Search

BACKGROUND AND PURPOSE: White matter lesions of presumed ischemic origin are associated with progressive cognitive impairment and impaired BBB function. Studying the longitudinal effects of white matter lesion biomarkers that measure changes in perfusion and BBB patency within white matter lesions is required for long-term studies of lesion progression. We studied perfusion and BBB disruption within white matter lesions in asymptomatic subjects. MATERIALS AND METHODS: Anatomic imaging was followed by consecutive dynamic contrast-enhanced and DSC imaging. White matter lesions in 21 asymptomatic individuals were determined using a Subject-Specific Sparse Dictionary Learning algorithm with manual correction. Perfusion-related parameters including CBF, MTT, the BBB leakage parameter, and volume transfer constant were determined. RESULTS: MTT was significantly prolonged (7.88 [SD, 1.03] seconds) within white matter lesions compared with normal-appearing white (7.29 [SD, 1.14] seconds) and gray matter (6.67 [SD, 1.35] seconds). The volume transfer constant, measured by dynamic contrast-enhanced imaging, was significantly elevated (0.013 [SD, 0.017] minutes(−1)) in white matter lesions compared with normal-appearing white matter (0.007 [SD, 0.011] minutes(−1)). BBB disruption within white matter lesions was detected relative to normal white and gray matter using the DSC-BBB leakage parameter method so that increasing BBB disruption correlated with increasing white matter lesion volume (Spearman correlation coefficient = 0.44; P < .046). CONCLUSIONS: A dual-contrast-injection MR imaging protocol combined with a 3D automated segmentation analysis pipeline was used to assess BBB disruption in white matter lesions on the basis of quantitative perfusion measures including the volume transfer constant (dynamic contrast-enhanced imaging), the BBB leakage parameter (DSC), and MTT (DSC). This protocol was able to detect early pathologic changes in otherwise healthy individuals.

Background Studies have found that individuals with mild cognitive impairment (MCI) exhibit a range of deficits outside the realm of primary explicit memory, yet the role of response speed and implicit learning in older adults with MCI have not been established. Objective The current study aims to explore and document response speed and implicit learning in older adults with neuropsychologically defined MCI using a simple serial reaction (SRT) task. In addition, the study aims to explore the feasibility of a novel utilization of the simple cognitive task using machine learning procedures as a proof of concept. Method Participants were 22 cognitively healthy older adults and 20 older adults with MCI confirmed through comprehensive neuropsychological evaluation. Two-sample t-test, multivariate regression, and mixed-effect models were used to investigate group difference in response speed and implicit learning on the SRT task. We also explored the potential utility of SRT feature analysis through random forest classification. Results With demographic variables controlled, the MCI group showed overall slower reaction time and higher error rate compared to the cognitively healthy volunteers. Both groups showed significant simple motor learning and implicit learning. The learning patterns were not statistically different between the two groups. Random forest classification achieved overall accuracy of 80.9%. Conclusions Individuals with MCI demonstrated slower reaction time and higher error rate compared to cognitively healthy volunteers but demonstrated largely preserved motor learning and implicit sequence learning. Preliminary results from random forest classification using features from SRT performance supported further research in this area.

Introduction: White matter lesions of presumed ischemic origin (WMH) have been associated with increased risk of stroke, cognitive and motor decline, and are a subject of public health research. Engineering new MRI pipelines allowing for determination of mean transit time (MTT), and blood brain barrier permeability (BBBP), within WMH lesions is required for long-term population-based studies of lesion progression in patients with dementia and vascular cognitive impairment. Methods: WMH lesion volumes in 24 asymptomatic individuals was determined using an automated segmentation methodology, S3DL, with manual correction to remove false positives. A double contrast injection scheme was used to measure both K trans using dynamic contrast enhanced (DCE) imaging and K 2 using dynamic susceptibility contrast (DSC) imaging which also provided perfusion-related measures. BBBP was measured as k 2 within segmented WMH lesions and compared with normal white and gray matter. Results: The mean transit time (MTT) was found to be significantly prolonged (8.11, ptrans (0.018, p=0.351) between the lesions and the white/gray matter. Permeability measured in the WMH lesions using the DSC-K 2 method was increased and was correlated withincreasing total WMH lesion volume (spearman correlation 0.44; p< 0.046). Conclusion: In this first study using an advanced WMH lesion automated segmentation pipeline, we measured DCE and DSC perfusion and permeability variables within WMH lesions and compared them to normal white and grey matter in healthy people. We observed increasing MTT, within WMH lesions as compared to unaffected white and gray matter. Using the DSC-K 2 method, BBBP was higher within WMH lesions in these asymptomatic people, and correlated with increasing total lesion volume.

