Exploration of Novel AI-enabled Blue Light Enhanced Cystoscopy

NCT ID: NCT07144319

Last Updated: 2025-12-26

Basic Information

• Recruitment Status: NOT_YET_RECRUITING
• Total Enrollment: 500 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2026-01-31
• Study Completion Date: 2027-12-31

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

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: PROSPECTIVE

Study Groups

BLC patients

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

No interventions assigned to this group

Eligibility Criteria

Inclusion Criteria

• 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

Exclusion Criteria

• None

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Photocure

INDUSTRY

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Central Contacts

Kristine Young-Halvorsen, PhD

Role: CONTACT

Phone: 004722062210

Email: research@photocure.com

Other Identifiers

PCAIX01/25

Identifier Type: -

Identifier Source: org_study_id