Study of bladdeR Cancer Detection in Standard White Light Versus AI-Supported Endoscopy-02

Status

Enrolling by invitation

Phases

Study type

Interventional

Source

ClinicalTrials.gov

Registry ID

NCT06780358

Acronym

RAISE02

Enrollment

Registered

2025-01-17

Start date

2024-11-20

Completion date

2025-05-31

Last updated

2025-01-17

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Bladder Cancer

Brief summary

This study is being conducted to investigate if an artificial intelligence support tool is non-inferior in detecting bladder cancer compared to the traditional method, standard white light cystoscopy (WLC). The researchers will compare how well the artificial intelligence tool and WLC perform in detecting bladder cancer through a controlled, organized testing process.

Detailed description

This clinical investigation aims to confirm that an artificial intelligence model utilizing a Convolutional Neural Network (CNN) can achieve sensitivity in detecting bladder cancer that is non-inferior to traditional white light cystoscopy (WLC) in a randomized controlled trial. The investigational artificial intelligence device leverages the advanced capabilities of CNNs, a type of deep learning model designed to analyze visual imagery with high precision.

Interventions

DEVICEAI supported detection of bladder cancer

AI-model-supported detection of bladder cancer during white light cystoscopy

Study design

Allocation

RANDOMIZED

Intervention model

PARALLEL

Primary purpose

OTHER

Masking

NONE

Intervention model description

Premarket Confirmatory, National, single-center, randomized, prospective, non-inferiority trial

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

Inclusion criteria

* Men and women adults, age \>18 years old Suspicion of primary or recurrent bladder cancer Willingness to sign the Informed Consent Form (ICF) for the CI Ability to comprehend the oral and written Patient Information Leaflet (PIL)

Exclusion criteria

* Not able or willing to sign the Informed Consent Form

Design outcomes

Primary

Measure	Time frame	Description
Sensitivity of standard WLC compared to WLC assisted by the AI model evaluated with a non-inferiority margin of 5%.	7 month	To determine whether the AI model is non-inferior with regards to sensitivity compared to standard WLC in a randomized controlled trial.

Countries

Denmark

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026