Intraoperative Ultrasound for Brain Tumor Surgery Enhanced by AI

NCT07376304 | Not Yet Recruiting Phase 3

• 1 other identifier: PI-25-191-H
• Study Type: interventional
• Target: 100
• Locations: 0 countries
• Sites: N/A

Brief Summary

Intraoperative ultrasound is a versatile, low-cost imaging tool that has been shown to improve safety and efficacy in brain tumor surgery. However, its widespread adoption remains limited due to operator dependency, the complexity of image interpretation, the presence of artifacts, and a restricted field of view. This project aims to prospectively evaluate, in a multicenter and non-randomized setting, a prototype real-time deep learning-based segmentation model for brain tumor delineation in intraoperative ultrasound. The model is designed to facilitate the identification of tumor tissue during surgery, potentially enhancing intraoperative decision-making and surgical precision. By increasing the precision and accessibility of ioUS, this innovation is expected to enable safer and more complete resections, with the potential to improve both survival and quality of life for patients with brain tumors.

Conditions

Brain Tumor Adult

Keywords

brain tumor; glioma; glioblastoma; low-grade glioma; high-grade glioma; ious; computer vision; AI; ultrasound

Outcome Measures

Primary Outcomes (1)

• Diagnostic performance of BrainUS-AI for residual tumor detection at end of resection

  Residual tumor presence/absence will be determined by the BrainUS-AI segmentation overlay during the final intraoperative ultrasound acquisition (when the surgeon considers the resection complete). This binary classification (residual present/absent) will be compared against early postoperative MRI when available (reference standard), and agreement with the surgeon's intraoperative assessment will also be recorded. Diagnostic performance will be reported as sensitivity, specificity, PPV, and NPV with 95% confidence intervals, and concordance will be assessed using Cohen's kappa.

  During surgery (baseline, during resection, and end of resection), with the primary assessment at the end of resection on the final intraoperative ultrasound acquisition.

Study Arms (1)

Real-time AI-assisted intraoperative ultrasound segmentation

EXPERIMENTAL

Participants undergoing standard-of-care brain tumor resection with intraoperative ultrasound (ioUS) will use a prototype real-time deep learning-based segmentation system that overlays automated tumor delineation on the live ultrasound feed during surgery. The tool is used as an adjunct to routine intraoperative imaging and does not mandate changes to the surgical strategy; the surgeon remains fully responsible for intraoperative decision-making. Technical performance (e.g., segmentation accuracy, latency/FPS, operational stability), feasibility/workflow impact, residual tumor detection agreement, and surgeon-reported usability will be prospectively collected across participating centers.

Device: BrainUS-AI real-time intraoperative ultrasound segmentation system

Interventions

BrainUS-AI real-time intraoperative ultrasound segmentation system DEVICE

A prototype AI-based device (software system) that performs real-time deep learning segmentation of brain tumor tissue on intraoperative ultrasound (ioUS) and displays the segmentation as an overlay on the live ultrasound feed during surgery. The system is used as an adjunct to standard-of-care ioUS without mandating any change to the planned surgical strategy; intraoperative decisions remain under the surgeon's responsibility. System logs capture processing performance (e.g., FPS, end-to-end latency, operational uptime) and outputs used for subsequent technical validation and workflow/usability assessments.

Real-time AI-assisted intraoperative ultrasound segmentation

Eligibility Criteria

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

You may qualify if:

• Age ≥ 18 years.
• Scheduled for craniotomy and resection of a brain tumor with ioUS planned as part of the standard surgical workflow.
• Preoperative MRI available for surgical planning.
• Ability to obtain informed consent from the patient or legal representative.

You may not qualify if:

• Inadequate ioUS image acquisition due to technical failure or intraoperative complications unrelated to the tumor.

Sponsors & Collaborators

• Hospital del Rio Hortega: lead
• Department of Neurosurgery, Bratislava University Hospital: collaborator

Related Publications (2)

• Cepeda S, Esteban-Sinovas O, Singh V, Shetty P, Moiyadi A, Dixon L, Weld A, Anichini G, Giannarou S, Camp S, Zemmoura I, Giammalva GR, Del Bene M, Barbotti A, DiMeco F, West TR, Nahed BV, Romero R, Arrese I, Hornero R, Sarabia R. Deep Learning-Based Glioma Segmentation of 2D Intraoperative Ultrasound Images: A Multicenter Study Using the Brain Tumor Intraoperative Ultrasound Database (BraTioUS). Cancers (Basel). 2025 Jan 19;17(2):315. doi: 10.3390/cancers17020315.

  PMID: 39858097 RESULT

• Cepeda S, Esteban-Sinovas O, Romero R, Singh V, Shett P, Moiyadi A, Zemmoura I, Giammalva GR, Del Bene M, Barbotti A, DiMeco F, West TR, Nahed BV, Arrese I, Hornero R, Sarabia R. Real-time brain tumor detection in intraoperative ultrasound: From model training to deployment in the operating room. Comput Biol Med. 2025 Jul;193:110481. doi: 10.1016/j.compbiomed.2025.110481. Epub 2025 May 30.

  PMID: 40449046 RESULT

MeSH Terms

Conditions

Brain Neoplasms; Glioma; Glioblastoma

Condition Hierarchy (Ancestors)

Central Nervous System Neoplasms; Nervous System Neoplasms; Neoplasms by Site; Neoplasms; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Neoplasms, Neuroepithelial; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms by Histologic Type; Neoplasms, Glandular and Epithelial; Neoplasms, Nerve Tissue; Astrocytoma

Central Study Contacts

Santiago Cepeda, MD., Ph.D.

CONTACT

+34651035158; scepedac@saludcastillayleon.es

Study Design

• Study Type: interventional
• Phase: phase 3
• Allocation: NA
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Staff Neurosurgeon

Study Record Dates

• First Submitted: January 22, 2026
• First Posted: January 29, 2026
• Study Start: March 1, 2026
• Primary Completion (Estimated): December 1, 2027
• Study Completion (Estimated): June 1, 2028
• Last Updated: January 29, 2026

Record last verified: 2026-01