Diagnostics & imaging AI · Lung nodule risk AI
Optellum
Optellum makes AI software that finds patients with lung nodules in radiology reports and scores each nodule's cancer risk from the CT scan to guide follow-up, biopsy, and treatment decisions.
Strong fit
- Health systems running lung nodule clinics or incidental nodule follow-up programs
- Pulmonology and thoracic teams deciding which nodules need biopsy, treatment, or more scans
- Programs adding robotic bronchoscopy that want help choosing patients
Weak fit
- Radiology groups shopping for broad triage AI across many findings
- Sites with too few chest CT scans to run a nodule program
- Buyers who need a published price list
Bottom line
Optellum is worth using for health systems that want earlier lung cancer diagnosis and fewer unneeded biopsies in their lung nodule programs. Its FDA-cleared AI gives each nodule a cancer risk score and is paid for by Medicare under its own codes. Radiologists wanting general chest CT detection may prefer Riverain.
Score breakdown
Weights: Outcomes 35% · Product 30% · Implementation 20% · Pricing clarity 15%.
Optellum, based in Oxford, England, makes the Virtual Nodule Clinic.
Václav Potěšil founded the company in 2016 with Timor Kadir, Jérôme Declerck, Lyndsey Pickup, and Professor Sir Michael Brady, colleagues from his doctoral work at the University of Oxford. Johnathan Watkins, a former McKinsey consultant, has led it as CEO since 2021, and Brady is its chair.
The Virtual Nodule Clinic reads radiology reports across a health system to find patients with incidental lung nodules. Its Lung Cancer Prediction AI turns each nodule on the CT scan into a cancer risk score. That helps pulmonologists choose between follow-up scans, biopsy, and treatment.
That AI is FDA cleared, CE and UKCA marked, and paid for by Medicare under its own codes. Its LungOS platform adds modules that link imaging to treatment decisions.
Optellum has a US office at the Texas Medical Center in Houston.
The software runs at more than 250 sites and had analyzed more than 3 million cases by June 2026.
Customers include Penn Medicine, Vanderbilt, Oxford University Hospitals, AtlantiCare, and SimonMed, and Tanner Health rolled it out across its system in Georgia.
In January 2026, Guy's and St Thomas' in London began an NHS pilot pairing its AI with robotic bronchoscopy in a single lung cancer diagnostic pathway.
Johnson & Johnson, GE Healthcare, and Coreline Soft are partners, and Intuitive's venture arm invested in its Series A.
Compare Riverain Technologies when radiologists want FDA-cleared detection tools for chest CT and X-ray.
Qure.ai fits a system that wants chest and emergency triage AI at a mid-range cost. Aidoc fits when the goal is triage and alerts across many critical findings.
Competitor landscape
| Vendor | Overall | Ease of implementation |
|---|---|---|
| Aidoc | 7.9 | 7.5 |
| Qure.ai | 7.4 | 7.1 |
| Optellum | 7.4 | 7.0 |
| Riverain Technologies | 7.3 | 6.9 |
Pricing
| Item | Detail |
|---|---|
| Model | Custom contract quoted by Optellum. Medicare pays for use of its Lung Cancer Prediction AI under CPT codes 0721T and 0722T. |
| What usually drives cost | Number of sites and CT volume, whether scanning reports for incidental nodules is included, PACS and EHR connection, and expected Medicare billing. |
| What to ask before you buy | Whether pricing is per scan or a site license, how Medicare payments under the CPT codes offset the cost, and what integration with the PACS and EHR costs. |
| Published pricing | Optellum does not publish a price list. |
Prerequisites for purchase
| Need | Why it matters |
|---|---|
| What you need to get Optellum to function | |
| Pulmonology or nodule program lead | Owns the workflow. |
| PACS and radiology report access | The software reads both. |
| Navigator or coordinator for follow-up | Flagged patients need outreach. |
| Baseline biopsy and diagnosis times | You need them to show the change later. |
| Billing setup for the CPT codes | Captures Medicare payment. |
| What will maximize your value | |
| Start with incidental nodule tracking | Finds patients who fall through gaps. |
| Review risk scores at a multidisciplinary meeting | Builds clinician trust. |
| Track benign biopsy rates | Shows avoided procedures. |
| Deal-breakers | |
| You do few chest CT scans | |
| No team will follow up flagged patients | |
| There is no way to connect to your PACS | |
Value creation time frame
| # | Stage | Typical range |
|---|---|---|
| 1 | Contract and PACS connection | 1-3 months |
| 2 | Nodule clinic live | 1-2 months |
| 3 | Report scanning and more sites | 6-12 months |
Leadership
Methodology
| Weight | Factor | What it measures |
|---|---|---|
| 35% | Customer outcomes | Whether buyers get measurable operational or clinical-workflow results after go-live |
| 30% | Product | Capability depth, reliability, and fit for the job the category buys |
| 20% | Implementation | How hard it is to stand up, integrate, train, and stabilize |
| 15% | Pricing clarity | Whether a buyer can model total cost without a mystery quote |
| Label | Meaning |
|---|---|
| Highly recommend | Strong outcomes and product with manageable caveats |
| Recommend | Solid fit for the right buyer; know the tradeoffs |
| Conditional | Only with a specific use case or heavy caveats |
| Not recommended | Avoid for most buyers in this category |
Read our full methodology for how we weight scores and assign recommend labels.