Your browser doesn't support javascript.
loading
Statistical Characterization of the Morphologies of Nanoparticles through Machine Learning Based Electron Microscopy Image Analysis.
Lee, Byoungsang; Yoon, Seokyoung; Lee, Jin Woong; Kim, Yunchul; Chang, Junhyuck; Yun, Jaesub; Ro, Jae Chul; Lee, Jong-Seok; Lee, Jung Heon.
Afiliación
  • Lee B; School of Advanced Materials Science and Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Yoon S; SKKU Advanced Institute of Nanotechnology (SAINT), Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Lee JW; School of Advanced Materials Science and Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Kim Y; School of Advanced Materials Science and Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Chang J; School of Advanced Materials Science and Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Yun J; Department of Systems Management Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Ro JC; School of Advanced Materials Science and Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Lee JS; Department of Systems Management Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
  • Lee JH; School of Advanced Materials Science and Engineering, Sungkyunkwan University (SKKU), Suwon 16419, South Korea.
ACS Nano ; 14(12): 17125-17133, 2020 Dec 22.
Article en En | MEDLINE | ID: mdl-33231065
Although transmission electron microscopy (TEM) may be one of the most efficient techniques available for studying the morphological characteristics of nanoparticles, analyzing them quantitatively in a statistical manner is exceedingly difficult. Herein, we report a method for mass-throughput analysis of the morphologies of nanoparticles by applying a genetic algorithm to an image analysis technique. The proposed method enables the analysis of over 150,000 nanoparticles with a high precision of 99.75% and a low false discovery rate of 0.25%. Furthermore, we clustered nanoparticles with similar morphological shapes into several groups for diverse statistical analyses. We determined that at least 1,500 nanoparticles are necessary to represent the total population of nanoparticles at a 95% credible interval. In addition, the number of TEM measurements and the average number of nanoparticles in each TEM image should be considered to ensure a satisfactory representation of nanoparticles using TEM images. Moreover, the statistical distribution of polydisperse nanoparticles plays a key role in accurately estimating their optical properties. We expect this method to become a powerful tool and aid in expanding nanoparticle-related research into the statistical domain for use in big data analysis.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: ACS Nano Año: 2020 Tipo del documento: Article País de afiliación: Corea del Sur Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: ACS Nano Año: 2020 Tipo del documento: Article País de afiliación: Corea del Sur Pais de publicación: Estados Unidos