We present a computer-aided diagnosis algorithm for mammography trained and validated on studies acquired from six clinical sites. We hold out the full dataset from a seventh hospital for testing to assess the algorithm’s ability to generalize to new sites. Our classifiers are convolutional neural networks that take multiple input images from a mammography study and produce classifications for the study. The studies are globally labeled as normal, biopsy benign, high risk or biopsy malignant. We report on experimental results from several network variants, including study-level and breast-level models, single- and multiple-output models, and a novel model architecture that incorporates prior studies. Each model variation includes an image-level classifier that is pre-trained with per-image labels and is used as a feature extractor in our study-level models. Our best study-level model achieves 0.85 area under the ROC curve for normal vs malignant classification on the held-out test site. In comparison with other recent work, we achieve a similar level of classification sensitivity and specificity on a dataset with greater site and vendor variation. Additionally, our test performance is demonstrated on a held-out site to more accurately assess how the model would perform when deployed in the field.

Multi-modal deformable registration is important for many medical image analysis tasks such as atlas alignment, image fusion, and distortion correction. Whereas a conventional method would register images with different modalities using modality independent features or information theoretic metrics such as mutual information, this paper presents a new framework that addresses the problem using a two-channel registration algorithm capable of using mono-modal similarity measures such as sum of squared differences or cross-correlation. To make it possible to use these same-modality measures, image synthesis is used to create proxy images for the opposite modality as well as intensity-normalized images from each of the two available images. The new deformable registration framework was evaluated by performing intra-subject deformation recovery, intra-subject boundary alignment, and inter-subject label transfer experiments using multi-contrast magnetic resonance brain imaging data. Three different multi-channel registration algorithms were evaluated, revealing that the framework is robust to the multi-channel deformable registration algorithm that is used. With a single exception, all results demonstrated improvements when compared against single channel registrations using the same algorithm with mutual information.

With the advent of convolutional neural networks~(CNN), supervised learning methods are increasingly being used for whole brain segmentation. However, a large, manually annotated training dataset of labeled brain images required to train such supervised methods is frequently difficult to obtain or create. In addition, existing training datasets are generally acquired with a homogeneous magnetic resonance imaging~(MRI) acquisition protocol. CNNs trained on such datasets are unable to generalize on test data with different acquisition protocols. Modern neuroimaging studies and clinical trials are necessarily multi-center initiatives with a wide variety of acquisition protocols. Despite stringent protocol harmonization practices, it is very difficult to standardize the gamut of MRI imaging parameters across scanners, field strengths, receive coils etc., that affect image contrast. In this paper we propose a CNN-based segmentation algorithm that, in addition to being highly accurate and fast, is also resilient to variation in the input acquisition. Our approach relies on building approximate forward models of pulse sequences that produce a typical test image. For a given pulse sequence, we use its forward model to generate plausible, synthetic training examples that appear as if they were acquired in a scanner with that pulse sequence. Sampling over a wide variety of pulse sequences results in a wide variety of augmented training examples that help build an image contrast invariant model. Our method trains a single CNN that can segment input MRI images with acquisition parameters as disparate as $T_1$-weighted and $T_2$-weighted contrasts with only $T_1$-weighted training data. The segmentations generated are highly accurate with state-of-the-art results~(overall Dice overlap$=0.94$), with a fast run time~($\approx$ 45 seconds), and consistent across a wide range of acquisition protocols., Typo in author name corrected. Greves -> Greve

