English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Flow-Imaging Microscopy (FIM) is commonly used in both academia and industryto characterize subvisible particles (those $\le 25 \mu m$ in size) in proteintherapeutics. Pharmaceutical companies are required to record vast volumes ofFIM data on protein therapeutic products, but are only mandated under US FDAregulations (i.e., USP $\big \langle 788 \big \rangle$) to control the numberof particles exceeding $10$ and $25 \mu m$ in delivered products. Hence, a vastamount of digital images are available to analyze. Current state-of-the-artmethods rely on a relatively low-dimensional list of "morphological features"to characterize particles, but these methods ignore an enormous amount ofinformation encoded in the existing large digital image repositories. DeepConvolutional Neural Networks (CNNs or "ConvNets") have demonstrated theability to extract predictive information from raw macroscopic image datawithout requiring the selection or specification of "morphological features" ina variety of tasks. However, the heterogeneity, polydispersity of proteintherapeutics, and optical phenomena associated with subvisible FIM particlemeasurements introduce new challenges regarding the application of CNNs to FIMimage analysis. In this article, we demonstrate a supervised learning techniqueleveraging CNNs to extract information from raw images in order to predict theprocess conditions or stress states (freeze-thaw, mechanical shaking, etc.)that produced a variety of different protein images. We demonstrate that ournew classifier (in combination with a sample "image pooling" strategy) canobtain nearly perfect predictions using as few as 20 FIM images from a givenprotein formulation in a variety of scenarios of relevance to proteintherapeutics quality control and process monitoring.

Using Deep Convolutional Neural Networks to Circumvent Morphological  Feature Specification when Classifying Subvisible Protein Aggregates from  Micro-Flow Images