Related Experiment Video
Updated: Jun 3, 2026
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.
Background:
Cerebral microbleeds, visible on gradient-recalled echo (GRE) T2* MRI, have generated increasing interest as an imaging marker of small vessel diseases, with relevance for intracerebral bleeding risk or brain dysfunction.
Methodology/Principal Findings:
Manual rating methods have limited reliability and are time-consuming. We developed a new method for microbleed detection using automated segmentation (MIDAS) and compared it with a validated visual rating system. In thirty consecutive stroke service patients, standard GRE T2* images were acquired and manually rated for microbleeds by a trained observer. After spatially normalizing each patient's GRE T2* images into a standard stereotaxic space, the automated microbleed detection algorithm (MIDAS) identified cerebral microbleeds by explicitly incorporating an "extra" tissue class for abnormal voxels within a unified segmentation-normalization model. The agreement between manual and automated methods was assessed using the intraclass correlation coefficient (ICC) and Kappa statistic. We found that MIDAS had generally moderate to good agreement with the manual reference method for the presence of lobar microbleeds (Kappa = 0.43, improved to 0.65 after manual exclusion of obvious artefacts). Agreement for the number of microbleeds was very good for lobar regions: (ICC = 0.71, improved to ICC = 0.87). MIDAS successfully detected all patients with multiple (≥2) lobar microbleeds.
Conclusions/Significance:
MIDAS can identify microbleeds on standard MR datasets, and with an additional rapid editing step shows good agreement with a validated visual rating system. MIDAS may be useful in screening for multiple lobar microbleeds.
Insights
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.
