Imagene AI
Imagene AI reads routine stained lung cancer slides and predicts which gene changes a tumor carries, without using more tissue for sequencing. Clinicians order its LungOI test, and drug companies use its software and services for research.
LungOI runs in Imagene's own certified laboratory in Phoenix, Arizona, and returns results the next day. It has its own billing code and a Medicare payment rate, and is not cleared by the FDA. A research version, the Lung Prediction Panel, predicts eight alterations to help decide which samples to send for testing and which patients to screen for trials, and is also available inside Mindpeak's peakDeploy.
Both run on CanvOI, a pathology foundation model Imagene built with Oracle and the Ellison Medical Institute. Drug companies, contract research organizations and diagnostics companies use OI Suite to train prediction models on their own patient groups, in the cloud or on their own servers. A 2026 peer reviewed study tested the model on 968 lung cancer samples.
Imagene AI Ltd is an Israeli company with a US laboratory, and Oracle's chairman Larry Ellison sits on its board. No price is published.
Capability Axes
An AI Health Index grade measures what a buyer can verify from public sources on the date shown. It is not a rating of how good the product is. A vendor can build an excellent system and grade low on an axis because it publishes nothing an outsider can check. How grades read
The models are the product. LungOI and the Lung Prediction Panel report gene alterations that CanvOI, Imagene's pathology foundation model, predicts from H&E images, with no sequencing behind the result. OI Suite is software for training and running prediction models on a customer's own patient groups. Without the models there is no test result and no software to sell.
Results go to an ordering clinician, and the controls around a prediction are not described. Only authorized clinicians can order LungOI. Results arrive through a portal with heat maps and summaries of the tissue features behind the prediction. The research panel runs a quality control step on tissue integrity and the amount of analyzable tissue after each upload.
The research panel is positioned for deciding which samples go to confirmatory molecular testing and is labeled not for clinical use. The LungOI page says the test supports timely clinical decisions and presents a patient whose EGFR prediction was confirmed by a rapid PCR test before treatment began. It does not say whether confirmatory testing is required before a LungOI result is acted on.
Nothing published states the threshold at which a prediction is reported as positive, when a result is withheld as indeterminate, or how a wrong prediction is handled.
The model is named and its training data outlined. Version and update practice are not. CanvOI is Imagene's pathology foundation model, developed with Oracle and the Ellison Medical Institute. It is described as trained on more than two million H&E and immunohistochemistry images and tiles from multiple sites across more than 40 organs, with billions of parameters. The 2026 peer reviewed study names version 1.1.
Imagene claims up to 20 percent better performance than other models when data is limited, without publishing the comparison on its pages. No release notes, version history or notice of model changes is published for LungOI or OI Suite customers.
Imagene builds its own model. CanvOI was developed with Oracle and the Ellison Medical Institute, and no outside model provider is named or implied between a slide and a result. Imagene describes cloud infrastructure through Oracle, which hosts the systems rather than supplying the model.
No subprocessor list is published, and the parties that handle laboratory images, results and OI Suite customer cohorts are not listed.
A peer reviewed study and a larger external abstract support the predictions, without figures at a stated threshold or any outcome in use. A study in npj Precision Oncology (Rolfo and colleagues, 2026), which Imagene cites, tested CanvOI 1.1 on 968 non small cell lung cancer samples. Areas under the curve were 0.87 for EGFR, 0.96 for ALK, 0.88 for BRAF and 0.83 for MET. A WCLC 2026 abstract led by AstraZeneca authors, with Imagene coauthors, validated the multi gene panel on a blinded set of more than 2,000 samples, including two clinical trials, with areas under the curve above 0.8 for some genes and up to 0.93.
Imagene also describes validation on outside data from more than ten medical centers and a single center prospective study. It cites a case report in the Journal of Clinical Pathology of a patient whose EGFR prediction was confirmed by PCR before treatment, and names Sheba Medical Center, Tel Aviv Sourasky Medical Center, Northwestern Medicine, Hoag and Ohio State among its partners. The research panel has run more than 4,300 analyses across more than 20 sites, a measure of use rather than benefit.
Imagene's pages give no sensitivity, specificity or negative predictive value at the threshold used for reporting. No study shows how often LungOI results change or speed treatment compared with standard testing.
Imagene gives general assurances that do not answer the questions its models raise. It describes its laboratory system as HIPAA compliant and secured, and its website privacy policy, updated in October 2026, says personal data from the website is kept only as long as needed and then deleted or anonymized.
Nothing published says how long patient slides, images and results are kept, whether clinical cases or customer cohorts are used to train or refine CanvOI, or how training data was de identified. CanvOI is trained on millions of images from multiple sites, and OI Suite customers upload their own cohorts. No safety engineering is published.
HIPAA compliance is claimed without the documents behind it. The LungOI page describes a HIPAA compliant, secured laboratory information system, and the test is run by a US clinical laboratory that receives patient slides and images.
The website privacy policy, last updated on 19 October 2026, covers the website only and asks visitors not to send health or patient information through it. No notice of privacy practices for the laboratory, no business associate position for OI Suite customers and no agreement are published.
There is no published security audit or certification. The company describes a HIPAA compliant, secured laboratory information system, which is a compliance claim, not an audit. No SOC 2 report, ISO/IEC 27001 certificate, HITRUST certification, penetration testing statement or trust center appears on its site.
Laboratory certification and accreditation cover testing quality, not information security. Any certifications Oracle's cloud holds are the host's, not Imagene's.
