Now Available for Public Comment: Notice of Proposed Rulemaking (NPRM) for FDAAA 801 and NIH Draft Reporting Policy for NIH-Funded Trials

Identification of Clinically Occult Glioma Cells and Characterization of Glioma Behavior Through Machine Learning Analysis of Advanced Imaging Technology

This study is currently recruiting participants. (see Contacts and Locations)
Verified June 2014 by AHS Cancer Control Alberta
Sponsor:
Information provided by (Responsible Party):
AHS Cancer Control Alberta
ClinicalTrials.gov Identifier:
NCT00330109
First received: May 23, 2006
Last updated: June 5, 2014
Last verified: June 2014
  Purpose

Gliomas are one of the most challenging tumors to treat, because areas of the apparently normal brain contain microscopic deposits of glioma cells; indeed, these occult cells are known to infiltrate several centimeters beyond the clinically apparent lesion visualized on standard computer tomography or magnetic resonance imaging (MR). Since it is not feasible to remove or radiate large volumes of the brain, it is important to target only the visible tumor and the infiltrated regions of the brain. However, due to the limited ability to detect occult glioma cells, clinicians currently add a uniform margin of 2 cm or more beyond the visible abnormality, and irradiate that volume. Evidence, however, suggests that glioma growth is not uniform - growth is favored in certain directions and impeded in others. This means it is important to determine, for each patient, which areas are at high risk of harboring occult cells. We propose to address this task by learning how gliomas grown, by applying Machine Learning algorithms to a database of images (obtained using various advanced imaging technologies: MRI, MRS, DTI, and MET-PET) from previous glioma patients. Advances will directly translate to improvements for patients.


Condition Intervention
Glioma
Procedure: MRS Imaging
Procedure: PET Scanning
Procedure: Diffusion Tensor Imaging

Study Type: Interventional
Study Design: Endpoint Classification: Efficacy Study
Intervention Model: Single Group Assignment
Masking: Open Label
Primary Purpose: Diagnostic
Official Title: Identification of Clinically Occult Glioma Cells and Characterization of Glioma Behavior Through Machine Learning Analysis of Advanced Imaging Technology

Resource links provided by NLM:


Further study details as provided by AHS Cancer Control Alberta:

Primary Outcome Measures:
  • image glioma patients with advanced imaging techniques to help us better characterize gliomas in the future [ Time Frame: Pretreatment, 1 month post treatment and 7 months post treatment ] [ Designated as safety issue: No ]
    Eligible patients will be given the opportunity to undergo additional diagnostic imaging. These images will be anonymized and databased. the data will be analyzed using machine learning techniques.

  • create an image-based database to allow machine learning analysis of all the clinically available data [ Time Frame: Pretreatment, 1 month post treatment and 7 months post treatment ] [ Designated as safety issue: No ]
    Eligible patients will be given the opportunity to undergo additional diagnostic imaging. These images will be anonymized and databased. the data will be analyzed using machine learning techniques.


Secondary Outcome Measures:
  • through machine learning analysis, develop computer algorithms to allow us to automate tumour segmentation, predict tumour behaviour and predict location of clinically occult glioma cells [ Time Frame: Pretreatment, 1 month post treatment and 7 months post treatment ] [ Designated as safety issue: No ]
    Eligible patients will be given the opportunity to undergo additional diagnostic imaging. These images will be anonymized and databased. the data will be analyzed using machine learning techniques.


Estimated Enrollment: 120
Study Start Date: June 2006
Estimated Study Completion Date: December 2014
Estimated Primary Completion Date: December 2014 (Final data collection date for primary outcome measure)
Intervention Details:
    Procedure: MRS Imaging
    Performed on a 3.0 Tesla Philips Intera MRI Unit (Best, Netherlands). Scout views and T2 transverse images are obtained to locate the tumor in conjunction with any previous diagnostic images.
    Procedure: PET Scanning
    Using an Allegro scanner, the patient will be scanned for approximately 20-30 minutes. All emission scan data is processed by a multi-step procedure.
    Procedure: Diffusion Tensor Imaging
    Subjects will be scanned with a 3T Philips Intera MRI scanner for approximately 26 minutes for anatomical and DTI imaging. Total DTI acquisition time will be 6:06 minutes with 40 contiguous axial slices for full brain coverage.
Detailed Description:

Gliomas are the most common primary brain tumors in adults; most are high-grade and have a high level of mortality. The standard treatment is to kill or remove the cancer cells. Of course, this can only work if the surgeon or radiologist can find these cells. Unfortunately, there are inevitably so-called "occult" cancer cells, which are not found even by today's sophisticated imaging techniques.

This proposal proposes a technology to predict the locations of these occult cells, by learning the growth patterns exhibited by gliomas in previous patients. We will also develop software tools that help both practitioners and researchers find gliomas similar to a current one, and that can autonomously find the tumor region within a brain image, which can save radiologists time, and perhaps help during surgery.

  Eligibility

Ages Eligible for Study:   18 Years and older
Genders Eligible for Study:   Both
Accepts Healthy Volunteers:   No
Criteria

Inclusion Criteria:

  • must have histologically proven glioma
  • the patient or legally authorized representative must fully understand all elements of informed consent, and sign the consent form

Exclusion Criteria:

  • psychiatric conditions precluding informed consent
  • medical or psychiatric condition precluding MRI or PET studies (e.g. pacemaker, aneurysm clips, neurostimulator, cochlear implant, severe claustrophobia/anxiety, pregnancy)
  Contacts and Locations
Choosing to participate in a study is an important personal decision. Talk with your doctor and family members or friends about deciding to join a study. To learn more about this study, you or your doctor may contact the study research staff using the Contacts provided below. For general information, see Learn About Clinical Studies.

Please refer to this study by its ClinicalTrials.gov identifier: NCT00330109

Contacts
Contact: Albert Murtha, MD, FRCPC 780-432-8517 albert.murtha@albertahealthservices.ca

Locations
Canada, Alberta
Cross Cancer Institute Recruiting
Edmonton, Alberta, Canada, T6G 1Z2
Contact    780-432-8517      
Principal Investigator: Albert Murtha, MD, FRCPC         
Sponsors and Collaborators
AHS Cancer Control Alberta
Investigators
Principal Investigator: Albert Murtha, MD, FRCPC AHS Cancer Control Alberta
  More Information

No publications provided

Responsible Party: AHS Cancer Control Alberta
ClinicalTrials.gov Identifier: NCT00330109     History of Changes
Other Study ID Numbers: CNS-9-0032 / 22151-22523
Study First Received: May 23, 2006
Last Updated: June 5, 2014
Health Authority: Canada: Health Canada

Keywords provided by AHS Cancer Control Alberta:
glioma
machine learning
advanced diagnostic imaging

Additional relevant MeSH terms:
Glioma
Neoplasms
Neoplasms by Histologic Type
Neoplasms, Germ Cell and Embryonal
Neoplasms, Glandular and Epithelial
Neoplasms, Nerve Tissue
Neoplasms, Neuroepithelial
Neuroectodermal Tumors

ClinicalTrials.gov processed this record on November 27, 2014