Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Data

arXiv cs.CV / 4/1/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that subcellular-resolution whole-brain light-sheet fluorescence microscopy (LSFM) generates petabyte-scale 3D data that is difficult to process and interpret with current scalable methods.
It introduces CANVAS, a large benchmark dataset of intact whole mouse brain LSFM data with six neuronal/immune markers, cell annotations, and a leaderboard designed to support development of generalizable foundation models.
The authors report that baseline visual-task models (e.g., detection/classification architectures) struggle to generalize to this LSFM modality, especially across varying cellular morphologies by phenotype and brain anatomical region.
CANVAS is presented as the first and largest LSFM benchmark in this domain that captures intact mouse brain tissue at subcellular resolution while providing extensive annotations throughout the brain.

Abstract

Unprecedented visual details of biological structures are being revealed by subcellular-resolution whole-brain 3D microscopy data, enabled by recent advances in intact tissue processing and light-sheet fluorescence microscopy (LSFM). These volumetric data offer rich morphological and spatial cellular information, however, the lack of scalable data processing and analysis methods tailored to these petabyte-scale data poses a substantial challenge for accurate interpretation. Further, existing models for visual tasks such as object detection and classification struggle to generalize to this type of data. To accelerate the development of suitable methods and foundational models, we present CANVAS, a comprehensive set of high-resolution whole mouse brain LSFM benchmark data, encompassing six neuronal and immune cell-type markers, along with cell annotations and a leaderboard. We also demonstrate challenges in generalization of baseline models built on existing architectures, especially due to the heterogeneity in cellular morphology across phenotypes and anatomical locations in the brain. To the best of our knowledge, CANVAS is the first and largest LSFM benchmark that captures intact mouse brain tissue at subcellular level, and includes extensive annotations of cells throughout the brain.