Computer-aided detection of cerebral microbleeds in susceptibility-weighted imaging. (December 2015)

• Record Type: Journal Article
• Authors: Fazlollahi, Amir; Meriaudeau, Fabrice; Giancardo, Luca; Villemagne, Victor L.; Rowe, Christopher C.; Yates, Paul; Salvado, Olivier; Bourgeat, Pierrick
• Is Part Of: Computerized medical imaging and graphics. Volume 46:Part 3(2015)
• Page Start: 269
• Page End: 276
• Publication Date: 2015-12
• Subjects: Cerebral microbleed -- Susceptibility-weighted imaging -- Radon transform -- Multi-scale Laplacian of Gaussian -- Random forests; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2015.10.001
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract : Highlights: A computer-aided technique for detecting cerebral microbleeds on SWI is proposed. All regions with microbleeds are identified by a multi-scale Laplacian of Gaussian. A cascade of random forest classifiers is designed to handle class imbalance problem. Proposed approach has higher performance compared to state of the art approaches. It may assist manual screening by minimizing assessment time and rater variability. 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.