A micro-XRT image analysis and machine learning methodology for the characterisation of multi- particulate capsule formulations

Research output: Contribution to journalArticle

5 Downloads (Pure)

Abstract

The application of X-ray microtomography for quantitative structural analysis of pharmaceutical multi-particulate systems was demonstrated for commercial capsules, each containing approximately 300 formulated ibuprofen pellets. The implementation of a marker-supported watershed transformation enabled the reliable segmentation of the pellet population for the 3D analysis of individual pellets. Isolated translation- and rotation-invariant object cross-sections expanded the applicability to additional 2D image analysis techniques. The full structural characterisation gave access to over 200 features quantifying aspects of the pellets' size, shape, porosity, surface and orientation. The extracted features were assessed using a ReliefF feature selection method and a supervised Support Vector Machine learning algorithm to build a model for the detection of broken pellets within each capsule. Data of three features from distinct structure-related categories were used to build classification models with an accuracy of more than 99.55% and a minimum precision of 86.20% validated with a test dataset of 886 pellets. This approach to extract quantitative information on particle quality attributes combined with advanced data analysis strategies has clear potential to directly inform manufacturing processes, accelerating development and optimisation.

Original languageEnglish
Article number100041
Number of pages11
JournalInternational Journal of Pharmaceutics: X
Volume2
Early online date15 Jan 2020
DOIs
Publication statusE-pub ahead of print - 15 Jan 2020

Fingerprint

Capsules
X-Ray Microtomography
Ibuprofen
Porosity
Pharmaceutical Preparations
Population
Machine Learning
Datasets
Support Vector Machine

Keywords

  • Pharmaceutical Formulation
  • Micro-XRT Particle Analysis
  • Watershed Image Segmentation
  • Sensitivity Analysis
  • Feature Selection
  • Machine Learning
  • Classification Model

Cite this

@article{e4daac1d08c148ea90ba2590ef20184f,
title = "A micro-XRT image analysis and machine learning methodology for the characterisation of multi- particulate capsule formulations",
abstract = "The application of X-ray microtomography for quantitative structural analysis of pharmaceutical multi-particulate systems was demonstrated for commercial capsules, each containing approximately 300 formulated ibuprofen pellets. The implementation of a marker-supported watershed transformation enabled the reliable segmentation of the pellet population for the 3D analysis of individual pellets. Isolated translation- and rotation-invariant object cross-sections expanded the applicability to additional 2D image analysis techniques. The full structural characterisation gave access to over 200 features quantifying aspects of the pellets' size, shape, porosity, surface and orientation. The extracted features were assessed using a ReliefF feature selection method and a supervised Support Vector Machine learning algorithm to build a model for the detection of broken pellets within each capsule. Data of three features from distinct structure-related categories were used to build classification models with an accuracy of more than 99.55{\%} and a minimum precision of 86.20{\%} validated with a test dataset of 886 pellets. This approach to extract quantitative information on particle quality attributes combined with advanced data analysis strategies has clear potential to directly inform manufacturing processes, accelerating development and optimisation.",
keywords = "Pharmaceutical Formulation, Micro-XRT Particle Analysis, Watershed Image Segmentation, Sensitivity Analysis, Feature Selection, Machine Learning, Classification Model",
author = "Doerr, {Frederik J.S.} and Florence, {Alastair J.}",
year = "2020",
month = "1",
day = "15",
doi = "10.1016/j.ijpx.2020.100041",
language = "English",
volume = "2",
journal = "International Journal of Pharmaceutics: X",
issn = "2590-1567",

}

TY - JOUR

T1 - A micro-XRT image analysis and machine learning methodology for the characterisation of multi- particulate capsule formulations

AU - Doerr, Frederik J.S.

AU - Florence, Alastair J.

PY - 2020/1/15

Y1 - 2020/1/15

N2 - The application of X-ray microtomography for quantitative structural analysis of pharmaceutical multi-particulate systems was demonstrated for commercial capsules, each containing approximately 300 formulated ibuprofen pellets. The implementation of a marker-supported watershed transformation enabled the reliable segmentation of the pellet population for the 3D analysis of individual pellets. Isolated translation- and rotation-invariant object cross-sections expanded the applicability to additional 2D image analysis techniques. The full structural characterisation gave access to over 200 features quantifying aspects of the pellets' size, shape, porosity, surface and orientation. The extracted features were assessed using a ReliefF feature selection method and a supervised Support Vector Machine learning algorithm to build a model for the detection of broken pellets within each capsule. Data of three features from distinct structure-related categories were used to build classification models with an accuracy of more than 99.55% and a minimum precision of 86.20% validated with a test dataset of 886 pellets. This approach to extract quantitative information on particle quality attributes combined with advanced data analysis strategies has clear potential to directly inform manufacturing processes, accelerating development and optimisation.

AB - The application of X-ray microtomography for quantitative structural analysis of pharmaceutical multi-particulate systems was demonstrated for commercial capsules, each containing approximately 300 formulated ibuprofen pellets. The implementation of a marker-supported watershed transformation enabled the reliable segmentation of the pellet population for the 3D analysis of individual pellets. Isolated translation- and rotation-invariant object cross-sections expanded the applicability to additional 2D image analysis techniques. The full structural characterisation gave access to over 200 features quantifying aspects of the pellets' size, shape, porosity, surface and orientation. The extracted features were assessed using a ReliefF feature selection method and a supervised Support Vector Machine learning algorithm to build a model for the detection of broken pellets within each capsule. Data of three features from distinct structure-related categories were used to build classification models with an accuracy of more than 99.55% and a minimum precision of 86.20% validated with a test dataset of 886 pellets. This approach to extract quantitative information on particle quality attributes combined with advanced data analysis strategies has clear potential to directly inform manufacturing processes, accelerating development and optimisation.

KW - Pharmaceutical Formulation

KW - Micro-XRT Particle Analysis

KW - Watershed Image Segmentation

KW - Sensitivity Analysis

KW - Feature Selection

KW - Machine Learning

KW - Classification Model

U2 - 10.1016/j.ijpx.2020.100041

DO - 10.1016/j.ijpx.2020.100041

M3 - Article

VL - 2

JO - International Journal of Pharmaceutics: X

JF - International Journal of Pharmaceutics: X

SN - 2590-1567

M1 - 100041

ER -