Abstract: |
In the clinic, resected tissue samples are stained with Hematoxylin-and-Eosin (H&E) and/or Immunhistochem-istry (IHC) stains and presented to the pathologists on glass slides or as digital scans for diagnosis and assess-ment of disease progression. Cell-level quantification, e.g. in IHC protein expression scoring, can be extremely in-efficient and subjective. We present DeepLIIF (https://deepliif.org), a first free online platform for ef-ficient and reproducible IHC scoring. DeepLIIF outper-forms current state-of-the-art approaches (relying on man-ual error-prone annotations) by virtually restaining clinical IHC slides with more informative multiplex immunofluores-cence staining. Our DeepLIIF cloud-native platform sup-ports (1) more than 150 proprietary/non-proprietary input formats via the Bio-Formats standard, (2) interactive ad-justment, visualization, and downloading of the IHC quan-tification results and the accompanying restained images, (3) consumption of an exposed workflow API programmat-ically or through interactive plugins for open source whole slide image viewers such as QuPath/ImageJ, and (4) auto scaling to efficiently scale GPU resources based on user demand. © 2022 IEEE. |