NaviCam ProScan cut capsule reading time and found more lesions

In the ARTIC study that FDA reviewed, readers using NaviCam ProScan took 3 minutes and 50 seconds per video, against 33 minutes and 42 seconds. They also found lesions in more patients.

  • 2 an organization

    AI-assisted reads took 3 minutes and 50 seconds on average, against 33 minutes and 42 seconds, with diagnostic yield of 73.7% against 62.4%.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Standard reading of the same videos without AI at the enrolling center. Measured.

Without the system
Mean reading time of 33 minutes and 42 seconds, diagnostic yield 62.4%
With it
Mean reading time of 3 minutes and 50 seconds, diagnostic yield 73.7%
The system’s part
Standard and AI-assisted reads of the same videos were compared against an expert board, so the change is attributed to AI assistance. Different readers did the two reads, and the standard read came first.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
NaviCam ProScan
Made by
Ankon Technologies Co., Ltd.
Used by
Seven European centers in the prospective ARTIC study (22 capsule endoscopy readers)
Where
Seven centers in Italy, France, Germany, Hungary, Spain, Sweden and the United Kingdom
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings, Cross-border records
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Food and Drug Administration, Center for Devices and Radiological Health. De Novo classification request for NaviCam ProScan (DEN230027): decision summary. Granted 2023-12-12.

    At per-patient analysis, diagnostic yields for P1+P2 lesions were 62.4% (95% CI: 53.6% - 70.7%) and 73.7% (95% CI: 65.3% - 80.9%), for standard readings and AI+Physician readings, respectively (p=0.015).

Details

AI system

Workflow

The software marked suspected lesions with bounding boxes and could show only the flagged images. Readers with over 500 capsule readings each reviewed the AI output and made their own diagnoses.

Follow-up

Conditions for replication

Videos come from the NaviCam Small Bowel Capsule Endoscopy System. The clinician reviews the entire video as clinically appropriate.

Entry details

Sector

Healthcare.

Purpose

Ankon Technologies built NaviCam ProScan to help clinicians read capsule endoscopy videos of the small bowel faster by marking images with suspected lesions.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). NaviCam ProScan cut capsule reading time and found more lesions (AIBD-0775). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0775.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions