Semantic Mosaicing of Histo-Pathology Image Fragments using Visual Foundation Models
This addresses a domain-specific problem for histopathology analysis by improving automated stitching, though it appears incremental as it builds on existing foundation models for a known bottleneck.
The paper tackles the problem of automated stitching of histopathology image fragments to reconstruct whole mount slides, which is challenging due to tissue loss and distortions, and introduces SemanticStitcher using visual foundation models to achieve robust mosaicing, outperforming state-of-the-art methods in correct boundary matches on three datasets.
In histopathology, tissue samples are often larger than a standard microscope slide, making stitching of multiple fragments necessary to process entire structures such as tumors. Automated stitching is a prerequisite for scaling analysis, but is challenging due to possible tissue loss during preparation, inhomogeneous morphological distortion, staining inconsistencies, missing regions due to misalignment on the slide, or frayed tissue edges. This limits state-of-the-art stitching methods using boundary shape matching algorithms to reconstruct artificial whole mount slides (WMS). Here, we introduce SemanticStitcher using latent feature representations derived from a visual histopathology foundation model to identify neighboring areas in different fragments. Robust pose estimation based on a large number of semantic matching candidates derives a mosaic of multiple fragments to form the WMS. Experiments on three different histopathology datasets demonstrate that SemanticStitcher yields robust WMS mosaicing and consistently outperforms the state of the art in correct boundary matches.