Please use this identifier to cite or link to this item:
Title: Computer-aided detection of cerebral microbleeds in susceptibility-weighted imaging
Austin Authors: Fazlollahi, Amir;Meriaudeau, Fabrice;Giancardo, Luca;Villemagne, Victor L ;Rowe, Christopher C ;Yates, Paul A ;Salvado, Olivier;Bourgeat, Pierrick;AIBL Research Group
Affiliation: CSIRO Digital Productivity Flagship, The Australian e-Health Research Centre, Herston, Queensland, Australia
Le2I, University of Burgundy, Le Creusot, France
RLE, Massachusetts Institute of Technology, MA, USA
Department of Nuclear Medicine and Centre for PET, Austin Health, Heidelberg, Victoria, Australia
Issue Date: Dec-2015 2015-10-24
Publication information: Computerized Medical Imaging and Graphics 2015; 46(3): 269-276
Abstract: Susceptibility-weighted imaging (SWI) is recognized as the preferred MRI technique for visualizing cerebral vasculature and related pathologies such as cerebral microbleeds (CMBs). Manual identification of CMBs is time-consuming, has limited reliability and reproducibility, and is prone to misinterpretation. In this paper, a novel computer-aided microbleed detection technique based on machine learning is presented: First, spherical-like objects (potential CMB candidates) with their corresponding bounding boxes were detected using a novel multi-scale Laplacian of Gaussian technique. A set of robust 3-dimensional Radon- and Hessian-based shape descriptors within each bounding box were then extracted to train a cascade of binary random forests (RF). The cascade consists of consecutive independent RF classifiers with low to high posterior probability constraints to handle imbalanced training sets (CMBs and non-CMBs), and to progressively improve detection rates. The proposed method was validated on 66 subjects whose CMBs were manually stratified into "possible" and "definite" by two medical experts. The proposed technique achieved a sensitivity of 87% and an average false detection rate of 27.1 CMBs per subject on the "possible and definite" set. A sensitivity of 93% and false detection rate of 10 CMBs per subject was also achieved on the "definite" set. The proposed automated approach outperforms state of the art methods, and promises to enhance manual expert screening. Benefits include improved reliability, minimization of intra-rater variability and a reduction in assessment time.
DOI: 10.1016/j.compmedimag.2015.10.001
ORCID: 0000-0003-3910-2453
PubMed URL:
Type: Journal Article
Subjects: Cerebral microbleed
Multi-scale Laplacian of Gaussian
Radon transform
Random forests
Susceptibility-weighted imaging
Appears in Collections:Journal articles

Show full item record

Page view(s)

checked on Nov 25, 2022

Google ScholarTM


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.