HAMscope: a snapshot Hyperspectral Autofluorescence Miniscope for real-time molecular imaging

TL;DR

HAMscope is a compact hyperspectral imaging device that uses deep learning to enable real-time, label-free molecular imaging across various biological systems, with high fidelity and broad applicability.

Contribution

It introduces a novel, scalable hyperspectral miniscope with integrated deep learning for real-time molecular imaging without spectral unmixing.

Findings

Achieves high spectral fidelity with mean absolute error ~0.0048.

Successfully images plant tissues and generalizes to other biological samples.

Supports direct molecular mapping at video rates.

Abstract

We introduce HAMscope, a compact, snapshot hyperspectral autofluorescence miniscope that enables real-time, label-free molecular imaging in a wide range of biological systems. By integrating a thin polymer diffuser into a widefield miniscope, HAMscope spectrally encodes each frame and employs a probabilistic deep learning framework to reconstruct 30-channel hyperspectral stacks (452 to 703 nm) or directly infer molecular composition maps from single images. A scalable multi-pass U-Net architecture with transformer-based attention and per-pixel uncertainty estimation enables high spatio-spectral fidelity (mean absolute error ~ 0.0048) at video rates. While initially demonstrated in plant systems, including lignin, chlorophyll, and suberin imaging in intact poplar and cork tissues, the platform is readily adaptable to other applications such as neural activity mapping, metabolic profiling, and histopathology. We show that the system generalizes to out-of-distribution tissue types and supports direct molecular mapping without the need for spectral unmixing. HAMscope establishes a general framework for compact, uncertainty-aware spectral imaging that combines minimal optics with advanced deep learning, offering broad utility for real-time biochemical imaging across neuroscience, environmental monitoring, and biomedicine.