Synthesizing magnetic resonance (MR) and computed tomography (CT) images (from each other) has important implications for clinical neuroimaging. The MR to CT direction is critical for MRI-based radiotherapy planning and dose computation, whereas the CT to MR direction can provide an economic alternative to real MRI for image processing tasks. Additionally, synthesis in both directions can enhance MR/CT multi-modal image registration. Existing approaches have focused on synthesizing CT from MR. In this paper, we propose a multi-atlas based hybrid method to synthesize T1-weighted MR images from CT and CT images from T1-weighted MR images using a common framework. The task is carried out by: (a) computing a label field based on supervoxels for the subject image using joint label fusion; (b) correcting this result using a random forest classifier (RF-C); (c) spatial smoothing using a Markov random field; (d) synthesizing intensities using a set of RF regressors, one trained for each label. The algorithm is evaluated using a set of six registered CT and MR image pairs of the whole head.

Magnetic resonance (MR) images (MRI) are routinely acquired with high in-plane resolution and lower through-plane resolution. Improving the resolution of such data can be achieved through post-processing techniques knows as super-resolution (SR), with various frameworks in existence. Many of these approaches rely on external databases from which SR methods infer relationships between low and high resolution data. The concept of self super-resolution (SSR) has been previously reported, wherein there is no external training data with the method only relying on the acquired image. The approach involves extracting image patches from the acquired image constructing new images based on regression and combining the new images by Fourier Burst Accumulation. In this work, we present four improvements to our previously reported SSR approach. We demonstrate these improvements have a significant effect on improving image quality and the measured resolution.

Accurate automatic segmentation of brain anatomy from \(T_1\)-weighted (\(T_1\)-w) magnetic resonance images (MRI) has been a computationally intensive bottleneck in neuroimaging pipelines, with state-of-the-art results obtained by unsupervised intensity modeling-based methods and multi-atlas registration and label fusion. With the advent of powerful supervised convolutional neural networks (CNN)-based learning algorithms, it is now possible to produce a high quality brain segmentation within seconds. However, the very supervised nature of these methods makes it difficult to generalize them on data different from what they have been trained on. Modern neuroimaging studies are necessarily multi-center initiatives with a wide variety of acquisition protocols. Despite stringent protocol harmonization practices, it is not possible to standardize the whole gamut of MRI imaging parameters across scanners, field strengths, receive coils etc., that affect image contrast. In this paper we propose a CNN-based segmentation algorithm that, in addition to being highly accurate and fast, is also resilient to variation in the input \(T_1\)-w acquisition. Our approach relies on building approximate forward models of \(T_1\)-w pulse sequences that produce a typical test image. We use the forward models to augment the training data with test data specific training examples. These augmented data can be used to update and/or build a more robust segmentation model that is more attuned to the test data imaging properties. Our method generates highly accurate, state-of-the-art segmentation results (overall Dice overlap = 0.94), within seconds and is consistent across a wide-range of protocols.

It is faster and therefore cheaper to acquire magnetic resonance images (MRI) with higher in-plane resolution than through-plane resolution. The low resolution of such acquisitions can be increased using post-processing techniques referred to as super-resolution (SR) algorithms. SR is known to be an ill-posed problem. Most state-of-the-art SR algorithms rely on the presence of external/training data to learn a transform that converts low resolution input to a higher resolution output. In this paper an SR approach is presented that is not dependent on any external training data and is only reliant on the acquired image. Patches extracted from the acquired image are used to estimate a set of new images, where each image has increased resolution along a particular direction. The final SR image is estimated by combining images in this set via the technique of Fourier Burst Accumulation. Our approach was validated on simulated low resolution MRI images, and showed significant improvement in image quality and segmentation accuracy when compared to competing SR methods. SR of FLuid Attenuated Inversion Recovery (FLAIR) images with lesions is also demonstrated.

