Deep Learning Enables High-Throughput Analysis of Particle-Aggregation-Based Biosensors Imaged Using Holography

Abstract

Aggregation-based assays, using micro-and nano-particles have been widely accepted as an efficient and cost-effective bio-sensing tool, particularly in microbiology, where particle clustering events are used as a metric to infer the presence of a specific target analyte and quantify its concentration. Here, we present a sensitive and automated readout method for aggregation-based assays using a wide-field lens-free on-chip microscope, with the ability to rapidly analyze and quantify microscopic particle aggregation events in 3D, using deep learning-based holographic image reconstruction. In this method, the computation time for hologram reconstruction and particle autofocusing steps remains constant, regardless of the number of particles/clusters within the 3D sample volume, which provides a major throughput advantage, brought by deep learning-based image reconstruction. As a proof of concept, we demonstrate rapid detection of herpes simplex virus (HSV) by monitoring the clustering of antibodycoated micro-particles, achieving a detection limit of ~5 viral copies/µL (i.e., ~25 copies/test).

Machine Learning‐Enabled Smart Sensor Systems

“…Biomedical smart sensor systems are not limited to CNN smart model that solves classification and segmentation problems; they can be applied to reconstruct images taken by a lowerresolution image sensor. Wu et al [201] leveraged CNN to reconstruct localized microparticles from 20 mm 2 holographic images captured by a chip-based digital holographic microscope. Their system demonstrates real-time cluster detection and counting of herpes simplex virus (HSV) by monitoring the antibody microparticles attached to it.…”

“…Reproduced with permission. [201] Copyright 2019, American Chemical Society. c) Classification of breast cancer using H&E-stained biopsy images to train a CNN model.…”

Deep-Learning-Based Image Reconstruction and Enhancement in Optical Microscopy

“…10). All these properties have already made the algorithm useful for applications, such as particle aggregation-based sensing of viruses [135] and automatic detection/counting of bioaerosols [136], in which a trained network was used to improve both the quality of the autofocusing and phase recovery.…”

Metasurface‐Based Molecular Biosensing Aided by Artificial Intelligence

“…Although deep learning has already shown great potential in the field of biosensing, in which DNNs have previously been used for herpes simplex virus detection from holographic images, [85] it has not yet been fully explored for spectral-based biosensing. In this context, we envision that molecular barcodes are the ideal candidates to enable,i n conjunction with DNNs,t he identification and kinetic characterization of complex biological entities in realistic environments,s uch as the dynamic interactions between cells and extracellular vesicles (EVs), which include exosomes and synaptic vesicles.Specifically,adataset containing the molecular barcodes of extracellular vesicles under various biological and/or physiological conditions would be used to train aneural network to identify,categorize,and quantify them in real-time,enabling the recording of the intricate dynamics of these complex entities ( Figure 7C).…”