mViSE: A Visual Search Engine for Analyzing Multiplex IHC Brain Tissue Images
🤖 AI Summary
Multiplex immunohistochemistry (mIHC) whole-brain section images exhibit high information density, and their analysis typically requires custom programming, limiting accessibility and scalability.
Method: We propose a zero-code, query-driven visual search framework featuring a novel panel-wise self-supervised encoding architecture. This architecture integrates explicit visual verification with information-theoretic cross-panel similarity metrics, enabling interactive retrieval based on cellular phenotypes and tissue microenvironments.
Contribution/Results: Our method is the first to enable fully code-free brain regional parcellation, cortical laminar localization, and multi-cellular niche decomposition. It achieves high-accuracy retrieval at single-cell, cell-pair (neighborhood), and tissue-block scales. Implemented as an open-source QuPath plugin, it natively supports multiplex molecular marker modeling, significantly enhancing interpretability and accelerating exploratory analysis of neurohistological images.
Application Category
📝 Abstract
Whole-slide multiplex imaging of brain tissue generates massive information-dense images that are challenging to analyze and require custom software. We present an alternative query-driven programming-free strategy using a multiplex visual search engine (mViSE) that learns the multifaceted brain tissue chemoarchitecture, cytoarchitecture, and myeloarchitecture. Our divide-and-conquer strategy organizes the data into panels of related molecular markers and uses self-supervised learning to train a multiplex encoder for each panel with explicit visual confirmation of successful learning. Multiple panels can be combined to process visual queries for retrieving similar communities of individual cells or multicellular niches using information-theoretic methods. The retrievals can be used for diverse purposes including tissue exploration, delineating brain regions and cortical cell layers, profiling and comparing brain regions without computer programming. We validated mViSE's ability to retrieve single cells, proximal cell pairs, tissue patches, delineate cortical layers, brain regions and sub-regions. mViSE is provided as an open-source QuPath plug-in.
Problem
Research questions and friction points this paper is trying to address.
Develops a visual search engine for multiplex brain tissue images
Enables query-driven analysis without programming for tissue exploration
Retrieves similar cell communities and delineates brain regions
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses self-supervised learning for multiplex encoder training
Organizes data into panels of related molecular markers
Combines panels for visual queries using information-theoretic methods
🔎 Similar Papers
No similar papers found.
