guarantee any performance parameters. The validation of the solution for clinical use is the sole responsibility of the customer lab.