Altis Labs has raised a $25M Series A co-led by OrbiMed and Qiming Venture Partners USA, funding an AI imaging endpoint the company says can detect drug benefit earlier than standard scan measurements.
The Toronto company’s IPRO system reads CT scans already collected in trials and quantifies thousands of prognostic imaging biomarkers spanning tumor burden, body composition and organ health. It does not automate RECIST, the rule set used to measure lesion size. It predicts survival directly.
Evidence landed the same week. A post-hoc analysis of the MARIPOSA Phase 3 trial in EGFR-mutated non-small cell lung cancer, presented at the World Conference on Lung Cancer in Seoul, found the IPRO Response Rate favored the investigational treatment from week 16, with a rate ratio of 1.33. RECIST-based objective response rate never anticipated the trial’s 12-plus month median overall survival benefit.
IPRO analyzed roughly 10,000 scans automatically. The company says the signal appeared 11 months before the primary progression-free survival readout and 26 months before final overall survival data.
The readout shows AI can anticipate clinical benefit that traditional imaging endpoints may miss, said founder and CEO Felix Baldauf-Lenschen.
Why it matters: sponsors decide whether to keep funding a program long before survival data matures. An endpoint built on existing scans adds no imaging cost, but it will need regulator buy-in before it can anchor a filing, and progression-free survival took years to win that acceptance.