Accurate CT synthesis, sometimes called electron density estimation, from MRI is crucial for successful MRI-based radiotherapy planning and dose computation. Existing CT synthesis methods are able to synthesize normal tissues but are unable to accurately synthesize abnormal tissues (i.e., tumor), thus providing a suboptimal solution. We propose a multi-atlas-based hybrid synthesis approach that combines multi-atlas registration and patch-based synthesis to accurately synthesize both normal and abnormal tissues. Multi-parametric atlas MR images are registered to the target MR images by multi-channel deformable registration, from which the atlas CT images are deformed and fused by locally-weighted averaging using a structural similarity measure (SSIM). Synthetic MR images are also computed from the registered atlas MRIs by using the same weights used for the CT synthesis; these are compared to the target patient MRIs allowing for the assessment of the CT synthesis fidelity. Poor synthesis regions are automatically detected based on the fidelity measure and refined by a patch-based synthesis. The proposed approach was tested on brain cancer patient data, and showed a noticeable improvement for the tumor region.

The simulation of magnetic resonance (MR) images plays an important role in the validation of image analysis algorithms such as image segmentation, due to lack of sufficient ground truth in real MR images. Previous work on MRI simulation has focused on explicitly modeling the MR image formation process. However, because of the overwhelming complexity of MR acquisition these simulations must involve simplifications and approximations that can result in visually unrealistic simulated images. In this work, we describe an example-based simulation framework, which uses an “atlas” consisting of an MR image and its anatomical models derived from the hard segmentation. The relationships between the MR image intensities and its anatomical models are learned using a patch-based regression that implicitly models the physics of the MR image formation. Given the anatomical models of a new brain, a new MR image can be simulated using the learned regression. This approach has been extended to also simulate intensity inhomogeneity artifacts based on the statistical model of training data. Results show that the example based MRI simulation method is capable of simulating different image contrasts and is robust to different choices of atlas. The simulated images resemble real MR images more than simulations produced by a physics-based model.

Different magnetic resonance imaging pulse sequences are used to generate image contrasts based on physical properties of tissues, which provide different and often complementary information about them. Therefore multiple image contrasts are useful for multimodal analysis of medical images. Often, medical image processing algorithms are optimized for particular image contrasts. If a desirable contrast is unavailable, contrast synthesis (or modality synthesis) methods try to “synthesize” the unavailable constrasts from the available ones. Most of the recent image synthesis methods generate synthetic brain images, while whole head magnetic resonance (MR) images can also be useful for many applications. We propose an atlas based patch matching algorithm to synthesize \(T_2-\)w whole head (including brain, skull, eyes etc.) images from \(T_1-\)w images for the purpose of distortion correction of diffusion weighted MR images. The geometric distortion in diffusion MR images due to inhomogeneous \(B_0\) magnetic field are often corrected by non-linearly registering the corresponding \(b=0\) image with zero diffusion gradient to an undistorted \(T_2-\)w image. We show that our synthetic \(T_2-\)w images can be used as a template in absence of a real \(T_2-\)w image. Our patch based method requires multiple atlases with \(T_1\) and \(T_2\) to be registered to a given target \(T_1\). Then for every patch on the target, multiple similar looking matching patches are found on the atlas \(T_1\) images and corresponding patches on the atlas \(T_2\) images are combined to generate a synthetic \(T_2\) of the target. We experimented on image data obtained from 44 patients with traumatic brain injury (TBI), and showed that our synthesized \(T_2\) images produce more accurate distortion correction than a state-of-the-art registration based image synthesis method.

This paper presents a theoretical analysis of the effect of spatial resolution on image registration. Based on the assumption of additive Gaussian noise on the images, the mean and variance of the distribution of the sum of squared differences (SSD) were estimated. Using these estimates, we evaluate a distance between the SSD distributions of aligned images and non-aligned images. The experimental results show that by matching the resolutions of the moving and fixed images one can get a better image registration result. The results agree with our theoretical analysis of SSD, but also suggest that it may be valid for mutual information as well.

