Related Experiment Video
Updated: Jun 3, 2026
11:03
High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
Published on: November 10, 2015
Microbleed detection using automated segmentation (MIDAS): a new method applicable to standard clinical MR images
Mohamed L Seghier1, Magdalena A Kolanko, Alexander P Leff
1Wellcome Trust Centre for Neuroimaging, University College London Institute of Neurology, London, United Kingdom.
Plos One
|March 31, 2011
Summary
A new automated method for detecting cerebral microbleeds on MRI scans shows good agreement with manual ratings. This tool, MIDAS, can help screen for multiple lobar microbleeds, improving small vessel disease assessment.
Area of Science:
- Neuroimaging
- Radiology
- Medical image analysis
Background:
- Cerebral microbleeds (CMBs) are key imaging markers of small vessel diseases.
- CMBs are visible on gradient-recalled echo (GRE) T2* MRI.
- CMBs are relevant to intracerebral bleeding risk and brain dysfunction.
Purpose of the Study:
- To develop and evaluate an automated method for cerebral microbleed detection.
- To compare the automated method (MIDAS) with a validated visual rating system.
Main Methods:
- Developed an automated microbleed detection algorithm (MIDAS) using unified segmentation-normalization.
- Spatially normalized GRE T2* MRI images into standard stereotaxic space.
- Assessed agreement using intraclass correlation coefficient (ICC) and Kappa statistic.
Main Results:
- MIDAS showed moderate to good agreement with manual ratings for lobar microbleed presence (Kappa=0.43, improved to 0.65).
- Very good agreement was found for the number of lobar microbleeds (ICC=0.71, improved to 0.87).
- MIDAS successfully identified all patients with multiple (≥2) lobar microbleeds.
Conclusions:
- The automated microbleed detection with an editing step (MIDAS) agrees well with visual rating systems.
- MIDAS is a potentially useful tool for screening multiple lobar microbleeds on standard MRI datasets.
