Ignite Creation Date:
2025-12-24 @ 11:45 PM
Ignite Modification Date:
2025-12-25 @ 9:38 PM
Study NCT ID:
NCT05093751
Status:
COMPLETED
Last Update Posted:
2021-10-26
First Post:
2021-10-01
Is NOT Gene Therapy:
False
Has Adverse Events:
False
Brief Title:
Automated Segmentation and Volumetry for Meningioma Using Deep Learning
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D008579', 'term': 'Meningioma'}], 'ancestors': [{'id': 'D009380', 'term': 'Neoplasms, Nerve Tissue'}, {'id': 'D009370', 'term': 'Neoplasms by Histologic Type'}, {'id': 'D009369', 'term': 'Neoplasms'}, {'id': 'D009383', 'term': 'Neoplasms, Vascular Tissue'}, {'id': 'D008577', 'term': 'Meningeal Neoplasms'}, {'id': 'D016543', 'term': 'Central Nervous System Neoplasms'}, {'id': 'D009423', 'term': 'Nervous System Neoplasms'}, {'id': 'D009371', 'term': 'Neoplasms by Site'}, {'id': 'D009422', 'term': 'Nervous System Diseases'}]}, 'interventionBrowseModule': {'meshes': [{'id': 'D019370', 'term': 'Observation'}], 'ancestors': [{'id': 'D008722', 'term': 'Methods'}, {'id': 'D008919', 'term': 'Investigative Techniques'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'RETROSPECTIVE', 'observationalModel': 'CASE_ONLY'}, 'enrollmentInfo': {'type': 'ACTUAL', 'count': 600}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'COMPLETED', 'startDateStruct': {'date': '2013-03-23', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2021-10', 'completionDateStruct': {'date': '2021-09-30', 'type': 'ACTUAL'}, 'lastUpdateSubmitDate': '2021-10-13', 'studyFirstSubmitDate': '2021-10-01', 'studyFirstSubmitQcDate': '2021-10-13', 'lastUpdatePostDateStruct': {'date': '2021-10-26', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2021-10-26', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2021-09-30', 'type': 'ACTUAL'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Accuracy compared with ground truth', 'timeFrame': '10-01-2020 until 09-30-2021', 'description': 'As a primary endpoint, we will examine the ability of U-Net and nnU-Net to segment meningioma in brain MR compared with ground truth. Ground truth is defined as area on MR drawn by two neurosurgeons. Accuracy of autosegmentation of meningioma will be assessed in dice similarity coefficient, recall, and precision.'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Meningioma', 'Artificial intelligence', 'autosegmentation', 'volumetry'], 'conditions': ['Meningioma', 'Artificial Intelligence']}, 'descriptionModule': {'briefSummary': 'U-Net-based architectures will be applied to 500 contrast-enhanced axial MR images of different patients from a single institution after manual segmentation of meningioma, of which 50 were used for testing. Tumor volumetry after autosegmentation by trained U-Net-based architecture is final goal.', 'detailedDescription': "U-Net-based architectures will be applied to 500 contrast-enhanced axial MR images of different patients from a single institution after manual segmentation of meningioma, of which 50 were used for testing. After preprocessing with Z-isotropification and intensity normalization of images, 3 U-Net-based networks (2D U-Net, Attention U-Net, 3D U-Net) and 3 nnU-Net-based networks (2D nnU-Net, Attention nnU-Net, 3D nnU-Net) will be trained with meningioma-segmented images. For applying to 3D networks, sagittal and coronal images will be reconstructed using axial images. After prediction, the cut-off of the probability function, which is a trade-off, will be obtained with the Gaussian Mixture Modeling algorithm using the probability density function. The voxels having a probability function higher than that will be finally predicted as meningioma. Tumor volume is calculated as the sum of the product of segmented area and thickness of axial images. For performance evaluation, dice similarity coefficient (DSC), precision, and recall will be evaluated compared with manually segmented voxels for validation datasets. The results of volumetry of each model will be compared with manual segmentation-based volume through Pearson's correlation analysis."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': 'Intracranial meningioma patients who were diagnosed by MRI are study population of this study. Inclusion in this study have not been decided according to whether or not surgery for tumor resection was performed or MRI thickness and magnetic power.', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Radiologically diagnosed meningioma by MRI\n\nExclusion Criteria:\n\n* under 18 years old\n* Multiple meningiomas\n* Orbital meningioma\n* Any prior treatment for intracranial meningioma before registration'}, 'identificationModule': {'nctId': 'NCT05093751', 'briefTitle': 'Automated Segmentation and Volumetry for Meningioma Using Deep Learning', 'organization': {'class': 'OTHER', 'fullName': 'Seoul National University Hospital'}, 'officialTitle': 'Automated Meningioma Segmentation and Volumetry Using a nnU-Net Based Architecture on Contrast-enhanced MRI', 'orgStudyIdInfo': {'id': 'SNUH-MNG-AI001'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'Meningioma patients', 'interventionNames': ['Other: Observation']}], 'interventions': [{'name': 'Observation', 'type': 'OTHER', 'description': 'This study does not involve any intervention to subjects.', 'armGroupLabels': ['Meningioma patients']}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO', 'description': 'We have no plan to share IPD'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Seoul National University Hospital', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Professor', 'investigatorFullName': 'Chul-Kee Park', 'investigatorAffiliation': 'Seoul National University Hospital'}}}}