Connect with us


AI Quickens Process of Stem Cell Therapy



Stem cell therapy has exploded in popularity within the last few years given its incredible ability to act as a regenerative medicine. However, researchers and clinicians have traditionally had to evaluate stem cell quality by observing each individual cell under a microscope, which is a major limitation to the possible advancements.

Researchers from Japan have now found a way to quicken the entire process by using artificial intelligence (AI). The study was published back in February in Stem Cells.

In the study, researchers from Tokyo Medical and Dental University (TMDU) developed an AI system called DeepACT, which can identify healthy, productive skin stem cells. It can do this with the same level of accuracy as a human being.

Stem Cell Possibilities 

Because stem cells are capable of developing into various different types of mature cells, they can help grow new tissues when an individual suffers from an injury or disease. For example, keratinocyte (skin) stem cells can be used to treat inherited skin diseases, and they can enable entire sheets of skin to be grown in order to repair large burns. 

Takuya Hirose is one of the lead authors of the study.

“Keratinocyte stem cells are one of the few types of adult stem cells that grow well in the lab. The healthiest keratinocytes move more quickly than less healthy cells, so they can be identified by the eye using a microscope,” says Takuya Hirose. “However, this method is time-consuming, labor-intensive, and error-prone.”

In order to get around this time-consuming method, the researchers set out to develop a system capable of identifying and tracking the movement of the stem cells automatically. 

Jun’ichi Kotoku is co-lead author of the study.

“We trained this system through a process called ‘deep learning' using a library of sample images,” says Kotoku. “Then we tested it on a new group of images and found that the results were very accurate compared with manual analysis.”

Image: TMDU

Motion Index

Not only can the DeepACT system detect individual stem cells, but it can also calculate the ‘motion index’ of each colony. This motion index is what indicates how fast the cells at the central region of the colony move when compared to those located at the marginal region.

The study found that the colonies with the highest motion index were much more likely than their counterparts to grow well. This means the highest motion index colonies are better for generating sheets of new skin that can be transplanted to burn patients.

Daisuke Nanba is senior author of the study.

“DeepACT is a powerful new way to perform accurate quality control of human keratinocyte stem cells and will make this process both more reliable and more efficient,” says Nanba. 

Skin transplants have a risk of failing if they contain too many unhealthy or unproductive stem cells, so it is extremely helpful if medical professionals can identify the most suitable cells. This system could also enable automated quality control, which would help advance industrial stem cell manufacturing and ensure stable cell supplies and lower production costs. 

Alex McFarland is an AI journalist and writer exploring the latest developments in artificial intelligence. He has collaborated with numerous AI startups and publications worldwide.