AI Assistance for Detecting Active Bleeding During DSA Procedures

Real-Time DSA-VDet Assistance for Detecting Active Bleeding Across Multiple Anatomical Regions: A Multicenter, Prospective, Randomized, Open-Label, Blinded-Endpoint Controlled Trial

Clinically, DSA-VDet can continuously indicate suspected bleeding regions throughout a complete angiographic sequence and provide a second-reader opinion to the operator. It is expected to reduce the time required for frame-by-frame review and localization of culprit vessels, reduce missed detection of small, multiple, or unusually located bleeding sites, and improve consistency among physicians with different levels of experience. Faster culprit-vessel localization may also reduce repeat angiography, radiation exposure, and unnecessary superselective catheterization. These potential benefits will be tested in the prospective randomized trial; the study does not assume that the model will necessarily improve clinical outcomes. From a translational perspective, the study will establish a standardized temporal DSA database spanning multiple centers, devices, and anatomical regions, together with bleeding-site annotation standards, a model suitable for real-time deployment, and a pathway for clinical evaluation. These resources may provide a reproducible technical foundation for regional collaboration in emergency interventional care and AI-assisted interpretation in lower-resource hospitals.

The core value of this study is therefore to address the 'single-region, weak-temporal, algorithm-centered, clinically under-evaluated' limitations of existing models. Using multicenter DSA videos from multiple anatomical regions, the study will leverage contrast kinetics and motion information to improve detection of small bleeding sites and will progress from retrospective validation through controlled physician interpretation to a prospective randomized trial, providing a continuous evaluation from technical performance to clinical benefit.

Study Overview

• Status: Not yet recruiting
• Conditions: Hemorrhage; Bleeding; Acute Bleeding; AI (Artificial Intelligence); DSA
• Intervention / Treatment: Device: DSA-VDet v1.0

• Study Type: Interventional
• Enrollment (Estimated): 1324
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Jian Lu; Phone Number: 13616106021; Email: lujian43307131@126.com

Study Locations

• China
  • Jiangsu
    • Nanjing, Jiangsu, China, 213003
      • Zhongda Hospital
      • Contact: Jun-Hao Mei; Phone Number: 15052007938; Email: jh_mei240225@126.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• age 18 years or older;
• suspected acute active bleeding in an intracranial, solid-organ, pelvic, gastrointestinal, respiratory, great-vessel, or other relevant anatomical region requiring DSA-guided interventional diagnosis or treatment;
• clinical suitability for the planned DSA procedure;
• written informed consent from the patient or legally authorized representative before randomization whenever feasible, or eligibility for an ethics-approved deferred-consent pathway at an activated site when prior consent is impossible and treatment cannot be delayed.

Exclusion Criteria:

• a history of severe allergic reaction to iodinated contrast medium or related medications that precludes the planned procedure;
• severe coagulopathy or a platelet count below 50x10^9/L when interventional treatment is considered clinically inappropriate;
• severe cardiac or pulmonary insufficiency that makes the planned procedure unsafe;
• pregnancy or breastfeeding;
• severe renal insufficiency or another condition that may substantially increase interventional risk;
• inability to complete angiography safely according to the required workflow despite clinically appropriate support;
• any other circumstance that, in the investigator's judgment, makes participation unsuitable. Impaired decision-making capacity alone will not be an exclusion if consent can be obtained from a legally authorized representative or through the ethics-approved deferred-consent pathway.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: DSA-VDet-assisted group; During DSA acquisition, DSA-VDet v1.0 will perform continuous frame-by-frame inference and continuously display suspected bleeding regions, confidence scores, and relevant frame indices. The operator will retain responsibility for the final diagnosis, selection of culprit vessels, and all angiographic and embolization decisions.	Device: DSA-VDet v1.0; During DSA acquisition, DSA-VDet v1.0 will perform continuous frame-by-frame inference and continuously display suspected bleeding regions, confidence scores, and relevant frame indices. The operator will retain responsibility for the final diagnosis, selection of culprit vessels, and all angiographic and embolization decisions.
No Intervention: Conventional-interpretation group; The operator will perform frame-by-frame interpretation using the conventional DSA equipment and established workflow, without access to DSA-VDet output. Images may undergo offline model analysis after completion of the index procedure for exploratory purposes, but those results must not be available for the index clinical decision.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
the time from the start of the first diagnostic DSA acquisition to achievement of the correct diagnostic endpoint	To determine whether real-time DSA-VDet v1.0 assistance shortens the time from the start of the first diagnostic DSA acquisition to achievement of the correct diagnostic endpoint, compared with conventional interpretation.	Upon achievement of the correct diagnostic endpoint, an average of 1 hour

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
the detection and localization performance of DSA-VDet	To evaluate the detection and localization performance of DSA-VDet in DSA sequences acquired across multiple anatomical regions; to assess its effects on interpretation accuracy, interpretation time, and interobserver agreement among interventional physicians with different levels of experience; and to compare total procedure duration, technical embolization success, repeat angiographic acquisitions, radiation exposure, contrast-medium volume, intraprocedural complications, and adverse events through postprocedure day 30 between the randomized groups.	Upon achievement of the correct diagnostic endpoint, an average of 1 hour
effects on interpretation accuracy	To evaluate the detection and localization performance of DSA-VDet in DSA sequences acquired across multiple anatomical regions; to assess its effects on interpretation accuracy, interpretation time, and interobserver agreement among interventional physicians with different levels of experience; and to compare total procedure duration, technical embolization success, repeat angiographic acquisitions, radiation exposure, contrast-medium volume, intraprocedural complications, and adverse events through postprocedure day 30 between the randomized groups.	Upon achievement of the correct diagnostic endpoint, an average of 1 hour
interpretation time	To evaluate the detection and localization performance of DSA-VDet in DSA sequences acquired across multiple anatomical regions; to assess its effects on interpretation accuracy, interpretation time, and interobserver agreement among interventional physicians with different levels of experience; and to compare total procedure duration, technical embolization success, repeat angiographic acquisitions, radiation exposure, contrast-medium volume, intraprocedural complications, and adverse events through postprocedure day 30 between the randomized groups.	Upon achievement of the correct diagnostic endpoint, an average of 1 hour
interobserver agreement among interventional physicians with different levels of experience	To evaluate the detection and localization performance of DSA-VDet in DSA sequences acquired across multiple anatomical regions; to assess its effects on interpretation accuracy, interpretation time, and interobserver agreement among interventional physicians with different levels of experience; and to compare total procedure duration, technical embolization success, repeat angiographic acquisitions, radiation exposure, contrast-medium volume, intraprocedural complications, and adverse events through postprocedure day 30 between the randomized groups.	Upon achievement of the correct diagnostic endpoint, an average of 1 hour

Collaborators and Investigators

• Sponsor: Zhongda Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): October 1, 2026
• Primary Completion (Estimated): October 1, 2027
• Study Completion (Estimated): December 30, 2027

Study Registration Dates

• First Submitted: September 2, 2026
• First Submitted That Met QC Criteria: September 11, 2026
• First Posted (Actual): September 17, 2026

Study Record Updates

• Last Update Posted (Actual): September 17, 2026
• Last Update Submitted That Met QC Criteria: September 11, 2026
• Last Verified: September 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathologic Processes; Pathological Conditions, Signs and Symptoms; Hemorrhage
• Other Study ID Numbers: DSA-VDet

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No