Radiology · Chest X-ray enhancement, CAD and triage
ClearRead Xray
Riverain Technologies
Few AI chest-imaging products carry a regulatory record this long — a 2001 premarket approval for nodule CAD, four 510(k) generations, EU MDR certification in 2022, Health Canada licences and Australian TGA clearances dating to 2009. The independent evidence, however, is thinner and more cautionary than the footprint: reader studies found the nodule CAD too weak to stand alone (62 percent standalone sensitivity in one), and a 2021 Canadian study found bone-subtracted images the least accurate view for pneumothorax. Wide deployment across the US Veterans Health Administration and Department of Defense is vendor-reported. One mark: broad, durable regulatory presence; published evidence that argues for adjunct use, not more.
Performance Metrics
Clinical Evidence
The peer-reviewed record on ClearRead Xray's modules is independent, retrospective and candid about limits. For the nodule-CAD lineage, a 2017 Journal of Clinical Imaging Science study ran OnGuard 5.2 with SoftView 2.4A bone suppression over 100 CT-confirmed chest radiographs and measured standalone [[sensitivity]] of 62 percent and [[specificity]] of 58 percent, at 0.88 false positives per image — concluding that the CAD "does not qualify for a stand-alone standard of diagnosis" and belongs alongside critical radiological assessment. An earlier Journal of Digital Imaging pilot (2013) compared the same CAD across hardware dual-energy subtraction, SoftView software bone suppression and unprocessed films in 52 patients and found no significant difference between suppression methods — but flagged that low sensitivity (under 80 percent) and specificity (under 50 percent) "may limit their utility for clinical radiology". For the image-processing modules the picture is split by task. A 2021 Canadian Association of Radiologists Journal study of 202 patients with pneumothorax found the enhanced radiographs the most accurate view (AUC 0.96–0.99, above unprocessed baseline) but the bone-subtracted images the least accurate (AUC 0.89–0.97), with most false negatives — a direct caution that soft-tissue images must not be read in isolation for pneumothorax. The newest module, ClearRead Xray Pneumothorax, was cleared in 2022 on the strength of a multi-device validation the manufacturer describes as an independent third-party trial of more than 1,100 studies; no peer-reviewed publication of that validation was located in this review, so its performance figures are not reproduced here. No randomised or prospective outcome trial of any ClearRead Xray module was located.
| Study | Design | n | Sensitivity | Specificity | AUC | Published |
|---|---|---|---|---|---|---|
| Dellios N, et al. (independent, 100 CT-confirmed radiographs) | RetrospectiveRetrospective | 100 | 62% (CAD standalone) | 58% (CAD standalone) | — | J Clin Imaging Sci 2017; OnGuard 5.2 + SoftView 2.4A; 0.88 false positives/image |
| Independent reader study, 202 pneumothorax patients (4 readers) | RetrospectiveRetrospective | 202 | not reported as sens/spec | not reported as sens/spec | 0.96–0.99 enhanced vs 0.89–0.97 bone-subtracted | Can Assoc Radiol J 2021; enhanced images most accurate for pneumothorax, bone-subtracted least |
| Independent pilot, 27 malignant-nodule patients + 25 controls | RetrospectiveRetrospective | 52 | <80% (all methods) | <50% (all methods) | — | J Digit Imaging 2013; OnGuard 5.2 across dual-energy vs SoftView vs unprocessed — low values 'may limit utility for clinical radiology' |
Clinical Pulse
Verified clinician sentiment
Verified clinician reviews launching soon · Apply to contribute →
Reviews are signed by clinicians verified against their regulator's public register.
Inside the algorithm
Editorial featureHow ClearRead Xray processes a chest film.
Five stages — from raw input to verdict — drawn from manufacturer documentation and the public regulatory record.
- INGEST
- NORMALISE
- DETECT
- LOCALISE
- VERDICT
Stage 01 · INGEST
A standard frontal chest radiograph arrives from the modality or PACS.
ClearRead Xray takes an ordinary digital frontal chest radiograph — no dual-energy acquisition, no second exposure, no added dose. The pneumothorax triage module accepts upright and portable digital radiographs; it is not indicated for scanned film.
The original image is never altered; every module output is an additional series or a worklist signal.
Input
Chest radiograph (DR)
Inference
Per-image
Inside the Auris+ Listing
Five more sections complete this device’s Auris+ Listing.
Decision Ledger
ProPro unlocks a private, cross-vendor log of every case you read on this device — what the AI called, what you concluded, and a one-line reason if you overrode it. Ready for the EU AI Act's deployer logging obligations when they land in 2028.
Clinical Evidence Deep Dive
ProPro unlocks the structured clinical-evidence summary — study count, target patient population, and a tabular accuracy-metrics view drawn from peer-reviewed sources.
Peer-Reviewed Publications
ProPro unlocks the curated peer-reviewed publication list with PubMed cross-links — the citation backbone of every editorial verdict.
Post-Market & Regulatory Conditions
ProPro unlocks the post-market surveillance summary, recall record, and the conditions of approval that bound real-world use.
AI Algorithm Version History
ProPro unlocks the chronological record of algorithm version changes — what changed when, drawn from manufacturer changelogs and regulatory filings.
Regulatory Approvals
78227
Safety Record
No recall or FDA safety communication specific to ClearRead Xray was found in public reporting as of July 2026 — noting that MAUDE and the FDA enforcement database could not be queried directly from this environment, so this is "none found", not an exhaustive audit. The principal documented clinical risk is task-specific: the 2021 Canadian reader study found bone-subtracted (soft-tissue) images the least accurate view for detecting pneumothorax, with most false negatives — the soft-tissue image is an adjunct to the standard radiograph, never a replacement. The pneumothorax triage module is notification-only: it reprioritises worklists, does not mark findings, and a silent result is not an exclusion of pneumothorax.
Intended Use & Indications
ClearRead Xray is not one algorithm but a module family that has accreted around two decades of chest-radiograph work. The oldest lineage is a premarket approval, not a 510(k): RapidScreen RS-2000 (P000041, approved 2001), a computer-aided detection system for solitary pulmonary nodules of 9–30 mm on digitised frontal chest radiographs, which evolved through supplements into the OnGuard and ClearRead Detect nodule-CAD products. The commercial centre of the modern family is software bone suppression (SoftView, K092363): a single-exposure soft-tissue image that removes rib and clavicle shadow without dual-energy hardware or added dose. Around it sit temporal comparison (DeltaView/Compare, K111776), tube-and-line and general enhancement (+Confirm, K123526), and — the family's first [[deep-learning]]-era triage clearance — ClearRead Xray Pneumothorax (K213566, 2022), a computer-aided triage and notification device that flags cases with suspected pneumothorax of 5 mm or larger for worklist prioritisation on upright and portable digital radiographs. Every module is adjunctive or notification-only: none makes a diagnosis, and the pneumothorax module does not mark the finding on the image.