Multiple Sclerosis (MS) is a disease of the central nervous system in which the protective myelin sheath of the neurons is damaged. MS leads to the formation of lesions, predominantly in the white matter of the brain and the spinal cord. The number and volume of lesions visible in magnetic resonance (MR) imaging (MRI) are important criteria for diagnosing and tracking the progression of MS. Locating and delineating lesions manually requires the tedious and expensive efforts of highly trained raters. In this paper, we propose an automated algorithm to segment lesions in MR images using multi-output decision trees. We evaluated our algorithm on the publicly available MICCAI 2008 MS Lesion Segmentation Challenge training dataset of 20 subjects, and showed improved results in comparison to state-of-the-art methods. We also evaluated our algorithm on an in-house dataset of 49 subjects with a true positive rate of 0.41 and a positive predictive value 0.36.

Contains fulltext : 173122.pdf (Publisher’s version ) (Closed access) In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

Objectives/Hypothesis: To develop a robotic surgery training regimen integrating objective skill assessment for otolaryngology and head and neck surgery trainees consisting of training modules of increasing complexity leading up to procedure-specific training. In particular, we investigated applications of such a training approach for surgical extirpation of oropharyngeal tumors via a transoral approach using the da Vinci robotic system. Study Design: Prospective blinded data collection and objective evaluation (Objective Structured Assessment of Technical Skills [OSATS]) of three distinct phases using the da Vinci robotic surgical system in an academic university medical engineering/computer science laboratory setting. Methods: Between September 2010 and July 2011, eight otolaryngology–head and neck surgery residents and four staff experts from an academic hospital participated in three distinct phases of robotic surgery training involving 1) robotic platform operational skills, 2) set up of the patient side system, and 3) a complete ex vivo surgical extirpation of an oropharyngeal tumor located in the base of tongue. Trainees performed multiple (four) approximately equally spaced training sessions in each stage of the training. In addition to trainees, baseline performance data were obtained for the experts. Each surgical stage was documented with motion and event data captured from the application programming interfaces of the da Vinci system, as well as separate video cameras as appropriate. All data were assessed using automated skill measures of task efficiency and correlated with structured assessment (OSATS and similar Likert scale) from three experts to assess expert and trainee differences and compute automated and expert assessed learning curves. Results: Our data show that such training results in an improved didactic robotic knowledge base and improved clinical efficiency with respect to the set up and console manipulation. Experts (e.g., average OSATS, 25; standard deviation [SD], 3.1; module 1, suturing) and trainees (average OSATS, 15.9; SD, 3.9; week 1) are well separated at the beginning of the training, and the separation reduces significantly (expert average OSATS, 27.6; SD, 2.7; trainee average OSATS, 24.2; SD, 6.8; module 3) at the conclusion of the training. Learning curves in each of the three stages show diminishing differences between the experts and trainees, which is also consistent with expert assessment. Subjective assessment by experts verified the clinical utility of the module 3 surgical environment, and a survey of trainees consistently rated the curriculum as very useful in progression to human operating room assistance. Conclusions: Structured curricular robotic surgery training with objective assessment promises to reduce the overhead for mentors, allow detailed assessment of human-machine interface skills, and create customized training models for individualized training. This preliminary study verifies the utility of such training in improving human-machine operations skills (module 1), and operating room and surgical skills (modules 2 and 3). In contrast to current coarse measures of total operating time and subjective assessment of error for short mass training sessions, these methods may allow individual tasks to be removed from the trainee regimen when skill levels are within the standard deviation of the experts for these tasks, which can greatly enhance overall efficiency of the training regimen and allow time for additional and more complex training to be incorporated in the same time frame. Laryngoscope, 2012

Objectives Current robotic training approaches lack the criteria for automatically assessing and tracking (over time) technical skills separately from clinical proficiency. We describe the development and validation of a novel automated and objective framework for the assessment of training. Methods We are able to record all system variables (stereo instrument video, hand and instrument motion, buttons and pedal events) from the da Vinci surgical systems using a portable archival system integrated with the robotic surgical system. Data can be collected unsupervised, and the archival system does not change system operations in any way. Our open-ended multicenter protocol is collecting surgical skill benchmarking data from 24 trainees to surgical proficiency, subject only to their continued availability. Two independent experts performed structured (objective structured assessment of technical skills) assessments on longitudinal data from 8 novice and 4 expert surgeons to generate baseline data for training and to validate our computerized statistical analysis methods in identifying the ranges of operational and clinical skill measures. Results Objective differences in operational and technical skill between known experts and other subjects were quantified. The longitudinal learning curves and statistical analysis for trainee performance measures are reported. Graphic representations of the skills developed for feedback to the trainees are also included. Conclusions We describe an open-ended longitudinal study and automated motion recognition system capable of objectively differentiating between clinical and technical operational skills in robotic surgery. Our results have demonstrated a convergence of trainee skill parameters toward those derived from expert robotic surgeons during the course of our training protocol.

