Related Experiment Video
Updated: Mar 2, 2026
A Reproducible Computerized Method for Quantitation of Capillary Density using Nailfold Capillaroscopy
Published on: October 27, 2015
Automated algorithm for counting microbleeds in patients with familial cerebral cavernous malformations
Xiaowei Zou1, Blaine L Hart2, Marc Mabray2
1Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, California, USA.
Purpose:
Familial cerebral cavernous malformation (CCM) patients present with multiple lesions that can grow both in number and size over time and are reliably detected on susceptibility-weighted imaging (SWI). Manual counting of lesions is arduous and subject to high variability. We aimed to develop an automated algorithm for counting CCM microbleeds (lesions <5 mm in diameter) on SWI images.
Methods:
Fifty-seven familial CCM type-1 patients were included in this institutional review board-approved study. Baseline SWI (n = 57) and follow-up SWI (n = 17) were performed on a 3T Siemens MR scanner with lesions counted manually by the study neuroradiologist. We modified an algorithm for detecting radiation-induced microbleeds on SWI images in brain tumor patients, using a training set of 22 manually delineated CCM microbleeds from two random scans. Manual and automated counts were compared using linear regression with robust standard errors, intra-class correlation (ICC), and paired t tests. A validation analysis comparing the automated counting algorithm and a consensus read from two neuroradiologists was used to calculate sensitivity, the proportion of microbleeds correctly identified by the automated algorithm.
Results:
Automated and manual microbleed counts were in strong agreement in both baseline (ICC = 0.95, p < 0.001) and longitudinal (ICC = 0.88, p < 0.001) analyses, with no significant difference between average counts (baseline p = 0.11, longitudinal p = 0.29). In the validation analysis, the algorithm correctly identified 662 of 1325 microbleeds (sensitivity=50%), again with strong agreement between approaches (ICC = 0.77, p < 0.001).
Conclusion:
The automated algorithm is a consistent method for counting microbleeds in familial CCM patients that can facilitate lesion quantification and tracking.
Insights
An automated algorithm accurately counts cerebral cavernous malformation (CCM) microbleeds on SWI images, improving lesion quantification for familial CCM patients. This method offers a consistent approach for tracking disease progression.
Area of Science:
- Neuroimaging
- Medical Algorithms
- Genetics
Background:
- Familial cerebral cavernous malformation (CCM) is characterized by multiple, growing lesions.
- Susceptibility-weighted imaging (SWI) reliably detects these lesions.
- Manual microbleed counting is time-consuming and prone to variability.
Purpose of the Study:
- To develop and validate an automated algorithm for counting cerebral cavernous malformation (CCM) microbleeds on SWI images.
- To improve the accuracy and consistency of lesion quantification in familial CCM.
Main Methods:
- Modified an existing algorithm for microbleed detection on SWI.
- Trained the algorithm on manually delineated CCM microbleeds.
- Compared automated counts with manual counts using linear regression and ICC.
- Validated the algorithm's sensitivity against a consensus read.
Main Results:
- Strong agreement between automated and manual counts (ICC=0.95 baseline, ICC=0.88 longitudinal).
- No significant difference in average counts between manual and automated methods.
- Algorithm achieved 50% sensitivity in validation, with strong agreement (ICC=0.77).
Conclusions:
- The automated algorithm provides a consistent and reliable method for counting microbleeds in familial CCM.
- This tool can significantly facilitate lesion quantification and tracking in CCM patients.
- Automated counting aids in monitoring disease progression and treatment response.
