Related Experiment Video
Updated: May 28, 2026
Assessing Cortical Cerebral Microinfarcts on High Resolution MR Images
Published on: November 20, 2015
Efficient detection of cerebral microbleeds on 7.0 T MR images using the radial symmetry transform
Hugo J Kuijf1, Jeroen de Bresser, Mirjam I Geerlings
1Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands. hugok@isi.uu.nl
Abstract:
Cerebral microbleeds (CMBs) are commonly detected on MRI and have recently received an increased interest, because they are associated with vascular disease and dementia. Identification and rating of CMBs on MRI images may be facilitated by semi-automatic detection, particularly on high-resolution images acquired at high field strength. For these images, visual rating is time-consuming and has limited reproducibility. We present the radial symmetry transform (RST) as an efficient method for semi-automated CMB detection on 7.0 T MR images, with a high sensitivity and a low number of false positives that have to be censored manually. The RST was computed on both echoes of a dual-echo T2*-weighted gradient echo 7.0 T MR sequence in 18 participants from the Second Manifestations of ARTerial disease (SMART) study. Potential CMBs were identified by combining the output of the transform on both echoes. Each potential CMB identified through the RST was visually checked by two raters to identify probable CMBs. The scoring time needed to manually reject false positives was recorded. The sensitivity of 71.2% is higher than that of individual human raters on 7.0 T scans and the required human rater time is reduced from 30 to 2 minutes per scan on average. The RST outperforms published semi-automated methods in terms of either a higher sensitivity or less false positives, and requires much less human rater time.
Insights
A new radial symmetry transform (RST) method improves the detection of cerebral microbleeds (CMBs) on 7.0 T MRI scans. This semi-automated approach enhances sensitivity and significantly reduces the time needed for manual review.
Area of Science:
- Neuroimaging
- Medical image analysis
- Radiology
Background:
- Cerebral microbleeds (CMBs) are increasingly recognized as indicators of vascular disease and dementia.
- Accurate identification of CMBs on MRI is crucial but challenging, especially on high-resolution, high-field strength images.
- Manual rating of CMBs on such images is time-consuming and lacks reproducibility.
Purpose of the Study:
- To introduce and evaluate the radial symmetry transform (RST) for semi-automated detection of CMBs on 7.0 T MRI.
- To assess the sensitivity, specificity, and efficiency of the RST method compared to human raters and existing semi-automated techniques.
Main Methods:
- The radial symmetry transform (RST) was applied to dual-echo T2*-weighted gradient echo 7.0 T MR images from 18 participants.
- Potential CMBs were identified by integrating RST outputs from both echoes.
- Two raters manually reviewed potential CMBs, and the time for false positive rejection was recorded.
Main Results:
- The RST achieved a sensitivity of 71.2%, surpassing individual human raters on 7.0 T scans.
- The average human rater time per scan was reduced from 30 to 2 minutes.
- The RST demonstrated superior performance over published semi-automated methods in sensitivity and/or false positive reduction.
Conclusions:
- The radial symmetry transform (RST) offers an efficient and effective semi-automated method for detecting cerebral microbleeds on 7.0 T MRI.
- This method significantly improves detection sensitivity and reduces the workload for human raters.
- RST shows promise for improving the clinical assessment of vascular disease and dementia associated with CMBs.