Background With increased use of robotic surgery in specialties including urology, development of training methods has also intensified. However, current approaches lack the ability to discriminate between operational and surgical skills. Methods An automated recording system was used to longitudinally (monthly) acquire instrument motion/telemetry and video for four basic surgical skills – suturing, manipulation, transection, and dissection. Statistical models were then developed to discriminate the human–machine skill differences between practicing expert surgeons and trainees. Results Data from six trainees and two experts was analyzed to validate the first ever statistical models of operational skills, and demonstrate classification with very high accuracy (91.7% for masters, and 88.2% for camera motion) and sensitivity. Conclusions The paper reports on a longitudinal study aimed at tracking robotic surgery trainees to proficiency, and methods capable of objectively assessing operational and technical skills that would be used in assessing trainee progress at the participating institutions. Copyright © 2011 John Wiley & Sons, Ltd.

Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi) automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65-80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand., This study was financially supported by IMDI Grant 104002002 (Brainbox) from ZonMw, the Netherlands Organisation for Health Research and Development, within kind sponsoring by Philips, the University Medical Center Utrecht, and Eindhoven University of Technology. The authors would like to acknowledge the following members of the Utrecht Vascular Cognitive Impairment Study Group who were not included as coauthors of this paper but were involved in the recruitment of study participants and MRI acquisition at the UMC Utrecht (in alphabetical order by department): E. van den Berg, M. Brundel, S. Heringa, and L. J. Kappelle of the Department of Neurology, P. R. Luijten and W. P. Th. M. Mali of the Department of Radiology, and A. Algra and G. E. H. M. Rutten of the Julius Center for Health Sciences and Primary Care. The research of Geert Jan Biessels and the VCI group was financially supported by VIDI Grant 91711384 from ZonMw and by Grant 2010T073 of the Netherlands Heart Foundation. The research of Jeroen de Bresser is financially supported by a research talent fellowship of the University Medical Center Utrecht (Netherlands). The research of Annegreet van Opbroek and Marleen de Bruijne is financially supported by a research grant from NWO (the Netherlands Organisation for Scientific Research). The authors would like to acknowledge MeVis Medical Solutions AG (Bremen, Germany) for providing MeVisLab. Duygu Sarikaya and Liang Zhao acknowledge their Advisor Professor Jason Corso for his guidance. Duygu Sarikaya is supported by NIH 1 R21CA160825-01 and Liang Zhao is partially supported by the China Scholarship Council (CSC)., info:eu-repo/semantics/publishedVersion

Cerebral microbleeds (CMB) are a common marker of traumatic brain injury. Accurate detection and quantification of the CMBs are important for better understanding the progression and prognosis of the injury. Previous microbleed detection methods have suffered from a high rate of false positives, which is time consuming to manually correct. In this paper, we propose a fully automatic, example-based method to segment CMBs from susceptibility-weighted (SWI) scans, where examples from an already segmented template SWI image are used to detect CMBs in a new image. First, multiple radial symmetry transforms (RST) are performed on the template SWI to detect small ellipsoidal structures, which serve as potential microbleed candidates. Then 3D patches from the SWI and its RSTs are combined to form a feature vector at each voxel of the image. A random forest regression is trained using the feature vectors, where the dependent variable is the binary segmentation voxel of the template. Once the regression is learnt, it is applied to a new SWI scan, whose feature vectors contain patches from SWI and its RSTs. Experiments on 26 subjects with mild to severe brain injury show a CMB detection sensitivity of 85:7%, specificity 99:5%, and a false positive to true positive ratio of 1:73, which is competitive with published methods while providing a significant reduction in computation time.