Mycobacteria Imaging
Building a Convenient Digital Workflow for On-screen Review and Reporting

You may benefit most from the following customizations:
- Automated image acquisition of Auramine-stained slides without user interaction.
- Deep Neural Networks (DNNs) assist in the pre-classification of Auramine-stained objects (e.g., mycobacteria).
- Real-time image gallery for convenient on-screen assessment.
- Optional grading suggestions for expert review.
- Easy one-click re-location of found objects for closer examination, e.g. after Ziehl-Neelsen re-staining.
- Efficient management of cases and images with Neon.

Microscopy is often used as a rapid and cost-effective method to triage patients who might have TB before conducting confirmatory tests. In patients undergoing treatment, it plays an important role in assessing therapy success by quantifying bacterial presence over time.
With the support of our application specialists, users can set up a workflow that enables the automated acquisition of Auramine-stained slides. A specific number of camera fields can be defined, e.g. 300 Fields of View (FOVs) as recommended by the WHO.
Users can implement a customized Deep Neural Network (DNN) to pre-qualify the found objects. They can
also choose to set up a suggested grading of the detected Auramin-stained objects. The trained experts can easily confirm, modify, or reject these computer-generated proposals. For those accustomed to performing additional Ziehl-Neelsen staining, the software stores the XY coordinates of each identified object so that users can effortlessly re-locate them with a single mouse click.
Reports can be generated with the Neon case and image management installed with the Metafer Platform Software, or the results can be seamlessly transferred to the LIS.
The workflow described here has been customized for Auramine-stained slides. We recommend using a red fluorescent counterstain, e.g. Thiazin Red. The counterstain enhances autofocusing accuracy and speed, particularly for negative samples and those with few detectable objects. A specific fluorescence filterset allows both colors to be visible simultaneously eliminating the need to switch filters.
Ziehl-Neelsen staining can be used as an additional step, allowing re-stained objects to be quickly re-located under the microscope and documented with a single mouse click.
No, it does not. Confirmation of M. tuberculosis must be performed using culture or PCR. The Deep Neural Network (DNN) deployed by our customers has been trained to detect Auramine-stained mycobacteria. The final interpretation of the acquired microscopy images must always be performed by a qualified specialist.
Yes, the software can output detected Auramine-stained objects per area. Individual grading criteria can be discussed in advance with the responsible application specialist. Depending on specific requirements, custom grading adjustments can be offered as an additional service.
Every lab operates differently, and the time needed to process a slide depends on the sample area on the slide and the customized scanning process. This means that we cannot make general statements in this regard. With the support of our application specialists, you can optimize the settings for image acquisition and modify them to suit your individual needs.
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.