Supramarginal Resection in Glioblastoma Guided by Artificial Intelligence

NCT05735171 | Completed

• 1 other identifier: 22-PI208
• Study Type: interventional
• Target: 20
• Locations: 1 country
• Sites: 1

Brief Summary

Glioblastomas are the most common and poorly prognostic primary brain neoplasms. Despite advances in surgical techniques and chemotherapy, the median survival time for these patients remains less than 15 months. This highlights the need for more effective treatments and improved prognostic tools. The globally accepted surgical strategy currently consists of achieving the maximum safe resection of the enhancing tumor volume. However, the non-enhancing peritumoral region contains viable cells that cause the inevitable recurrence that these patients face. Clinicians currently lack an imaging tool or modality to differentiate neoplastic infiltration in the peritumoral region from vasogenic edema. In addition, it is not always feasible to include all the T2-FLAIR signal alterations surrounding the enhancing tumor in the surgical planning due to the proximity of eloquent areas and the higher risk of postoperative deficits. However, the investigators have developed a model to predict regions of recurrence based on machine learning and MRI radiomic features that have been trained and evaluated in a multi-institutional cohort. The investigators aim to analyze whether an adjusted supramarginal resection guided by these new recurrence probability maps improves survival in selected patients with glioblastoma.

Conditions

Glioblastoma

Outcome Measures

Primary Outcomes (2)

• Feasibility using eligibility

  Among all screened patients, the proportion of patients who meet the eligibility criteria

  Screening/Enrollment

• Feasibility using the proportion of consent

  Among all screened patients, the proportion of patients consenting to participate

  Screening/Enrollment

Secondary Outcomes (6)

• Efficacy using overall survival

  From date of surgery until the date of death from any cause, assessed up to 36 months

• Efficacy using progression-free survival

  From date of surgery until the date of first documented progression, assessed up to 36 months

• Safety using the neurological function

  30 days

• Safety using global disability

  30 days

• Extent of resection

  < 72 hours after surgery

Study Arms (1)

AI-guided resection

EXPERIMENTAL

Tailored supramarginal surgery guided by AI-based recurrence probability maps. Aim of supramarginal resection, where the high-risk of recurrence areas identified by the AI-based model are subsidiary to be removed as safe locations for the patient.

Procedure: AI-guided surgery

Interventions

AI-guided surgery PROCEDURE

Neuronavigated targeted biopsy sampling. Supramarginal resection including high-risk areas of recurrence defined by a radiomics-based model.

AI-guided resection

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• A suspected diagnosis of supratentorial glioblastoma by MRI.
• Tumor in non eloquent brain region according to the UCSF (University of California, San Francisco) classification, including the sensor motor areas (precentral and postcentral gyri), perisylvian language areas in the dominant hemisphere (superior temporal, inferior frontal, and inferior parietal gyri), basal ganglia, internal capsule, thalamus, and visual cortex around the calcarine sulcus
• Indication for surgical treatment and where supramarginal resection is considered possible according to the preoperative imaging. This consideration needs to be verified by two specialists in neurosurgery. This criterion needs to be verified by two senior neurosurgeons.
• Karnofsky Performance Score ≥ 70;
• Written informed consent

You may not qualify if:

• Tumors in eloquent areas.
• Recurrent gliomas (except biopsy)
• MR image data not usable due to artifacts during acquisition. Inability to give written informed consent
• KPS \< 70
• Severe comorbidity.

Sponsors & Collaborators

• UiT The Arctic University of Norway: collaborator
• University Hospital of North Norway: collaborator
• University of Valladolid: collaborator
• Hospital del Rio Hortega: lead

Study Sites (1)

University Hospital Rio Hortega

Valladolid, Valladolid, 47012, Spain

Location

Related Publications (1)

• Cepeda S, Luppino LT, Perez-Nunez A, Solheim O, Garcia-Garcia S, Velasco-Casares M, Karlberg A, Eikenes L, Sarabia R, Arrese I, Zamora T, Gonzalez P, Jimenez-Roldan L, Kuttner S. Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI. Cancers (Basel). 2023 Mar 22;15(6):1894. doi: 10.3390/cancers15061894.

  PMID: 36980783 BACKGROUND

MeSH Terms

Conditions

Glioblastoma

Condition Hierarchy (Ancestors)

Astrocytoma; Glioma; Neoplasms, Neuroepithelial; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Neoplasms, Nerve Tissue

Study Officials

• Santiago Cepeda, PhD

  Hospital Río Hortega

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: NONE
• Purpose: TREATMENT
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: February 7, 2023
• First Posted: February 21, 2023
• Study Start: November 1, 2022
• Primary Completion: May 30, 2025
• Study Completion: December 1, 2025
• Last Updated: December 24, 2025

Record last verified: 2025-12

Locations

ES (1)