{
  "abstract": "Mass spectrometry imaging (MSI) records rich molecular spectra at each pixel, but pathology-oriented interpretation benefits from complementary views of the same tissue, loosely analogous to the multiple stains used in histopathology. We present an expert-aligned framework for constructing multi-view MSI panels. Soft Landmark Contrast Edges (SoLaCE) extracts molecular boundaries directly from high-dimensional spectra. Because standard structure-preservation metrics aligned poorly with rankings by pathologists, we combine luminance contrast and chromatic diversity with SpecEdgeDice, a boundary-aware measure of agreement between visualization edges and SoLaCE boundaries. Parametric MiCS+LMC (pMiCS) uses a neural network trained on subsampled data to distill multiple MSI segmentations into a reusable spectral-to-RGB mapping, enabling rapid full-image inference, out-of-sample projection, and more consistent color semantics across aligned images. A concept-based interpretation procedure explains pMiCS outputs through sparse mixtures of spectral concepts, scoped as a model output-equivalent summary rather than a molecular identification. We integrate these components into Virtual Pathology Panels, which use hyperparameter optimization to select fast, high-performing or spatially complementary views. This framework supports future workflows that combine automated, AI/ML-supported, morphology-oriented tissue assessment and molecular analysis within a single MSI acquisition.",
  "abstract_shown": true,
  "affiliations": [
    "Pahnke Lab"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "J. Gildenblat"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Pahnke"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/34r2263wsq422.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.07.26.740867",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.07.26.740867v2.full",
  "id": "34r2263wsq422",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.07.26.740867v2",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "pathology"
    ],
    [
      "openalex",
      "1607|Mass Spectrometry Techniques and Applications"
    ]
  ],
  "openalex": "W7171788391",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.07.26.740867v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/34r2263wsq422.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:52Z",
      "native_id": "10.64898/2026.07.26.740867",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.07.26.740867v2"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:1607|Mass Spectrometry Techniques and Applications",
      "subfield": "physical"
    }
  ],
  "title": "Automated Virtual Pathology Panels for ML-Assisted Interpretation of Mass Spectrometry Imaging",
  "title_text": "Automated Virtual Pathology Panels for ML-Assisted Interpretation of Mass Spectrometry Imaging",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:52Z",
  "url": "https://research.draconitic.com/paper/34r2263wsq422",
  "venue": "bioRxiv",
  "versions": []
}