- All Devices
- Pathology
- Galen Prostate / Galen Breast
Pathology · Computational pathology cancer detection
Galen Prostate / Galen Breast
Ibex Medical Analytics
Galen Prostate was the first standalone AI cancer-diagnostics product CE-marked under the IVDR, and its 2020 Lancet Digital Health validation — 98.46 percent sensitivity, 97.33 percent specificity, AUC 0.991 on UPMC prostate biopsies — remains among the strongest pathology-AI results published. Three years of real-world deployment at a Puerto Rico laboratory, spanning more than 122,000 slides, support that the performance holds in routine use. The honest limits: the US FDA clearance covers only a prostate second-read tool, the pivotal evidence is manufacturer-authored, and IVDR risk classes for the modules are not publicly confirmed — which keeps the platform at two marks.
Performance Metrics
Clinical Evidence
Galen Prostate's pivotal evidence is a manufacturer-authored blinded clinical validation and deployment study (Pantanowitz, Dhir, et al., Lancet Digital Health 2020;2:e407–e416), conducted on prostate core-needle biopsy whole-slide images from UPMC. The algorithm detected cancer with 98.46 percent sensitivity and 97.33 percent specificity at an AUC of 0.991, and went beyond detection to report Gleason grading, perineural invasion and tumour sizing — clinically necessary elements of a prostate pathology report. The numbers are among the highest reported in computational pathology, but the study was developed and funded by the manufacturer, and the predicate studies for Paige Prostate (a separate product) should not be read across to Galen. Independent evidence comes from a three-year real-world series at CorePlus, a Puerto Rico laboratory (Journal of Pathology Informatics 2024): in a validation phase Galen Prostate detected cancer with 96.6 percent sensitivity and 96.7 percent specificity, and across more than 122,000 slides and roughly 9,200 cases over three years of routine second-read use the algorithm produced an overall change in diagnosis ("AI Impact") of about 1.8 percent — a measure of how often the tool surfaced something the pathologist's first read had not captured. This is one of the longer real-world deployment records for a pathology-AI product and lends external support to the pivotal performance. The boundaries are worth stating plainly. The strongest, most independent evidence concerns the prostate algorithm; primary-validation publications for the breast and gastric modules were not located in PubMed in this review. The US FDA footprint is a single clearance for a prostate second-read tool, narrower than the CE-marked primary-diagnosis indication. Galen is assistive throughout — it raises alerts and heatmaps, and the pathologist remains the diagnostician.
| Study | Design | n | Sensitivity | Specificity | AUC | Published |
|---|---|---|---|---|---|---|
| Pantanowitz L, Dhir R, et al. (blinded clinical validation, UPMC) | ProspectiveProspective | 0 | 98.46% | 97.33% | 0.991 | Lancet Digital Health, Aug 2020; also reports Gleason grading, PNI, sizing |
| CorePlus real-world deployment (Puerto Rico) | RetrospectiveRetrospective | 9,200 | 96.6% | 96.7% | — | J Pathology Informatics, 2024; >122,000 slides over 3 years, AI Impact ~1.8% |
Clinical Pulse
Verified clinician sentiment
Verified clinician reviews launching · Apply to contribute →
Reviews are signed by clinicians verified against their regulator's public register.
Inside the Auris+ Listing
Six more sections complete this device’s Auris+ Listing.
Inside the algorithm
ProPro unlocks the five-stage editorial walkthrough of how this device's AI reaches a verdict — model architecture, training data, inference latency, and where the clinician stays in the loop.
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
K241232
Class II
Safety Record
No Ibex device recall or FDA safety communication was identified in publicly available sources as of June 2026; this is "none found in public reporting" rather than an exhaustive MAUDE audit, which could not be queried directly from this environment. A name-collision caveat applies: a 2012 MAUDE event filed under "IBEX" predates Ibex Medical Analytics (founded 2016) and belongs to a different device — it must not be attributed to this product. As a second-read alerting and decision-support overlay the software does not remove slides from the pathologist's queue or issue a primary diagnosis, which limits its harm surface; the principal documented risk is reliance on the absence of an alert, since published sensitivity, while high, is not perfect.
Intended Use & Indications
Ibex's Galen platform analyses digitised [[whole-slide-image]] scans of needle-core biopsies and applies deep-learning algorithms to detect cancer, grade it, and surface clinically relevant features. The US FDA-cleared product — Ibex Prostate Detect, cleared under the name Galen Second Read (K241232, 21 CFR 864.3750, product code QPN, Class II) — is a second-read application: after the pathologist's primary diagnosis it analyses the prostate core-needle-biopsy slides and raises case- and slide-level alerts with a heatmap when it identifies tissue suspicious for cancer that may have been missed, without making a primary diagnosis. In Europe, Galen Prostate is CE-marked under the IVDR to support pathologists in the primary diagnosis of prostate biopsies; Galen Gastric was certified under the legacy IVDD and additional modules (Breast, HER2) are at varying certification stages. The software is assistive, not autonomous: the reporting pathologist makes every diagnostic and grading decision.