Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Convolutional neural networks for segmentation of FIB-SEM nanotomography data from porous polymer films for controlled drug release
RISE Research Institutes of Sweden, Bioekonomi och hälsa, Jordbruk och livsmedel.
Chalmers University of Technology, Sweden; KTH Royal Institute of Technology, Sweden.
AstraZeneca, Sweden.
Visa övriga samt affilieringar
2021 (Engelska)Ingår i: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 283, nr 1, s. 51-63Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Phase-separated polymer films are commonly used as coatings around pharmaceutical oral dosage forms (tablets or pellets) to facilitate controlled drug release. A typical choice is to use ethyl cellulose and hydroxypropyl cellulose (EC/HPC) polymer blends. When an EC/HPC film is in contact with water, the leaching out of the water-soluble HPC phase produces an EC film with a porous network through which the drug is transported. The drug release can be tailored by controlling the structure of this porous network. Imaging and characterization of such EC porous films facilitates understanding of how to control and tailor film formation and ultimately drug release. Combined focused ion beam and scanning electron microscope (FIB-SEM) tomography is a well-established technique for high-resolution imaging, and suitable for this application. However, for segmenting image data, in this case to correctly identify the porous network, FIB-SEM is a challenging technique to work with. In this work, we implement convolutional neural networks for segmentation of FIB-SEM image data. The data are acquired from three EC porous films where the HPC phases have been leached out. The three data sets have varying porosities in a range of interest for controlled drug release applications. We demonstrate very good agreement with manual segmentations. In particular, we demonstrate an improvement in comparison to previous work on the same data sets that utilized a random forest classifier trained on Gaussian scale-space features. Finally, we facilitate further development of FIB-SEM segmentation methods by making the data and software used open access. © 2021 The Authors.

Ort, förlag, år, upplaga, sidor
Blackwell Publishing Ltd , 2021. Vol. 283, nr 1, s. 51-63
Nyckelord [en]
controlled drug release, convolutional neural networks, deep learning, focused ion beam scanning electron microscopy, image analysis, machine learning, microstructure, polymer films, porous materials, semantic segmentation
Nationell ämneskategori
Polymerkemi
Identifikatorer
URN: urn:nbn:se:ri:diva-53031DOI: 10.1111/jmi.13007Scopus ID: 2-s2.0-85104456896OAI: oai:DiVA.org:ri-53031DiVA, id: diva2:1557317
Anmärkning

Funding details: 2019‐01295; Funding details: Stiftelsen för Strategisk Forskning, SSF; Funding details: Vetenskapsrådet, VR, 2016‐03809; Funding text 1: We acknowledge Anna Olsson and Christian von Corswant at AstraZeneca Gothenburg for discussions and for providing the samples and Chalmers Material Analysis Laboratory for their support of microscopes. We acknowledge the financial support of the Swedish Research Council (Grant number 2016‐03809), the Swedish Research Council for Sustainable Development (Grant number 2019‐01295), the Swedish Foundation for Strategic Research (the project ‘Material structures seen through microscopes and statistics'), and Chalmers Area of Advance Materials Science. A GPU used for part of this research was donated by the NVIDIA Corporation. The computations were in part performed on resources at Chalmers Centre for Computational Science and Engineering (C3SE) provided by the Swedish National Infrastructure for Computing (SNIC)

Tillgänglig från: 2021-05-25 Skapad: 2021-05-25 Senast uppdaterad: 2023-05-26Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Loren, NiklasRöding, Magnus

Sök vidare i DiVA

Av författaren/redaktören
Loren, NiklasRöding, Magnus
Av organisationen
Jordbruk och livsmedel
I samma tidskrift
Journal of Microscopy
Polymerkemi

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 103 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf