Exploration of Novel AI-enabled Blue Light Enhanced Cystoscopy

NCT07144319 | Recruiting

• 1 other identifier: PCAIX01/25
• Study Type: observational
• Target: 500
• Locations: 2 countries
• Sites: 2

Brief Summary

Blue light cystoscopy (BLC) is a diagnostic procedure in bladder cancer where the inside of the bladder is observed with a camera to detect bladder lesions. Unlike regular white light cystoscopy, blue light cystoscopy makes use of a drug that induces fluorescence under blue light preferentially in neoplastic and malignant cells that helps visualize bladder lesions during the cystoscopic procedure. Blue light cystoscopy has shown to improve detection of bladder cancer. Cystoscopy, including blue light cystoscopy, is a procedure involving assessment of the visual appearance of the bladder surface, leading to decisions of taking biopsies, remove suspicious areas and assign treatment options. The assessment is subjective and has a large operator variability. These shortcomings show an opportunity for computer aided detection (CADe) medical device to add value to both clinicians and patients. The objective of this data collection study is to build a high-quality, diverse data set of video, image recordings and relevant clinical data from BLC procedures performed as part of routine clinical practice to train a computer-aided detection (CADe) algorithm for real- time lesion detection during cystoscopy. The data will be used to support the training, non-clinical technical development and testing of such AI algorithms for use during cystoscopy and to provide documentation needed for training of such algorithms and to assist in guiding future validation of such algorithms. Exploratory purposes of the study is to use data to explore future AI algorithms in bladder cancer, such as computer-aided diagnosis (CADx) AI algorithms, image enhancement and cystoscopy improvement algorithms, including bladder mapping, tumor visualization, cystoscopy documentation, and combination models of image and clinical data including risk assessment, clinical outcomes, and disease modeling

Conditions

Bladder Cancer; Non-muscle Invasive Bladder Cancer

Keywords

bladder cancer; artificial intelligence; cystoscopy

Outcome Measures

Primary Outcomes (1)

• Video and image collection

  To collect videos, images and relevant clinical data from BLC procedures performed as part of clinical practice. The data will be used to explore the potential of a BLC-enabled AI algorithm for lesion detection of bladder cancer.

  1 day

Study Arms (1)

BLC patients

Adult, consenting patients scheduled for BLC as part of clinical practice.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Routine clinical practice patients scheduled for BLC

You may qualify if:

• Age 18 or older
• Written informed consent, approved by relevant IRB/IEC, signed
• Hexvix/Cysview has been prescribed in the usual manner in accordance with the terms of the marketing authorization (see Appendix B)
• Physician has planned to do a blue light cystoscopy on the patient and to obtain biopsies, if clinically indicated, of suspicious lesions with video confirmation.
• Patient has not previously taken part in this study

You may not qualify if:

• None

Sponsors & Collaborators

• Photocure: lead

Study Sites (2)

Rutgers Cancer Institute

New Brunswick, New Jersey, 08901, United States

RECRUITING

Oslo University Hospital

Oslo, Norway

RECRUITING

MeSH Terms

Conditions

Urinary Bladder Neoplasms; Non-Muscle Invasive Bladder Neoplasms

Condition Hierarchy (Ancestors)

Urologic Neoplasms; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Urinary Bladder Diseases; Urologic Diseases; Male Urogenital Diseases; Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type

Central Study Contacts

Kristine Young-Halvorsen, PhD

CONTACT

004722062210; research@photocure.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 20, 2025
• First Posted: August 27, 2025
• Study Start: March 25, 2026
• Primary Completion (Estimated): December 1, 2027
• Study Completion (Estimated): December 1, 2027
• Last Updated: April 1, 2026

Record last verified: 2026-03

Data Sharing

• IPD Sharing: Will not share

Locations

NO (1); US (1)