What You Should Know:
– Proscia, a provider of AI-powered pathology solutions, is accelerating the pace of drug discovery and diagnostic development with the launch of Concentriq® Embeddings and the Proscia AI Toolkit.
– These powerful new tools empower life sciences organizations to leverage the full potential of artificial intelligence in pathology, leading to faster breakthroughs and improved patient outcomes.
Transforming AI Development in Pathology
Integrated into Proscia’s Concentriq platform, Concentriq Embeddings provides researchers and AI developers with a collection of pathology foundation models. These models, including DINOv2, PLIP, ConvNext, and CTransPath, allow teams to generate “embeddings” – high-dimensional numerical representations of whole slide images. These embeddings are essential for a wide range of AI applications in pathology, such as:
- Image classification and segmentation: Identifying and classifying different types of cells and tissues.
- Risk scoring: Predicting the likelihood of disease progression or treatment response.
- Multimodal data integration: Combining pathology data with other data sources, such as genomics and clinical records, to gain a more comprehensive understanding of disease.
Concentriq Embeddings ensures researchers always have access to the latest state-of-the-art AI models, with plans to continuously add new models as they evolve. This allows for rapid prototyping and large-scale AI model development directly within the Concentriq platform.
Accelerating AI Development with Immediate Data Access
By leveraging pathology data already stored within Concentriq, researchers can eliminate the time-consuming process of data migration and standardization. This seamless integration enables teams to:
- Generate embeddings instantly: Accelerating the AI development process.
- Rapidly iterate on AI models: Facilitating faster experimentation and optimization.
- Access real-world data: Proscia’s RWD offering provides access to high-quality, diverse datasets, empowering researchers to build more accurate and clinically relevant AI models.
Proven Performance and Scalability
Concentriq Embeddings has already demonstrated its ability to significantly accelerate AI development in pilot programs with leading CROs and pharmaceutical companies. In one case study, data scientists were able to develop algorithms 13 times faster, generating 80 AI-based breast cancer biomarker prediction models in under 24 hours. In a production environment, this translates to reducing AI development time from weeks to hours, enabling therapies to reach patients faster.
Proscia AI Toolkit: Empowering the Life Sciences Community
To further accelerate AI adoption in pathology, Proscia is also introducing the Proscia AI Toolkit. This suite of open-source resources provides developers and data scientists with the tools they need to build and deploy AI solutions more effectively. The toolkit includes:
- A Python client: For seamless integration with Concentriq Embeddings.
- Comprehensive tutorials: Paired with Python code in Jupyter Notebooks, enabling users to quickly learn and implement AI techniques.
- A growing library of helper functions: Simplifying common tasks like image tiling and organizing API outputs.
Unlocking the Future of AI-Driven Pathology
With the launch of Concentriq Embeddings and the Proscia AI Toolkit, Proscia is accelerating the development of novel AI solutions in the life sciences. By empowering researchers and developers with cutting-edge tools and a collaborative ecosystem, Proscia is playing a critical role in unlocking faster, more impactful advancements in AI-driven pathology, ultimately leading to improved patient care and outcomes.
“It’s an exciting time at the intersection of medicine and technology. The proliferation of digital pathology and explosion in capabilities of today’s AI models bring a totally new scale to how to develop therapies and diagnose patients,” said David West, CEO of Proscia. “We’re approaching a world where experiments that once took years can now be run in silico in a matter of days, and life-saving treatments that reach only a fraction of patients today could soon reach everyone.”
