Manual frame-by-frame analysis slowed research. Vision AI now extracts quantitative data directly from video to predict outcomes.
A spinoff from the renowned Gustave Roussy Institute tests cancer therapies on lab-grown organoids to simulate patient responses, generating vast amounts of experimental video data.
Researchers relied on labor-intensive manual analysis of individual video frames, making it difficult to scale interpretation across large datasets....
“The idea is to basically use images of these organoids to extract as much information as possible to make the prediction as accurate as possible. So we’re moving from a qualitative description of images to something quantitative that you can then feed to your downstream models.”
AI-native drug discovery platform using patient-derived tumor avatars.
Social technology company developing AI frameworks, VR hardware, and digital platforms.
Collaborated on the project to help Orakl Oncology train DINOv2 on organoid images.
Related implementations across industries and use cases
Prenatal exams miss 66% of heart defects. Using a pre-trained vision model accelerated R&D to secure FDA clearance in 2 years.
Matching phages required screening trillions of options. Gen AI simulates interactions, cutting discovery from 10 years to 2 months.
Diagnostic delays averaged six months in low-resource areas. AI now analyzes tissue and drafts reports to accelerate care.
Silos forced teams to manually chase data. Now, AI agents identify adverse events in seconds, eliminating weeks of cross-referencing.
Attorneys juggled fragmented tools to search 50,000 cases. An AI orchestrator now routes queries to sub-agents in a single chat.
Lab supply orders were handwritten in notebooks. Digital ordering now takes seconds, saving 30,000 hours for research annually.
Experts spent 15 minutes pulling data from scattered systems. Natural language prompts now generate detailed reports instantly.