Life sciences organizations can quickly build AI algorithms to discover biomarkers, optimize clinical trials, and advance companion diagnostics—powered by the first digital pathology platform to seamlessly integrate underlying models
Proscia®, the global leader in AI-based pathology solutions for precision medicine, today announced the launch of Concentriq® Embeddings and the Proscia AI Toolkit, enabling life sciences organizations to accelerate the discovery and development of novel therapeutics and diagnostics. Integrated into Proscia’s Concentriq platform, Concentriq Embeddings seamlessly delivers a collection of pathology-based models to AI developers and research scientists, allowing them to leverage an organization’s large proprietary data sets and execute the models within their regular workflows.
“This is an exciting time at the intersection of medicine and technology. The proliferation of digital pathology and the explosion in the capabilities of today’s artificial intelligence models brings a whole new scale to how treatments are developed and patients are diagnosed,” said David West, CEO of Proscia. “We are moving toward a world where experiments that once took years can now be performed in computers in days, and where life-saving treatments that today only reach a small proportion of patients will soon be available to everyone.”
Artificial Intelligence Development Transforming Pathology
Concentriq Embeddings, enabled in Proscia’s Concentriq® platform, allows pathology and data science teams to generate high-dimensional digital representations (embeddings) from entire slide images. These embeddings are initially derived from four powerful base models – DINOv2, PLIP, ConvNext and CTransPath – with plans to add new models as they are developed. This ensures that researchers always have access to the latest state-of-the-art tools and can experiment with multiple models in parallel, further enhancing downstream performance and improving accuracy for biomarker discovery and other critical tasks. Researchers can also select the best base model for their specific needs, with applications ranging from image classification and segmentation to risk scoring and multimodal data integration, supporting rapid prototyping and large-scale AI model development directly within the Concentriq platform.
Get instant access to data and faster results
Because pathology data is already stored in the Concentriq platform, teams can immediately leverage the data for AI development, eliminating the need for time-consuming data migration, external processing, and image format standardization. This tight integration with existing data infrastructure enables organizations to instantly generate embeddings and quickly iterate on AI models, reducing development time and speeding up experimentation. Proscia’s Real World Data (RWD) products further enrich the platform, providing high-quality, diverse, multi-modal datasets that enable researchers to build more accurate, clinically actionable AI models.
Proven performance and scalability
In pilot projects with top CROs and top pharmaceutical companies, Concentriq Embeddings has demonstrated its ability to significantly accelerate AI development. In an internal case study, data scientists developed an algorithm that was 13 times faster, generating 80 AI-based breast cancer biomarker prediction models in 24 hours. In a production environment, pharmaceutical companies can reduce AI development time from weeks to hours, allowing treatments to reach patients faster.
Proscia AI Toolkit: Accelerating AI Adoption
Proscia not only provides cutting-edge technology, but also fosters innovation in digital pathology by fostering a collaborative environment where developers and data scientists can leverage each other’s expertise. To complement Concentriq Embeddings, Proscia launches Proscia Artificial Intelligence Toolkit—A set of open source resources designed to empower the life sciences community and accelerate the adoption of artificial intelligence.
Developed and refined by Proscia’s expert AI R&D team, these tools have been instrumental in driving internal AI development, and they are now being shared with the wider community. this Proscia Artificial Intelligence Toolkit include:
- Python client For seamless API integration with Concentriq Embeddings.
- Comprehensive tutorial Used with Python code in Jupyter Notebooks, it enables users to quickly learn and implement AI.
- A growing library of helper functions Ideal for tasks such as image tiling and organizing API output, reducing the complexity of common processes.
These resources are designed to help teams quickly integrate Concentriq Embeddings into their workflows, allowing them to focus on building and refining AI models rather than overcoming technical obstacles. In addition, we encourage the growing community of Concentriq users to contribute their own tools to extend the library with new technologies and innovations. This collaborative, community-driven approach will not only enhance the implementation of underlying models, but also expand the use of artificial intelligence across the entire Concentriq platform, whether building, visualizing or deploying models.
By accelerating the development of novel AI solutions in the life sciences, Proscia’s AI toolkit plays a key role in enabling faster, more impactful advances in AI-driven pathology.
“This is really powerful technology,” said Julianna Ianni, vice president of artificial intelligence research and development at Proscia. “Concentriq Embeddings not only accelerates the development of artificial intelligence, but will also trigger a new wave of innovation in pathology. It enables teams to achieve breakthroughs faster and faster than we have ever imagined, providing new opportunities for research and patient care.” Laying the foundation for transformative progress.”
Sign up for the free insideAI news newsletter.
Join us on Twitter: https://twitter.com/InsideBigData1
Join us on LinkedIn: https://www.linkedin.com/company/insideainews/
Join us on Facebook: https://www.facebook.com/insideAINEWSNOW
