⟷ drag to compare ⟷
aView · LCS
Axial · Slice 147/320 · W:1500 L:-600
LungAI v2.4
~10 mm
Lung-RADS
4X
Very Suspicious
Manual caliper · rounded · category only · ~5 to 10 min
Malignancy Risk
87/100
High Risk
+1.8 mm vs prior
LungAI · Nodule #1
TypeSolid
Size10.2 × 8.4 mm
Volume384 mm³
Density+28 HU
MarginSpiculated
LocationLUL · periph
VDT240 d
Drag to compare
Workflow
Split view
Read time
5 to 10 min / ~2 min
Output
Category + Score
Billable
Professional + Technology fees + CPT 0721T following FDA clearance
Drag the divider to compare a manual Lung-RADS read with LungAI CADx on the same scan.
AI-Powered Lung Cancer Screening + CADx Diagnostics

Lung-RADS Tells You the Category.
LungAI Tells You the Probability.

A per-nodule malignancy risk score that brings multidisciplinary tumor board-level insight to every radiologist's screen. Prior-scan comparison built in. Native to your existing CADe viewer. Billable under CPT 0721T following FDA clearance.

0.96
AUROC on NLST
vs Lung-RADS 0.88
100M
Parameter
Vision Transformer
CPT 0721T
Reimbursable
under Hospital outpatient setting following FDA clearance
Request a Demo See the Technology
The Problem

Up to 40% False Positive Rate in Current Screening.

Lung-RADS v2022 depends entirely on human judgement, a manual rule-based scoring system with no AI and no patient personalization.

How Lung-RADS Works Today
1
Manual chart review by radiologist
2
Size-based rules only (no shape or texture AI)
3
Subjective reading, 5-10 min per scan
4
Single snapshot with no longitudinal tracking
5
Result: blanket biopsy referrals or missed cancers
  ~10%
False Negatives
Real cancers missed, caught only when it's too late.
Up to 40%
False Positives
Unnecessary biopsies, procedures, and patient anxiety.
  30%
Inter-Reader Variability
Two radiologists reading the same scan will disagree on the risk category nearly a third of the time.
In a seven-reader observer study using NLST data, Lung-RADS category disagreement occurred in 29% of reading pairs, with 8% resulting in different patient management recommendations (Defined et al., European Radiology, 2019).
The Solution

AI That Sees What Lung-RADS Misses

LungAI integrates directly into your existing CADe workflow to deliver a continuous 0–100 malignancy risk score per nodule, backed by a 100-million-parameter model trained on 100,000 CT scans and reimbursable under CPT 0721T.

Architecture
Three-Component AI Model
A 3D Vision Transformer nodule encoder, a Sybil-derived whole-scan encoder, and a dense decoder that fuses both with patient demographics and prior scan data to output a per-nodule malignancy probability.
0.96 AUROC
vs Lung-RADS 0.88 on NLST held-out set
Clinical Performance
Fewer Misses. Fewer False Alarms.
In retrospective testing on the NLST held-out dataset, LungAI achieved 94% sensitivity and approximately 88% specificity at the high-sensitivity operating point, compared to 91% sensitivity and 82% specificity for Lung-RADS v2022 alone. Pre-FDA clearance. Retrospective study on held-out data. Results may differ in prospective clinical use.
94% Sensitivity
~88% Specificity · 1.5–3 min read time
Integration
Zero New Clicks. Built for Your Workflow.
LungAI scores appear directly in your existing CADe viewer. No new workstation, no new login, no IT project. One integration with a CADe partner unlocks their entire hospital network. Post-FDA clearance, qualifying scans are reimbursable under CPT 0721T.
No workflow disruption · Embedded in CADe
CPT 0721T · post-FDA clearance
Pre-FDA Clearance · NLST held-out retrospective study · Results may differ in prospective clinical use
Three Ways We Help

One Integration. Better Screening Outcomes.

Oatmeal Health helps your team identify eligible patients, adds AI-powered risk stratification to every LDCT, and supports coordinated follow-up within your system.

Identify
ELIGIBLE PATIENTS
Close the screening gap

Oatmeal's AI-powered patient identification engine finds patients who meet USPSTF lung cancer screening criteria but have not yet been screened. No manual chart review required.

AI identifies 20-pack-year history patients 9x faster than manual chart review
91% scan agreement rate from shared decision-making visits
Supports annual re-screening adherence year after year
Stratify
NODULE RISK
AI-powered clinical decision support

LungAI adds a quantitative malignancy risk score to every eligible LDCT, helping radiologists and pulmonologists stratify nodules within Lung-RADS categories. Billable under CPT 0721T.

Integrates into your existing CADe workflow
CPT 0721T has an established CMS payment rate. Following FDA clearance, qualifying AI-assisted reads will be billable under this code.
Companion code CPT 0722T also available
Coordinate
FOLLOW-UP CARE
Keep patients on the right pathway

LungAI's risk stratification helps clinicians prioritize high-confidence findings for timely follow-up. Biopsy, PET-CT, and oncology referrals stay coordinated within your care team.

33–50% fewer false positive callbacks means fewer unnecessary procedures
High-confidence cases get acted on faster, improving time to treatment
Positions your center as a lung cancer center of excellence
For Radiologists

A Second Opinion That Fits in Your Existing Read

LungAI appears inside your current CADe viewer, next to the nodule you're already looking at. No new login, no new screen, just a 0–100 malignancy score and a billable PDF report in under 3 minutes.

For Radiologists
Built for how you already read

LungAI doesn't add a new screen, a new login, or a new step. The malignancy score appears directly next to each nodule's characteristics in your existing CADe viewer. You review the score, you make the decision.

