{"id":2217,"date":"2024-07-16T15:50:38","date_gmt":"2024-07-16T13:50:38","guid":{"rendered":"https:\/\/websites.fraunhofer.de\/smart-sensing-insights\/?p=2217"},"modified":"2025-10-29T14:10:46","modified_gmt":"2025-10-29T13:10:46","slug":"ihc-cell-detection-by-roi","status":"publish","type":"post","link":"https:\/\/websites.fraunhofer.de\/smart-sensing-insights\/ihc-cell-detection-by-roi\/","title":{"rendered":"MIKAIA: Differential IHC Cell Detection by ROI"},"content":{"rendered":"\n

This article is based on a our presentation “IHC Cell Analysis — More than just Cell Counting: A proposed Workflow” at the European Conference for Digital Pathology (ECDP) 2024 in Vilnius, Lithuania.<\/p>\n\n\n\n

The IHC analysis workflow in MIKAIA\u00ae<\/sup> comprises multiple pre- and post-processing steps in addition to the cell detection itself:<\/h2>\n\n\n\n
    \n
  1. Automatic tissue (foreground) detection<\/strong><\/li>\n\n\n\n
  2. *Division of slide into Scan Areas<\/strong> to support multiple specimens per slide (e.g., TMA cores)<\/li>\n\n\n\n
  3. *Further subdivision into ROIs<\/strong> (e.g., \u201cmetastasis\u201d)<\/li>\n\n\n\n
  4. *Automatic creation of concentric ROI-distance-margins<\/strong><\/li>\n\n\n\n
  5. Cell detection<\/strong> and assignment to distinct ROIs and scan areas<\/li>\n\n\n\n
  6. Cell qualification<\/strong>: computation of morphometric and color attributes<\/li>\n\n\n\n
  7. *False positive<\/strong> filtering<\/li>\n\n\n\n
  8. *Hotspot search<\/strong><\/li>\n\n\n\n
  9. *Spatial clustering<\/strong><\/li>\n\n\n\n
  10. *Visualization<\/strong> using interactive markup and heatmaps<\/li>\n\n\n\n
  11. Export to CSV<\/strong> for downstream statistical analysis<\/li>\n\n\n\n
  12. Export of markup files, experiment settings, etc., for documentation and repeatability<\/strong> (GLP)<\/li>\n<\/ol>\n\n\n\n

    Steps marked with a * are optional. <\/p>\n\n\n\n

    Dividing slide into “scan areas”<\/h3>\n\n\n\n

    In some cases, it is important to divide the scan into “scan areas”, for instance when a scan contains multiple specimens. The following gallery shows two such instances. The third example is a TMA where it is also necessary to collect downstream statistics separately by core.<\/p>\n\n\n\n

    The Tissue Detection App<\/strong> is used to recognize all tissue objects. It offers to automatically group tissue pieces (“particles”) into scan area. Alternatively it can do TMA-dearraying. In case the result is not right, the user can automatically create scan areas, simply by creating a “scan areas” class and drawing rectangles. When annotation texts are provided, these will be interpreted as the scan area name (and show up in the CSV file with the export results).<\/p>\n\n\n