← sunnyray.com
The Sunny Ray Show · Episode Page

From Devastation to Breakthrough: How She’s Revolutionizing Human Fertility

Cara Wells · Founder and CEO, eMGenesis · 25:00
watch on youtube ↗

What we talked about.

Cara Wells, founder and CEO of eMGenesis, joins Sunny Ray to share how a childhood love of horses led her from an animal science degree toward a PhD in reproductive physiology, then into human IVF work, and finally into entrepreneurship. She describes the industry problem she uncovered, that roughly 20 percent of transferred embryos are already dead or dying, and explains how eMGenesis uses AI to analyze 30 second smartphone microscope videos of embryos, tracking cellular activity frame by frame to predict pregnancy probability. Wells recounts training the models on outcomes from over 60,000 cattle, a chance airplane meeting with mentor Dr. Kimberly Graham that pushed her toward starting a company, the painful collapse of her first venture and lawsuit against her university, and the TED talk on video motion magnification that sparked eMGenesis in 2020. She closes by outlining the company's expansion into human fertility and endangered species conservation.

A reproductive physiologist explains how AI-powered embryo video analysis could transform IVF success rates in animals and humans.

The questions, and the answers.

Tell us a bit about what you're working on.

I am founder and CEO of eMGenesis. We build software solutions to evaluate embryo health using video analysis and machine learning, originally for livestock IVF and now expanding into human fertility.

Where does your backstory begin? Were you born in Texas?

I'm born and bred in Texas, from the Houston area. My parents were oil and gas engineers with no ties to agriculture or biomed. I fell in love with horses young, pursued animal science, landed in an undergraduate embryo research lab, and stayed for a PhD before moving to Austin and eventually starting eMGenesis.

Can you explain what happens in an IVF clinic?

Eggs are extracted and fertilized with sperm, then embryos are grown for several days, day seven in cattle, day five in humans. An embryologist visually grades them under a microscope to decide which to transfer, freeze, or discard. It's highly subjective, and about 20 percent of transferred embryos are actually dead or dying at that point.

How are you using AI and deep learning to evaluate embryos?

AI is pattern recognition, not magic, so we had to build our own dataset. We collect 30 second smartphone videos of embryos through a microscope and run machine learning frame by frame to capture cellular activity. We trained models on real pregnancy outcomes from over 60,000 cattle so the system can predict a pregnancy probability for embryos it has never seen.

Are you saying this technology can be used by people struggling to have babies?

That's where we're using it already. We're partnering with IVF labs, still in the research phase, to train our models on human embryos and identify which ones are healthiest and most likely to result in pregnancy versus ones that are genetically abnormal and will never result in a viable pregnancy.

Can you talk about your chance encounter with Dr. Kimberly Graham on an airplane?

I was finishing my PhD, unsure what came next, and sat next to Kimberly on a Southwest flight. She was building an innovation ecosystem in Lubbock and told me I could start a company. I was making 21 dollars an hour with a PhD, so I took her advice, joined her programs, and she coached me to win about 2 million dollars in pitch competitions.

What was the hardest part after your first company dissolved?

All of it. Team conflicts over funding and ego turned into the university working against us, and I ended up suing my alma mater and my former professor over the IP. After a year of fighting with no resolution, I accepted you can't reason with unreasonable people, and I vowed to never build on university owned IP again.

What sparked the pivot that led to eMGenesis in 2020?

Someone sent me a TED talk about video motion magnification from MIT, which amplified micro-motions in video, like showing blood flow changing color in a man's face. I realized if embryos are dynamic and their cells are constantly active, we could analyze real time video to objectively evaluate them. That became the proof of concept for eMGenesis.

IVFEmbryo HealthAI and Machine LearningAgTechHuman FertilityEntrepreneurshipAnimal Science

Cara Wells

Founder and CEO, eMGenesis

Building something daring? Sunny talks to founders like this every day. Fifteen minutes to see if your story belongs on the stage.

Claim your pre-interview
Built with help from AI. We use AI tools to research, draft, and assemble pages like this one. A human reviews everything, but if something looks off, tell us and we will fix it fast.