Ongoing advances in computer architecture and data analysis make imaging an increasingly appealing option for tracking bioprocessing. As Sang-Kyu Jung, PhD, associate professor of biological and chemical engineering at Hongik University in Sejong, Republic of Korea, noted: “The development of various deep learning architectures and training techniques suitable for image processing, along with the emergence of high-performance GPUs (Graphics Processing Units) capable of handling them, has led to the application of more sophisticated image processing technologies.”

Today’s imaging analysis can tell scientists much more about the status of a bioprocess. As Jung explained, analyzing images with machine learning “can now be used to classify objects according to their characteristics and predict important phenomena.”

CHO cells

As one example, a team of scientists at the Beijing Key Laboratory of Enze Biomass Fine Chemicals in China applied image analysis to Chinese hamster ovary (CHO) cells in culture. Specifically, these scientists used a deep-learning approach to analyze images of these cells. In addition to providing online, real-time information, these scientists pointed out that “accurate and automatic statistics of geometrical characteristics facilitate optimization and control of culture process.”

Various imaging technologies can be used to enhance bioprocessing. For instance, Jean-Sébastien Guez, PhD, a senior scientist at the Institut Pascal in France, and his colleagues used in situ microscopy to analyze antibody production by mammalian cells in a bioreactor. As these scientists concluded: Analyzing these images with AI-based methods “produced cell density and viability estimates showing very high accuracy … under non-suboptimal culture conditions.”

Imaging-based methods in bioprocessing will likely continue to attract more attention. At the 16th Bioprocessing Summit in Boston, for example, Theodore Randolph, PhD, professor of chemical and biological engineering at the University of Colorado, will give a talk about using machine learning to analyze images for the formation of aggregates during a bioprocess.

Over time, imaging will be used to analyze even more features of bioprocessing, do so in real time, and lead to more efficient and productive biomanufacturing.

Previous articleEmerging Purification Method May Be Ni-NTA FPLC Alternative
Next articleMeeting the Challenge of Manufacturing Macrophages