Automated Virtual Pathology Panels for ML-Assisted Interpretation of Mass Spectrometry Imaging
- 1Pahnke Lab
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.
Related
- Automated Full-Spectrum Multivariate Calibration for Quantitative Glow Discharge Optical Emission Spectrometry
- Mass Spectrometry-Based Omics: An Integrated Framework for Analytical Quality, Data Integrity, and Biological Interpretation
- Software Tool for Automated Kinetic Tracking in Mass Spectrometry Data
- PolycIMS: Polymers for Automated Cyclic Ion Mobility Spectrometry Calibration
- A retrieval-augmented agent bridges virtual screening and automated synthesis
BibTeX
@misc{gildenblat2026automated,
title = {{Automated Virtual Pathology Panels for ML-Assisted Interpretation of Mass Spectrometry Imaging}},
author = {J. Gildenblat and J. Pahnke},
howpublished = {bioRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.26.740867},
url = {https://www.biorxiv.org/content/10.64898/2026.07.26.740867v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Automated Virtual Pathology Panels for ML-Assisted Interpretation of Mass Spectrometry Imaging
AU - J. Gildenblat
AU - J. Pahnke
PY - 2026
DA - 2026/07/26
PB - bioRxiv
DO - 10.64898/2026.07.26.740867
UR - https://www.biorxiv.org/content/10.64898/2026.07.26.740867v2
AB - 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.
ER -