DataVXApplied SciencesPaper
journal article·2022-06-08Open access

Transfer Learning Analysis for Subvisible Particle Flow Imaging of Pharmaceutical Formulations

Xiangan Long, Chongjun Ma, Han Sheng, Liwen Chen, Yiyan Fei, Lan Mi, Dongmei Han, Jiong Ma

Applied Sciences· Volume 12· Issue 12
Publisher pageOpen full text
Source abstract

Abstract

Subvisible particles are an ongoing problem in biotherapeutic injectable pharmaceutical formulations, and their identification is an important prerequisite for tracing them back to their source and optimizing the process. Flow imaging microscopy (FIM) is a favored imaging technique, mainly because of its ability to achieve rapid batch imaging of subvisible particles in solution with excellent imaging quality. This study used VGG16 after transfer learning to identify subvisible particle images acquired using FlowCam. We manually prepared standards for seven classes of particles, acquired the image information through FlowCam, and fed the images over 5 µm into VGG16 consisting of a convolutional base of VGG16 pre-trained with ImageNet data and a custom classifier for training. An accuracy of 97.51% was obtained for the test set data. The study also demonstrated that the recognition method using transfer learning outperforms machine learning methods based on morphological parameters in terms of accuracy, and has a significant training speed advantage over scratch-trained CNN. The combination of transfer learning and FIM images is expected to provide a general and accurate data-analysis method for identifying subvisible particles.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Microfluidic and Bio-sensing Technologies · Electrical and Bioimpedance Tomography · Cell Image Analysis Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Institute of Biomedical Engineering and Technology, Academy for Engineering and Technology, Fudan University, 220 Handan Road, Shanghai 200433, China

Process Development Downstream & Formulation, Shanghai Henlius Biotech, Inc., 1801 Hongmei Road, Shanghai 200233, China

Shanghai Engineering Research Center of Ultra-Precision Optical Manufacturing, Key Laboratory of Micro and Nano Photonic Structures (Ministry of Education), Green Photoelectron Platform, Department of Optical Science and Engineering, Fudan University, 220 Handan Road, Shanghai 200433, China

Ruidge Biotech Co., Ltd., Lin-Gang Special Area, China (Shanghai) Pilot Free Trade Zone, No. 888, Huanhu West 2nd Road, Shanghai 200131, China

Shanghai Engineering Research Center of Industrial Microorganisms, The Multiscale Research Institute of Complex Systems (MRICS), School of Life Sciences, Fudan University, 220 Handan Road, Shanghai 200433, China

Funding

National Key R&D Program of China · National Natural Science Foundation of China · Shanghai Natural Science Foundation · Science and Technology Research Program of Shanghai · Shanghai key discipline construction plan (2020–2022) · Shanghai Engineering Technology Research Center of Hair Medicine · Medical Engineering Fund of Fudan University · Fudan University

References (26)

Show source-provided references
1. An industry perspective on the monitoring of subvisible particles as a quality attribute for protein therapeutics10.1002/jps.22097 ↗
2. Visual Inspection of Injections (2022, March 27). The United States Pharmacopeial Convention. Available online: https://www.pharmout.net/wp-content/uploads/2018/02/NGVF-2016-Visual-Inspections-of-Injection.pdf.
3. Protein aggregation—Pathways and influencing factors10.1016/j.ijpharm.2010.02.025 ↗
4. Mechanistic complexity of subvisible particle formation: Links to protein aggregation are highly specific10.1002/jps.23299 ↗
5. Compatibility, physical stability, and characterization of an IgG4 monoclonal antibody after dilution into different intravenous administration bags10.1002/jps.23224 ↗
6. Protein nanoparticles promote microparticle formation in intravenous immunoglobulin solutions during freeze-thawing and agitation stresses10.1016/j.xphs.2018.03.016 ↗
7. Highly Aggregated Antibody Therapeutics can enhance the in vitro innate and late-stage T-cell immune responses10.1074/jbc.M111.330902 ↗
8. Immunogenicity of structurally perturbed hen egg lysozyme adsorbed to silicone oil microdroplets in wild-type and transgenic mouse models10.1016/j.xphs.2017.02.008 ↗
9. The effect of small oligomeric protein aggregates on the immunogenicity of intravenous and subcutaneous administered antibodies10.1002/jps.24592 ↗
10. Subvisible particle content, formulation, and dose of an erythropoietin peptide mimetic product are associated with severe adverse postmarketing events10.1016/S0022-3549(15)00180-X ↗
11. (2022, March 27). Particulate Matter in Injections, the United States Pharmacopeial Convention. Available online: https://www.uspnf.com/sites/default/files/usp_pdf/EN/USPNF/revisionGeneralChapter788.pdf.
12. Flow imaging microscopy for protein particle analysis—A comparative evaluation of four Different Analytical Instruments10.1208/s12248-013-9522-2 ↗
13. Characterization of particles in Protein Solutions: Reaching the limits of current technologies10.1208/s12248-010-9233-x ↗
14. (2022, March 27). Methods for Detection of Particulate Matter in Injections and Ophthalmic Solutions. The United States Pharmacopeial Convention. Available online: https://www.usp.org/.
15. Subvisible (2–100 Μm) particle analysis during biotherapeutic drug product development: Part 1, Considerations and Strategy10.1002/jps.24437 ↗
16. Discrimination between silicone oil droplets and protein aggregates in biopharmaceuticals: A novel multiparametric image filter for sub-visible particles in microflow imaging analysis10.1007/s11095-011-0590-7 ↗
17. Deep learning10.1038/nature14539 ↗
18. Deep convolutional neural networks for image classification: A comprehensive review10.1162/neco_a_00990 ↗
19. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
20. Collaborative deep learning models to handle class imbalance in flowcam plankton imagery10.1109/ACCESS.2020.3022242 ↗
21. Deep convolutional neural network analysis of flow imaging microscopy data to classify subvisible particles in protein formulations10.1016/j.xphs.2017.12.008 ↗
22. Machine learning and statistical analyses for extracting and characterizing “fingerprints” of antibody aggregation at container interfaces from flow microscopy images10.1002/bit.27501 ↗
23. Automatic identification of the stress sources of protein aggregates using flow imaging microscopy images10.1016/j.xphs.2019.10.034 ↗
24. Towards quantification and differentiation of protein aggregates and silicone oil droplets in the low micrometer and submicrometer size range by using oil-immersion flow imaging microscopy and convolutional neural networks10.1016/j.ejpb.2021.09.010 ↗
25. Huh, M., Agrawal, P., and Efros, A.A. (2016). What makes ImageNet good for transfer learning?. arXiv.
26. Simonyan, K., and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv, Available online: https://arxiv.org/abs/1409.1556.