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

Christopher P. Calderon, Austin L. Daniels, Theodore W. Randolph

Flow-Imaging Microscopy (FIM) is commonly used in both academia and industry to characterize subvisible particles (those $\le 25\mu m$ in size) in protein therapeutics. Pharmaceutica…