CT scans may carry a second clue.
A peer-reviewed study tested whether EAGLE, an AI system, could flag esophageal cancer on non-contrast chest CT scans people received for other reasons.
- Maturity
- Demonstrated, stage 3 of 4
- Support
- 1 source · paper
- Evidence detail
- How we know ↓
Esophageal cancer is often difficult to see on ordinary chest CT and can be diagnosed after disease has advanced.
Chest CT scans taken for other reasons contain the esophagus, but subtle lesions can be overlooked and endoscopy is not performed for everyone.
A deep-learning system analyzed non-contrast chest CT scans for signs of esophageal cancer and high-grade intraepithelial neoplasia, including scans acquired for other reasons.
What was shown, and what wasn’t
Shown
Across 11,466 patients at eight external centres, EAGLE flagged 90.0% of known cancers (sensitivity) and correctly left 98.5% of patients without cancer unflagged (specificity). It flagged 60.1% of stage I cancers and 52.5% of precancerous lesions. In a separate prospective cohort of 17,446 patients at one hospital, it flagged 87.8% of known cancers. Of 90 alerts, 38 were confirmed malignant—36 cancers and two high-grade intraepithelial neoplasias—so 42.2% of alerts were confirmed malignant (positive predictive value).
Not shown · limits
- The prospective cohort had incomplete follow-up: among 52 people without confirmed malignancy, 28 had other findings, 19 were negative or had no symptoms, and five were lost to follow-up.
- The 10,959-person low-dose CT cohort was retrospective and single-site. Eight people were flagged, one cancer was confirmed, and five did not undergo endoscopy, so its 12.5% positive predictive value is not a complete screening outcome.
- External sensitivity for stage I cancer was 60.1% and for precancerous lesions was 52.5%; the study does not show reduced mortality or better patient outcomes.
- The authors call for broader international validation. DAMO Academy (Hupan Lab) was the main funder, and eight authors reported Alibaba employment and stock compensation.
Bright editorial interpretation
If broader validation supports it, opportunistic review could draw attention to a hard-to-see disease on CT scans people already receive, without adding another scan.
Still open
Will performance hold across more countries, cancer subtypes, scanners and care settings?
Can a complete follow-up pathway show whether alerts lead to earlier diagnosis and better outcomes without excessive procedures?
How should clinicians manage uncertain positives and precancerous lesions?
Keep the evidence together · share a card
BRIGHT / EVIDENCE TO KEEP
CT scans may carry a second clue.
Possible benefit · Bright interpretation
If broader validation supports it, opportunistic review could draw attention to a hard-to-see disease on CT scans people already receive, without adding another scan.
Documented result · source-backed
Across 11,466 patients at eight external centres, EAGLE flagged 90.0% of known cancers (sensitivity) and correctly left 98.5% of patients without cancer unflagged (specificity). It flagged 60.1% of stage I cancers and 52.5% of precancerous lesions. In a separate prospective cohort of 17,446 patients at one hospital, it flagged 87.8% of known cancers. Of 90 alerts, 38 were confirmed malignant—36 cancers and two high-grade intraepithelial neoplasias—so 42.2% of alerts were confirmed malignant (positive predictive value).
Limits & unknowns
The prospective cohort had incomplete follow-up: among 52 people without confirmed malignancy, 28 had other findings, 19 were negative or had no symptoms, and five were lost to follow-up.
The 10,959-person low-dose CT cohort was retrospective and single-site. Eight people were flagged, one cancer was confirmed, and five did not undergo endoscopy, so its 12.5% positive predictive value is not a complete screening outcome.
External sensitivity for stage I cancer was 60.1% and for precancerous lesions was 52.5%; the study does not show reduced mortality or better patient outcomes.
The authors call for broader international validation. DAMO Academy (Hupan Lab) was the main funder, and eight authors reported Alibaba employment and stock compensation.
Will performance hold across more countries, cancer subtypes, scanners and care settings?
Can a complete follow-up pathway show whether alerts lead to earlier diagnosis and better outcomes without excessive procedures?
How should clinicians manage uncertain positives and precancerous lesions?
Evidence state: Demonstrated. Source check: 2026-09-25. A source check is not independent replication.
Large-scale esophageal cancer screening through noncontrast computed tomography and artificial intelligence · Nature Medicine: https://www.nature.com/articles/s41591-026-04656-4
https://brightaifuture.com/discoveries/eagle-esophageal-ct
How we know1 source · checked 2026-09-25 · no corrections
Original sources
Institutions: Sichuan Cancer Hospital · Shanghai Institution of Pancreatic Disease
- Maturity
- Demonstrated
- Claim confidence
- high
- Source published
- 2026-09-22
- Captured
- 2026-09-25
- Last source review
- 2026-09-25
- Editorial method
- AI-assisted source review
- Place / relevance
- Multicentre study · global-study
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
2026-09-25 · Published “CT scans may carry a second clue.” with its source date, evidence state and material limitations explicit.
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.