Automated algorithm for counting microbleeds in patients with familial cerebral cavernous malformations

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...

Full description

Saved in:
Bibliographic Details
Published in:Neuroradiology Vol. 59; no. 7; pp. 685 - 690
Main Authors: Zou, Xiaowei, Hart, Blaine L., Mabray, Marc, Bartlett, Mary R., Bian, Wei, Nelson, Jeffrey, Morrison, Leslie A., McCulloch, Charles E., Hess, Christopher P., Lupo, Janine M., Kim, Helen
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2017
Springer Nature B.V
Subjects:
Algorithms
Automation
Brain
Brain cancer
Brain tumors
Cerebral Hemorrhage - diagnostic imaging
Congenital defects
Counting
Female
Functional Neuroradiology
Hemangioma, Cavernous, Central Nervous System - diagnostic imaging
Hemorrhage
Humans
Image Interpretation, Computer-Assisted - methods
Imaging
Lesions
Magnetic Resonance Imaging - methods
Male
Medicine
Medicine & Public Health
Middle Aged
Neuroimaging
Neurology
Neuroradiology
Neurosciences
Neurosurgery
Patients
Radiation
Radiation effects
Radiology
Regression analysis
Risk Factors
Robustness (mathematics)
Sensitivity
Sensitivity analysis
Vein & artery diseases
Susceptibility-weighted imaging
Cerebral cavernous malformations
Automated lesion counting
Microbleeds
ISSN:0028-3940, 1432-1920, 1432-1920
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0028-3940
1432-1920
1432-1920
DOI:10.1007/s00234-017-1845-8