TY - JOUR
T1 - Assessment of subvisible particles in biopharmaceuticals with image feature extraction and machine learning
AU - Maharjan, Ravi
AU - Lee, Jae Chul
AU - Bøtker, Johan Peter
AU - Kim, Ki Hyun
AU - Kim, Nam Ah
AU - Jeong, Seong Hoon
AU - Rantanen, Jukka
N1 - Publisher Copyright:
© 2024 Elsevier B.V.
PY - 2024/2/15
Y1 - 2024/2/15
N2 - An image classification tool was developed to classify subvisible particles, namely silicone oil (SO) and non-silicone oil (NSO; protein aggregate, rubber closure, and air bubble) particles, present in biopharmaceuticals using feature extraction in FlowCam® images, and the outcomes were validated with six machine learning (ML) classifiers. The image classification tool set at specific configuration: condition 1 − CDEP {(compactness, diameter, elongation, perimeter) = (8.06, 10.44, 13.30, 27.20)} identified SO, while the configuration set at condition 2 – CDEL {(compactness, diameter, elongation, length) = (3.14, 24.48, 1.97, 4.28)} detected NSO. The classification tool was particularly useful in detecting the release of SO after exposure to the stress sources. Additionally, the morphological features-based classification tool (p < 0.05) enhanced the predictive accuracy of the ML classification tools (≥97.2 %). Specifically, CNN (100 %) outperformed naïve Bayes (99.3 %), linear discriminant analysis (98.4 %), artificial neural network (98.1 %), support vector machine (SVM 97.2 %). Bootstrap forest was excluded because it failed to classify SO in a large dataset. The developed classification tool could be an alternative in classifying the image datasets without the burden of complex ML tools. Such image-based classification tool can be computationally economical solution in quality control of the protein formulations.
AB - An image classification tool was developed to classify subvisible particles, namely silicone oil (SO) and non-silicone oil (NSO; protein aggregate, rubber closure, and air bubble) particles, present in biopharmaceuticals using feature extraction in FlowCam® images, and the outcomes were validated with six machine learning (ML) classifiers. The image classification tool set at specific configuration: condition 1 − CDEP {(compactness, diameter, elongation, perimeter) = (8.06, 10.44, 13.30, 27.20)} identified SO, while the configuration set at condition 2 – CDEL {(compactness, diameter, elongation, length) = (3.14, 24.48, 1.97, 4.28)} detected NSO. The classification tool was particularly useful in detecting the release of SO after exposure to the stress sources. Additionally, the morphological features-based classification tool (p < 0.05) enhanced the predictive accuracy of the ML classification tools (≥97.2 %). Specifically, CNN (100 %) outperformed naïve Bayes (99.3 %), linear discriminant analysis (98.4 %), artificial neural network (98.1 %), support vector machine (SVM 97.2 %). Bootstrap forest was excluded because it failed to classify SO in a large dataset. The developed classification tool could be an alternative in classifying the image datasets without the burden of complex ML tools. Such image-based classification tool can be computationally economical solution in quality control of the protein formulations.
KW - Biopharmaceuticals
KW - Classification
KW - Feature extraction
KW - Image classification tool
KW - Machine learning
KW - Subvisible particle
UR - http://www.scopus.com/inward/record.url?scp=85181910015&partnerID=8YFLogxK
U2 - 10.1016/j.chemolab.2024.105061
DO - 10.1016/j.chemolab.2024.105061
M3 - Article
AN - SCOPUS:85181910015
SN - 0169-7439
VL - 245
JO - Chemometrics and Intelligent Laboratory Systems
JF - Chemometrics and Intelligent Laboratory Systems
M1 - 105061
ER -