Single-Nanoparticle Orientation Sensing by Deep Learning

Jingtian Hu; Tingting Liu; Priscilla Choo; Shengjie Wang; Thaddeus Reese; Alexander D. Sample; Teri W. Odom

doi:10.1021/acscentsci.0c01252

Single-Nanoparticle Orientation Sensing by Deep Learning

Jingtian Hu, Tingting Liu, Priscilla Choo, Shengjie Wang, Thaddeus Reese, Alexander D. Sample, Teri W. Odom^*

^*Corresponding author for this work

Chemistry

Research output: Contribution to journal › Article › peer-review

15 Scopus citations

Abstract

This paper describes a computational imaging platform to determine the orientation of anisotropic optical probes under differential interference contrast (DIC) microscopy. We established a deep-learning model based on data sets of DIC images collected from metal nanoparticle optical probes at different orientations. This model predicted the in-plane angle of gold nanorods with an error below 20°, the inherent limit of the DIC method. Using low-symmetry gold nanostars as optical probes, we demonstrated the detection of in-plane particle orientation in the full 0-360° range. We also showed that orientation predictions of the same particle were consistent even with variations in the imaging background. Finally, the deep-learning model was extended to enable simultaneous prediction of in-plane and out-of-plane rotation angles for a multibranched nanostar by concurrent analysis of DIC images measured at multiple wavelengths.

Original language	English (US)
Pages (from-to)	2339-2346
Number of pages	8
Journal	ACS Central Science
Volume	6
Issue number	12
DOIs	https://doi.org/10.1021/acscentsci.0c01252
State	Published - Dec 23 2020

Funding

The work related to discovering optically responsive nanomaterials by machine learning was supported by the National Science Foundation (NSF) under NSF Award NSF CMMI-1848613 (J.H. and T.W.O.). The optical imaging development was supported by the National Institutes of Health (NIH) Grant 5 R01 GM131421-02 (T.L. and P.C.). This work was also partially supported by CONIX center of STARnet Semiconductor Research Corporation program, which was sponsored by MARCO and DARPA (S.W.). This work made use of the EPIC and NUFAB facility of Northwestern University’s NUANCE Center, which has received support from the Soft and Hybrid Nanotechnology Experimental (SHyNE) Resource (NSF ECCS-1542205); the MRSEC program (NSF DMR-1720139) at the Materials Research Center; the International Institute for Nanotechnology (IIN); the Keck Foundation; and the State of Illinois, through the IIN. This research was supported in part through the computational resources and staff contributions provided for the Quest high performance computing facility at Northwestern University, which is jointly supported by the Office of the Provost, the Office for Research, and Northwestern University Information Technology. This work also used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation Grant No. ACI-1548562.

ASJC Scopus subject areas

General Chemical Engineering
General Chemistry

Access to Document

10.1021/acscentsci.0c01252

Cite this

@article{56149a630e534c10a70f33598ee59dfe,

title = "Single-Nanoparticle Orientation Sensing by Deep Learning",

abstract = "This paper describes a computational imaging platform to determine the orientation of anisotropic optical probes under differential interference contrast (DIC) microscopy. We established a deep-learning model based on data sets of DIC images collected from metal nanoparticle optical probes at different orientations. This model predicted the in-plane angle of gold nanorods with an error below 20°, the inherent limit of the DIC method. Using low-symmetry gold nanostars as optical probes, we demonstrated the detection of in-plane particle orientation in the full 0-360° range. We also showed that orientation predictions of the same particle were consistent even with variations in the imaging background. Finally, the deep-learning model was extended to enable simultaneous prediction of in-plane and out-of-plane rotation angles for a multibranched nanostar by concurrent analysis of DIC images measured at multiple wavelengths.",

author = "Jingtian Hu and Tingting Liu and Priscilla Choo and Shengjie Wang and Thaddeus Reese and Sample, {Alexander D.} and Odom, {Teri W.}",

note = "Publisher Copyright: {\textcopyright} 2020 American Chemical Society.",

year = "2020",

month = dec,

day = "23",

doi = "10.1021/acscentsci.0c01252",

language = "English (US)",

volume = "6",

pages = "2339--2346",

journal = "ACS Central Science",

issn = "2374-7943",

publisher = "American Chemical Society",

number = "12",

}

TY - JOUR

T1 - Single-Nanoparticle Orientation Sensing by Deep Learning

AU - Hu, Jingtian

AU - Liu, Tingting

AU - Choo, Priscilla

AU - Wang, Shengjie

AU - Reese, Thaddeus

AU - Sample, Alexander D.

AU - Odom, Teri W.

PY - 2020/12/23

Y1 - 2020/12/23

N2 - This paper describes a computational imaging platform to determine the orientation of anisotropic optical probes under differential interference contrast (DIC) microscopy. We established a deep-learning model based on data sets of DIC images collected from metal nanoparticle optical probes at different orientations. This model predicted the in-plane angle of gold nanorods with an error below 20°, the inherent limit of the DIC method. Using low-symmetry gold nanostars as optical probes, we demonstrated the detection of in-plane particle orientation in the full 0-360° range. We also showed that orientation predictions of the same particle were consistent even with variations in the imaging background. Finally, the deep-learning model was extended to enable simultaneous prediction of in-plane and out-of-plane rotation angles for a multibranched nanostar by concurrent analysis of DIC images measured at multiple wavelengths.

AB - This paper describes a computational imaging platform to determine the orientation of anisotropic optical probes under differential interference contrast (DIC) microscopy. We established a deep-learning model based on data sets of DIC images collected from metal nanoparticle optical probes at different orientations. This model predicted the in-plane angle of gold nanorods with an error below 20°, the inherent limit of the DIC method. Using low-symmetry gold nanostars as optical probes, we demonstrated the detection of in-plane particle orientation in the full 0-360° range. We also showed that orientation predictions of the same particle were consistent even with variations in the imaging background. Finally, the deep-learning model was extended to enable simultaneous prediction of in-plane and out-of-plane rotation angles for a multibranched nanostar by concurrent analysis of DIC images measured at multiple wavelengths.

UR - http://www.scopus.com/inward/record.url?scp=85096648638&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85096648638&partnerID=8YFLogxK

U2 - 10.1021/acscentsci.0c01252

DO - 10.1021/acscentsci.0c01252

M3 - Article

C2 - 33376795

AN - SCOPUS:85096648638

SN - 2374-7943

VL - 6

SP - 2339

EP - 2346

JO - ACS Central Science

JF - ACS Central Science

IS - 12

ER -

Single-Nanoparticle Orientation Sensing by Deep Learning

Abstract

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this