Computational Sensing Using Low-Cost and Mobile Plasmonic Readers Designed by Machine Learning

Abstract

Plasmonic sensors have been used for a wide-range of biological and chemical sensing applications. Emerging nano-fabrication techniques have enabled these sensors to be cost-effectively mass-manufactured onto various types of substrates. To accompany these advances, major improvements in sensor read-out devices must also be achieved to fully realize the broad impact of plasmonic nano-sensors. Here, we propose a machine learning framework which can be used to design low-cost and mobile multi-spectral plasmonic readers that do not use traditionally employed bulky and expensive stabilized light-sources or high-resolution spectrometers. By training a feature selection model over a large set of fabricated plasmonic nano-sensors, we select the optimal set of illumination light-emitting-diodes needed to create a minimum-error refractive index prediction model, which statistically takes into account the varied spectral responses and fabrication-induced variability of a given sensor design. This computational sensing approach was experimentally validated using a modular mobile plasmonic reader. We tested different plasmonic sensors with hexagonal and square periodicity nano-hole arrays, and revealed that the optimal illumination bands differ from those that are ‘intuitively’ selected based on the spectral features of the sensor, e.g., transmission peaks or valleys. This framework provides a universal tool for the plasmonics community to design low-cost and mobile multi-spectral readers, helping the translation of nano-sensing technologies to various emerging applications such as wearable sensing, personalized medicine, and point-of-care diagnostics. Beyond plasmonics, other types of sensors that operate based on spectral changes can broadly benefit from this approach, including e.g., aptamer-enabled nanoparticle assays and graphene-based sensors, among others.

Plasmonic molecular assays: Recent advances and applications for mobile health

“…This lightweight device utilized a CMOS imager chip to record the diffraction patterns (holograms) of the plasmonic microarrays excited by low-cost LEDs, with a minimum detectable refractive index change of ~ 4 × 10 -3 RIU. More recently, a machine learning-based computational sensing framework was also developed, which could be used to help select the most sensitive illumination wavelengths for designing cost-effective plasmonic reader devices [201]. Mirkin et al reported a microarray format scanometric assay for the detection of protein and DNA.…”

Large‐Scale Plasmonic Nanodisk Structures for a High Sensitivity Biosensing Platform Fabricated by Transfer Nanoprinting

“…Plasmonic nanostructure sensors have recently attracted substantial interest for applications in medical diagnostics, food safety, and environmental monitoring, owing to their stronger near‐field confined capacity on the surface, as compared with that of prism‐based metallic film sensors . Moreover, surface plasmon resonance (SPR) in plasmonic nanostructures can be directly excited by using simple free‐space incident light instead of complex and bulky optical prism excitation systems, which exhibits great potential for developing ultracompact and multiplexed sensing applications . Many efforts have been focused on engineering the topography and materials of nanostructures to improve their sensitivity and to realize portable sensing applications, such as nanoholes, nanodisks, nanorings, and nanomushroom arrays …”

Portable Multiplex Optical Assays

“…Reprinted from refs. (a,b), (c,d), (e,f), (g), (h), and (i) with permission: CC‐BY 4.0 open access publication (a,b,i); CC‐BY‐NC‐ND open access publication (c and d); Copyright 2017, American Chemical Society (e and f); Copyright 2009 and 2012, Royal Society of Chemistry (g and h).…”

“…Instead of analyzing spectral shifts, this portable design relied on reduction of transmission signals that were detected by a CMOS camera during the measurement of binding kinetics. Recently, a machine learning framework was introduced to select the optimum source and plasmonic chip combination through a minimum‐error refractive index prediction model . Modular design of the portable multispectral plasmonic reader was presented (Figure E).…”