Multidimensional particle characterisation from in-situ imaging using deep learning and transfer learning

Christopher Boyle; Carla Ferreira; Yi-Chieh Chen; Christos Tachtatzis; Ivan Andonovic; Cameron Brown; Jan Sefcik; Javier Cardona

Multidimensional particle characterisation from in-situ imaging using deep learning and transfer learning

Research output: Contribution to conference › Poster

99 Downloads (Pure)

Abstract

Particle size and shape are important in the pharmaceutical industry, affecting both process efficiency and product performance. Quality-by-design and continuous manufacturing are aided with appropriate models of processes — selection and calibration of which are informed by measurement of particle size and shape. Off-line measurements have inherent limitations when following the trajectory of particle attributes in a process; removing and treating material for off-line analysis can alter particle characteristics. In contrast, in-line measurements provide representative measures of particle size and shape at the expense of producing more challenging (out of focus, overlapping particles) datasets for extraction of particle characteristics.

Original language	English
Number of pages	1
Publication status	Published - 30 Aug 2021
Event	21st International Symposium on Industrial Crystallisation - Online Duration: 30 Aug 2021 → 2 Sept 2021 Conference number: 21 https://dechema.de/en/ISIC_2021.html https://dechema.converia.de/frontend/index.php?sub=500#:~:text=taking%20place%20from%2030%20August,give%20you%20some%20general%20information.

Conference

Conference	21st International Symposium on Industrial Crystallisation
Abbreviated title	ISIC 21
Period	30/08/21 → 2/09/21
Internet address	https://dechema.de/en/ISIC_2021.html https://dechema.converia.de/frontend/index.php?sub=500#:~:text=taking%20place%20from%2030%20August,give%20you%20some%20general%20information.

Keywords

process analytical technologies (PAT)
deep learning
in-situ imaging
particle size

Access to Document

Boyle-etal-ISIC-2021-Multidimensional-particle-characterisation-from-in-situ-imaging-using-deep-learningFinal published version, 3.02 MB

Cite this

@conference{4c699d6451774f738d6ce1ad31c6fca1,

title = "Multidimensional particle characterisation from in-situ imaging using deep learning and transfer learning",

abstract = "Particle size and shape are important in the pharmaceutical industry, affecting both process efficiency and product performance. Quality-by-design and continuous manufacturing are aided with appropriate models of processes — selection and calibration of which are informed by measurement of particle size and shape. Off-line measurements have inherent limitations when following the trajectory of particle attributes in a process; removing and treating material for off-line analysis can alter particle characteristics. In contrast, in-line measurements provide representative measures of particle size and shape at the expense of producing more challenging (out of focus, overlapping particles) datasets for extraction of particle characteristics.",

keywords = "process analytical technologies (PAT), deep learning, in-situ imaging, particle size",

author = "Christopher Boyle and Carla Ferreira and Yi-Chieh Chen and Christos Tachtatzis and Ivan Andonovic and Cameron Brown and Jan Sefcik and Javier Cardona",

year = "2021",

month = aug,

day = "30",

language = "English",

note = "21st International Symposium on Industrial Crystallisation, ISIC 21 ; Conference date: 30-08-2021 Through 02-09-2021",

url = "https://dechema.de/en/ISIC\_2021.html, https://dechema.converia.de/frontend/index.php?sub=500\#:\textasciitilde{}:text=taking\%20place\%20from\%2030\%20August,give\%20you\%20some\%20general\%20information.",

}

TY - CONF

T1 - Multidimensional particle characterisation from in-situ imaging using deep learning and transfer learning

AU - Boyle, Christopher

AU - Ferreira, Carla

AU - Chen, Yi-Chieh

AU - Tachtatzis, Christos

AU - Andonovic, Ivan

AU - Brown, Cameron

AU - Sefcik, Jan

AU - Cardona, Javier

N1 - Conference code: 21

PY - 2021/8/30

Y1 - 2021/8/30

N2 - Particle size and shape are important in the pharmaceutical industry, affecting both process efficiency and product performance. Quality-by-design and continuous manufacturing are aided with appropriate models of processes — selection and calibration of which are informed by measurement of particle size and shape. Off-line measurements have inherent limitations when following the trajectory of particle attributes in a process; removing and treating material for off-line analysis can alter particle characteristics. In contrast, in-line measurements provide representative measures of particle size and shape at the expense of producing more challenging (out of focus, overlapping particles) datasets for extraction of particle characteristics.

AB - Particle size and shape are important in the pharmaceutical industry, affecting both process efficiency and product performance. Quality-by-design and continuous manufacturing are aided with appropriate models of processes — selection and calibration of which are informed by measurement of particle size and shape. Off-line measurements have inherent limitations when following the trajectory of particle attributes in a process; removing and treating material for off-line analysis can alter particle characteristics. In contrast, in-line measurements provide representative measures of particle size and shape at the expense of producing more challenging (out of focus, overlapping particles) datasets for extraction of particle characteristics.

KW - process analytical technologies (PAT)

KW - deep learning

KW - in-situ imaging

KW - particle size

UR - https://dechema.de/en/ISIC_2021.html

M3 - Poster

T2 - 21st International Symposium on Industrial Crystallisation

Y2 - 30 August 2021 through 2 September 2021

ER -

Multidimensional particle characterisation from in-situ imaging using deep learning and transfer learning

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this