The clinical test is offered as a laboratory developed test, with no device claim. LungOI runs in a CLIA certified, CAP accredited laboratory, and its page states it has not been cleared or approved by the FDA. The Lung Prediction Panel is labeled for research use only, not for diagnosis, and OI Suite is research software. The FDA's databases list no Imagene device.
The LungOI page describes the test as supporting timely clinical decisions. Its patient story presents a case in which a rapid PCR test confirmed an AI predicted EGFR mutation before targeted therapy began.
Imagene describes validation across sites, but publishes no results by patient group and no governance process. It describes external validation on data from more than ten medical centers and a prospective study, and a 2026 peer reviewed study reports results by alteration.
Nothing published compares performance across centers, scanners, specimen types, sex, smoking history or ancestry. That matters because lung cancer driver alterations differ in frequency by ancestry and smoking history, which affects how a prediction performs. No responsible AI policy, model governance process or monitoring after release is described.
Clinicians can check a prediction, but nothing stands behind it. LungOI results come with heat maps and summaries of the tissue features behind each prediction, which a pathologist can inspect. The research panel is positioned for deciding which samples go on to confirmatory molecular testing.
The published validation reports areas under the curve, which do not give an error rate at the threshold used to report a result. No notice of privacy practices or correction route for laboratory results, warranty, retesting commitment or indemnity is published.
Named platforms carry the products, with direction and production use undocumented. The LungOI ordering portal is operated with Lumea, and clinicians upload whole slide images and pathology reports through it to Imagene's laboratory information system. In October 2026 Imagene and Mindpeak announced that the research use Lung Prediction Panel is available inside Mindpeak's peakDeploy, which embeds tissue AI in laboratories' existing systems. Imagene joined Proscia's partner alliance in August 2026 to build AI immunohistochemistry companion diagnostics.
No hospital record system, laboratory information system or interface standard is named for sending LungOI results into a hospital's systems, and results arrive through the portal.
Named platforms, with no documented route into a hospital's records.
Deployment options are named, but no location is committed. OI Suite is offered in the cloud, as a hybrid or on premises, and Imagene describes cloud infrastructure through Oracle. LungOI runs in Imagene's US laboratory, with results on a portal operated with Lumea.
Nothing published says in which region images and results are stored, whether data from US patients is processed in Israel, or how customer environments are kept apart.
No price is published, but how each product is sold can be worked out. Clinicians order LungOI through Imagene's laboratory portal. It has its own billing code and a Medicare payment rate, which is what Medicare pays the laboratory, not a price Imagene states.
The Lung Prediction Panel is sold for research use. OI Suite is licensed by subscription for cloud, hybrid or on premises use, with access arranged by email. OI Predict and OI CDx are sold as services to drug companies, with Daiichi Sankyo and CellCarta named as collaborators.
The scope is narrow, and the lung products have validation behind them. LungOI and the Lung Prediction Panel are for non small cell lung cancer, working from biopsy H&E images or glass slides. The panel names eight alterations, the EGFR, KRAS G12C, ERBB2 and BRAF V600E mutations, the ALK, RET and ROS1 fusions, and MET exon 14 skipping. A 2026 peer reviewed study reports results for four of them on 968 samples.
LungOI is a clinical test ordered by oncologists. OI Suite serves drug company translational research, biomarker discovery and companion diagnostic work. CanvOI is described as trained across more than 40 organs. The publications page lists earlier work on HER2 in breast cancer, FGFR3 in bladder cancer and high grade B cell lymphoma, and OI Predict offers custom assays such as KRAS and PIK3CA in colorectal cancer, but every product sold is for lung. OI CDx supports companion diagnostic work with drug companies, and OI Discover is listed as coming soon.
Alternatives to Imagene AI
Other products that do the same kind of work as Imagene AI, and what each one does.
Lunit SCOPE is the pathology AI line of Lunit, the Seoul medical AI company. Drug companies, contract research organizations and digital pathology platforms use it to measure cancer biomarkers on tissue slides for research and trials.
Biomy makes DeepPathFinder, cloud software that uses AI to map immune and cancer cells on tissue slides for drug research.
PreciseDx sells PreciseBreast, a test that predicts whether early breast cancer will come back, using AI to read the cell patterns on a routine stained slide.
PictorLabs, which now styles its name Pictor Labs, makes software that stains tissue images with AI instead of chemicals, and a tissue intelligence platform built on it.
Aiosyn sells AI that analyzes images of stained tissue, to pathology laboratories and to drug companies running animal studies.
Bioptimus is a Paris company that builds AI foundation models for pathology and biology. Drug companies, research groups and pathology software makers license them as a base for their own tools.
Pricing
Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.
| Entry Price | Pricing Basis | BAA Tier | Implementation | Source |
|---|---|---|---|---|
|
Not published
|
LungOI is a laboratory developed test billed per test, with its own billing code and a Medicare payment rate; the Lung Prediction Panel is sold for research use; OI Suite is licensed by subscription for cloud, hybrid or on premises deployment. No price published. | Not published. A HIPAA compliant laboratory system is claimed, and the published privacy policy covers the website alone. | Not published. | Vendor Published |
Imagene publishes how each product is reached without a price. LungOI is ordered by registered clinicians through the laboratory portal, and its Medicare payment rate is what Medicare pays the laboratory, not a list price. The research use panel and OI Suite are arranged through the laboratory email address and an onboarding call. No test price outside Medicare and no OI Suite subscription basis is published.