Clinical trial · Observational

Automated Segmentation and Volumetry for Meningioma Using Deep Learning

Automated Meningioma Segmentation and Volumetry Using a nnU-Net Based Architecture on Contrast-enhanced MRI

NCT05093751CI-TRIAL-00054686completedClinicalTrials.gov clinicaltrialsPublishedExplore in graph →

Summary

Brief summary (as posted)

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.

Conditions

Conditions (2)

Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.

Condition (as posted)	Mapped entity	Match	Confidence
Artificial Intelligence	—	UNRESOLVED	—
Meningioma	Meningioma	ONTOLOGY_EXACT	0.90

Interventions

Interventions (1)

Intervention	Type	Mapped drug	Match
Observation	Other	—	UNRESOLVED

Design

Arms and outcomes

Arms (1)

label
Meningioma patients
interventionNames
1. Other: Observation

Primary outcomes (1)

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.

Eligibility

Eligibility (as posted)

Sex: All
Minimum age: 18 Years

Show eligibility criteria text

Inclusion Criteria:

* Radiologically diagnosed meningioma by MRI

Exclusion Criteria:

* under 18 years old
* Multiple meningiomas
* Orbital meningioma
* Any prior treatment for intracranial meningioma before registration

References

Publications (0)

Data not yet available

No reference posted for this study.