Abstract: A framework for a few-shot learning method is disclosed. In a first part, self-supervision and classification supervision are used to train a feature extractor. An example self-supervision method comprises running grayscale images through an edge filter, normalizing the filtered images, setting the normalized images to ground truth, generating feature-extracted images, using a decoder to reconstruct images from the feature-extracted images, determining a loss between the reconstructed images and the ground truth images, and using the loss to update parameters of the feature extractor. In a second part, a few-shot adaptation process is performed to adapt the model to a novel rapid test kit.

Abstract: The present disclosure provides devices, systems, and methods for detection of nucleic acids based on CRISPR-Cas editing systems, for example for use in biosurveillance. Disclosed herein are systems and methods utilizing two devices: 1) a point of—need disposable “FET Strip” (enzymatic), and 2) an instrument-operated “FET Multiplexor” (electronic), to provide detection of a nucleic acid for biosurveillance.