<3 min
Average read time
33%
Fewer false positive callbacks
0.96
AUROC, NLST test set
$650
Billable per read, CPT 0721T
Score appears in your CADe viewer
The 0–100 malignancy score displays directly next to each nodule's characteristics inside your existing CADe platform. No new application to open.
Augments Lung-RADS, doesn't replace it
Use your Lung-RADS classification for guideline-concordant documentation. Use the LungAI score as a quantitative second opinion on borderline cases.
Accounts for nodule type, history, and prior scan
Solid, part-solid, and GGO nodules are scored differently. Patient age, sex, and pack-years are explicit model inputs. Prior LDCT is registered automatically when available.
Documented, billable second opinion
A PDF report with per-nodule score and probability curve is delivered inside PACS for documentation and CPT 0721T billing.
For Pulmonologists

A Number You Can Rank Your Nodule Backlog By

Lung-RADS gives you a category. LungAI gives you a continuous 0 to 100 score so you can triage within Lung-RADS 3 and 4A, down-triage low-risk indeterminate nodules, and get the right patients into your limited appointment slots first.

Prioritize who needs 3-month vs 6-month follow-up
LungAI's continuous score gives you finer ranking within Lung-RADS 3 and 4A, where clinical uncertainty is highest and appointment slots are most limited.
Reduce unnecessary bronchoscopies
A low LungAI score on an indeterminate nodule gives you quantitative support for a watchful waiting decision, reducing invasive procedures on benign lesions.
Longitudinal tracking built in
Prior LDCT is registered automatically. The score accounts for interval change without manual scan comparison.
Patient-specific, not population-based
A 6mm nodule in a 72-year-old 40 pack-year smoker is not the same clinical question as the same nodule in a 51-year-old. LungAI scores them differently.
For Pulmonologists
Risk-rank your nodule backlog

You have a growing list of indeterminate nodules and limited appointment slots. Lung-RADS gives you a category. LungAI gives you a number you can rank by, so the patients who need you most get seen first.

Decision support only. LungAI does not automate diagnosis or recommend treatment. The pulmonologist reviews the score and makes the clinical decision.
Ready to Deploy

Already in Your Network.
The Reimbursement Path Exists Today.

LungAI integrates into your existing CADe and PACS infrastructure with no IT project and no new hardware. CPT 0721T is already covered by Medicare and major commercial insurers.

Already embedded in your network
Integration
No integration needed
If your health system uses Coreline aView LCS or other major CADe software, you are already in the network.
Works with any CADe or PACS
Compatible with GE, Philips, and Siemens scanners and any PACS or CADe software. Available as cloud or Docker on-premise.
Zero burden on your IT team
HIPAA-secure deployment via your existing CADe integration. No new hardware, no new project, no added burden on radiology staff.
The reimbursement path exists today
Regulatory and Reimbursement
CPT 0721T: ~$650 per scan. CMS-priced AI-specific quantitative image analysis code. Covered by Medicare and major commercial insurers today.
510(k) Pre-Submission filed March 2026. Pivotal study at Mass General Brigham launching Q2 2026. FDA clearance target Q2 2027.
HEDIS quality mandate. Lung screening may become the 4th HEDIS quality measure, creating payer pressure to drive screening volume.
H.R. 1406. The Lung Cancer Screening and Prevention Act expands Medicare coverage of FDA-cleared screening tests.
The Stage Shift Argument

Earlier Detection Keeps Patients and Revenue in Your System

Every stage shift from IV to I saves a patient's life and cuts treatment costs by 4-6x. LungAI is designed to catch cancers while they're still surgical, the outcome that benefits patients and health systems equally.

Stage 5-year survival Est. life-months Cost multiplier Est. lifetime cost What this means
Stage I 70–90% ~60 months 1x (baseline) ~$200K Surgery + monitoring. Best outcome. LungAI target
Stage II 50–60% ~48 months 1.55x ~$310K More aggressive treatment. Chemo likely
Stage III 20–40% ~30 months 2.41x ~$480K Radiation + chemo + possible surgery
Stage IV 6–10% ~18 months 4–6x ~$800K–$1.2M Palliative focus. Immunotherapy. 85% diagnosed here
For a health system treating 100 lung cancer cases: shifting from Stage IV to Stage I detection saves an estimated $60M–$100M in treatment costs, while keeping those patients in your system for follow-up imaging and monitoring for years.
From the CEO of Coreline Soft

A Partnership Built Around Real Patients and Real Revenue

Coreline Soft, the CADe platform embedded in health systems nationwide, chose Oatmeal Health as its AI partner for lung cancer CADX Diagnostics.

"Our collaboration with Oatmeal Health extends beyond technology partnerships to secure insurance reimbursement-based revenue structures for actual US patients and establish leading technology in the lung cancer screening market. This demonstrates how AI diagnostic technology evolution can drive screening reimbursement structures, improved healthcare accessibility, and revenue model innovation."
KJ
Kim Jin-kook
CEO, Coreline Soft
For Imaging Centers and Health Systems

Ready to Put LungAI to Work in Your Center?

Whether you want to see it in your CADe viewer or build a full lung screening program, the next step takes less than 30 minutes.

For Radiologists and Department Heads
See LungAI in your workflow

Request a live demo showing how LungAI appears inside your CADe viewer, what the score looks like per nodule, and how the PDF report is delivered into PACS. Less than 30 minutes.

Request a workflow demo
For Imaging Program Leaders and CMOs
Build a lung screening program

Talk to our partnerships team about how Oatmeal Health drives scan referrals to your center, integrates LungAI into your CADe workflow, and enables your radiologists to bill CPT 0721T on eligible scans.

Talk to our team