Toronto, ON – Altis Labs, Inc. (“Altis”), the computational imaging platform for advancing precision medicine, today announces the publication of its imaging-based prognostication (IPRO) study in the Journal of Clinical Oncology - Clinical Cancer Informatics (link). This work is the result of a close collaboration between clinicians and researchers from Princess Margaret Cancer Centre, Toronto General Hospital, Dana-Farber Cancer Institute, and Altis.
The retrospective study included 1,110 stage I-IV non-small cell lung cancer patients and describes how IPRO, a fully-automated deep learning system, predicts 1-, 2-, and 5-year mortality risk from three-dimensional imaging features present in the thorax.
“Our study demonstrates that CT scans, which are used in lung cancer screening, staging, and response assessment, contain rich prognostic information beyond tumor size that we haven’t been able to take advantage of, until now” states lead author Felipe S. Torres, MD, PhD, cardiothoracic radiologist from the Joint Department of Medical Imaging at Toronto General Hospital. Torres points out that, in future work, “we hope to explore how IPRO might help us inform treatment intensification or de-escalation to further personalize care decisions.”
Traditionally, clinicians focus on tumor presence and size when analyzing CT scans of lung cancer patients. IPRO, which is trained on CT scans and associated outcomes, complemented traditional image interpretation frameworks and generated more accurate, clinically meaningful insights across disease stages and subsequent treatment regimens.
Co-author Shazia Akbar, PhD, who leads machine learning research at Altis Labs, adds that “IPRO’s association with known prognostic factors like age, sex, and TNM stage, as well as its increased attention placed on tumors, is very revealing. It indicates that IPRO independently learned to discern these clinical factors from a CT scan and that they are of prognostic importance. Now the question is, what else is IPRO learning from these images that we don’t already know, and how can we use that to make novel discoveries?”
Altis Labs is the computational imaging company advancing precision medicine. We believe that medical imaging is the richest source of untapped information. Life sciences companies use our software platform, Nota, to accelerate all stages of clinical development. Trained on over 140 million real-world images with associated diagnostics, treatment information, and outcomes, Nota predicts clinically meaningful outcomes from baseline and follow-up scans to more accurately stratify patients and quantify treatment effect. Altis is proudly based in Toronto, Canada.
To unlock more insights from your clinical trial data, visit altislabs.com or email firstname.lastname@example.org.