Skip to main content

COMPUTER VISION

AI in Life Sciences Fast-Tracks Research and Development

A woman lab tech surrounded by equipment looks over data on a computer monitor.

Artificial Intelligence is causing a remarkable shift in the life sciences industry—from drug discovery and manufacturing to clinal trials and efficacy assessment. The accelerated development of the Covid-19 vaccine is a remarkable example. AI played a critical role in mRNA development, with vaccines put into action in less than a year, saving millions of lives.

So, it’s not a question of if AI in life sciences will accelerate biotech but how fast it will happen at scale. Companies that harness the latest technologies can fast-track drug discovery, clinical trials, operations efficiency, as well as ease the onerous work of regulatory compliance.

But the lab environment is complex and fragmented, without a unified architecture or equipment standards and tools. In this highly regulated space, integrating AI across special-purpose devices, legacy systems, and a general lack of data standards makes equipment upgrades costly and time-consuming.

It’s not a question of if #AI in life sciences will accelerate #biotech but how fast it will happen at scale. @Wallarooai via @insightdottech

Putting AI and Biotech Solutions to Work

One biotech company, an industry-leading provider of life sciences diagnostic and instrumentation, saw the status quo both as an opportunity for its business. To gain advantage, the company put into action an ambitious strategy to deliver fully configured AI solutions for use cases such as microscope image analysis and enhanced diagnostic workflows.

But the company lacked the technology, skills, and tools required to develop and deploy AI/ML software. To deliver new capabilities to their customer base, they needed expert help to effectively:

  • Package and deploy AI models at industrial scale
  • Manage AI models with centralized monitoring and observability
  • Ensure seamless updates and maintenance for models in production

This is where Wallaroo.AI, a provider of production-grade inference platforms, comes into the picture. With its deep expertise in AI and machine learning operations, Wallaroo.AI delivers integrated software and hardware solutions that enable its customers to ramp their AI development and advance staff expertise at scale.

AI Inference Platform Advances Stem Cell Research

Collaboration between Wallaroo.AI and Intel started with the integration of AI capabilities alongside the life sciences company’s products for stem cell research already used in labs around the world. To achieve optimal results, AI was customized for a particular microscope and cell line.

“Imagine a microscope today with a person sitting in front of it, having to look at every single plate with a set of wells which hold the cells being analyzed,” says Stephen Spellicy, Chief Operating Officer at Wallaroo.AI. “Now, computer vision technology can look at these plates at a glance and detect living or dead cells in the given well at scale. This improves efficiency of detection by an order of magnitude.”

In partnership with Intel, Wallaroo.AI developed edge AI infrastructure products that support the biotech company’s legacy microscopes and other third-party devices to fully automate and streamline stem cell research. 

“We basically disconnect the brain from the body and build that into an Intel-powered smart controller that connects to the microscope infrastructure inside their customers’ clinical laboratories,” says Spellicy. “But you’re trying not to throw the baby out with the bathwater. The smarter the tech is instrumented, the more easily it can be integrated into a legacy environment.”

Wallaroo.AI and the biotech product provider’s goal for the initial project includes deploying AI models to a set of 15 labs, forming the backbone for scalable diagnostics across thousands of labs worldwide. The solution integrates the Wallaroo Universal AI Inference Platform with existing IoT devices and life sciences instruments, enabling AI solutions for diverse use cases. Plus, it delivers centralized observability and edge AI management, ensuring efficient and reliable operations at scale.

Together, Wallaroo.AI and Intel have turned a complex challenge into a scalable AI solution, demonstrating the power of AI to transform the life sciences sector. Key outcomes include:

  • Efficiency gains: AI-powered analysis eliminates the need for volatile chemicals and streamlines workflows—significantly improving time to value.
  • Enhanced diagnostics: Cutting-edge technology enables the processing of microscope images to augment traditional cell-staining techniques.
  • Scalability: The tools to expand AI capabilities globally, providing consistent and reliable diagnostics across thousands of labs.

“We’re helping not just with the software and hardware combined solution, but also from a professional services perspective,” says Spellicy. “We understand what kind of effort this takes so we’re helping in many ways to streamline the process as they ramp their staff to be able to take on this project at scale.”

The Future of AI and Life Sciences

While still in the early phases of applying AI and computer vision in life sciences laboratories, the life sciences company sees these technologies disrupting their industry, starting with its own business.

“They have the potential to quickly train and deploy models for different use cases. Today it’s disease A, tomorrow it’s disease B, the next day it’s disease C,” says Spellicy. “With an adaptable product infrastructure, our customer can apply different pipelines to solve different challenges, enriching the value of the overall solution they’re selling to the laboratories.”

Generative AI is an obvious next step in the life sciences industry, where applications will take all the value of learned knowledge and transfer that knowledge to individuals. The new frontier of chatbots for research is changing the game in how scientists interact with, and drive more value from, laboratory data. Empowering people with technology creates endless possibilities for promising outcomes.

 

This article was edited by Christina Cardoza, Editorial Director for insight.tech.

About the Author

Georganne Benesch is an Editorial Director for insight.tech. Before this she was an independent writer, authoring blogs, web content, solution guides, white papers and more. Prior to her freelance career Georganne held product management and marketing positions at companies such as Cisco, Proxim and Netopia. She earned a B.A. at University of California at Santa Cruz.

Profile Photo of Georganne Benesch