Digital pathology developer Proscia is launching an artificial intelligence toolkit for life science researchers alongside a program that translates biopsy slide images into quantitative data for easier number-crunching by AI models.
The company said the new offerings under its Concentriq platform are aimed at healthcare organizations and research institutions that are looking to wield their own massive, proprietary data repositories—tapping them to train new foundation models that could then help identify biomarkers and support the development of new tests and treatments.
“It’s an exciting time at the intersection of medicine and technology,” Proscia CEO David West said in a statement. “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.”
“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,” West said.
The Concentriq Embeddings program relies on AI models to deliver numerical representations of whole-slide images, simplifying the process of feeding them into algorithms for computing cancer risk scores and image classifiers. The company said this could help eliminate the steps of data migration, processing and image standardization in AI development.
Proscia cited an internal case study with a customer that said a team of data scientists were able to develop algorithms 13 times faster and build 80 breast cancer prediction models in under 24 hours.
Meanwhile, the Proscia AI Toolkit includes open-source tech, including software libraries and tutorials, designed to help users implement Concentriq Embeddings into their research.