Annotation Studio facilitates information management and coordination of high-throughput multimodal MSI studies. Through its web-based nature, Annotation Studio allows expert pathologists and team members around the globe to annotate, label and explore high-resolution microscopy images accompanying the MSI data.
The resulting labels and regions of interest can then be integrated into the MSI analysis workflow, making them available for subsequent data analysis, anatomical stratification or tissue classification. Integration with other imaging modalities often requires high-resolution image registration (link) across imaging modalities.
Annotation Studio was designed to support high-throughput labeling of microscopy whole-slide images in teams with multiple members. Since it's web based, remote annotation is natively supported. We provide an overview of its key features below. If you're interested to learn more about a specific feature, click the button to get more details.
Annotation Studio features a cloud-based interactive viewer for exploration and annotation of images at full gigapixel microscopy resolution (supporting 40X zoom microscopy images). Users can mark regions of interest using circles and polygons, with labels defined at study setup. For each sample, meta-information can be provided to assist pathologists and team members in tissue assessment (here we used tissue type, lesion location and age).
The image below depicts the whole-slide viewer with annotation controls and a commenting section for collaboration.
Study managers can define parameters and workflows per project. An example workflow could be:
Annotation by expert pathologist
Review by study coordinator
Export annotations for downstream analysis
User groups can be managed and assigned tasks per project through the role-based permission system available in the Nexus platform. The project overview page provides information on a study, making it easy to search for information, and rapidly gain insight into the status of each image. Team members can easily identify actionable cases via smart filtering.
Assets such as whole-slide images can be imported into a special staging area from which they can be assigned to projects, or they can be added to relevant projects automatically when the correct metadata is present. Annotation Studio can be seamlessly integrated with your native cloud-based storage solution such as Sharepoint or Amazon S3 to fully automate the data importing process for maximal efficiency.
Communication is key to maintain momentum in large scale studies. Through Annotation Studio’s feedback function, users can communicate with each other to comment on individual images, provide information on annotations, or flag potential issues, as shown in the left panel. Conversely, users receive automated, personalized notifications based on their assigned roles, as shown on the right. This keeps all the information in one central location and facilitates full traceability of a study. Communication features as described here are embedded within all workflows as part of the Nexus platform.
Downstream data analysis
Once annotations are completed and reviewed, coordinates of the annotations can be exported and used for further analysis. A typical follow-up analysis is to use these labels to construct a tissue classification model. Very often this requires spatial registration of the imaging modality annotated in Annotation Studio to the MSI data collected in tandem.
Aspect Analytics develops custom pipelines to perform follow-up bioinformatics analyses. In a recent collaboration, Aspect developed a high-performant classification model for diagnosis of melanoma by combining expert pathologist-labeled high-resolution microscopy with imaging mass spectrometry data collected in tandem (more info via the button below) Aspect is currently working on tools to facilitate creation of such classification models, let us know here if you would like to be kept informed on future developments.