NIH Using Artificial Intelligence to Evaluate Stem Cell Quality

November 15, 2019 - NIH researchers used artificial intelligence to evaluate stem cell-derived “patches” of retinal pigment epithelium (RPE) tissue for implanting into the eyes of patients with age-related macular degeneration (AMD).

The study demonstrates the potential for AI to perform quality control of therapeutic cells and tissues. Researchers at the National Eye Institute (NEI), part of NIH, and the National Institute of Standards and Technology (NIST) worked together to develop the method.

“This AI-based method of validating stem cell-derived tissues is a significant improvement over conventional assays, which are low-yield, expensive, and require a trained user,” said Kapil Bharti, PhD, a senior investigator in the NEI Ocular and Stem Cell Translational Research Section.

Cells of the RPE support the light-sensoring photoreceptors in the eye and are among the first to die from geographic atrophy, known as dry AMD. Without the RPE, photoreceptors die, leading to blindness and vision loss.

“Our approach will help scale up manufacturing and will speed delivery of tissues to the clinic,” added Bharti, who led the research along with Carl Simon Jr., PhD, and Peter Bajcsy, PhD, of NIST.

The team is working on a technique for making RPE replacement patches from AMD patients’ cells. Patient blood cells are coaxed in the lab to become induced pluripotent stem cells (IPSCs), which can become any type of cell in the body. The IPS cells are then seeded onto a biodegradable scaffold where they were induced to differentiate into mature RPE. The scaffold-RPE is implanted back into the eye behind the retina to preserve vision.

In an animal model, the patch successfully preserved vision, and the team is planning a clinical trial.

The AI algorithm leveraged deep neural networks and was trained on images of the RPE obtained using quantitative bright-field absorbance microscopy. Researchers trained the networks to identify visual indications of RPE maturation that correlated with positive RPE function.

Specifically, the AI-based image analysis method accurately identified known markers of RPE maturity and function. The method can also match a particular iPSC-RPE tissue sample to other samples from the same donor, which helps confirm the identity of tissues during clinical-grade manufacturing.

“Multiple AI-methods and advanced hardware allowed us to analyze terabytes and terabytes of imaging data for each individual patient, and do it more accurately and much faster than in the past,” Bajcsy said.  

“This work demonstrates how a garden variety microscope, if used carefully, can make a precise, reproducible measurement of tissue quality,” Simon said.

Major players in the healthcare industry are doing more research with stem cells. Johns Hopkins Medicine recently announced an initiative to advance precision medicine research using the stem cell technologies of The New York Stem Cell Foundation (NYSCF) Research Institute.

“Stem cell science holds enormous potential for the treatment of a wide range of diseases,” Paul B. Rothman, dean of the School of Medicine and CEO of Johns Hopkins Medicine, said in a press release.

“By combining this approach with Johns Hopkins' groundbreaking work on precision medicine, we are creating a scientific powerhouse that will help us advance medicine and science at an even faster pace. I am excited to see the discoveries and innovations that will be produced by this collaboration.”