Object and Scene Classification: what does a Supervised Approach Provide us?

Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one

Computational anatomy for studying use-dependant brain plasticity.

In this article we provide a comprehensive literature review on the in vivo assessment of use-dependant brain structure changes in humans using magnetic resonance imaging (MRI) and computational anatomy. We highlight the recent findings in this field that allow the uncovering of the basic principles behind brain plasticity in light of the existing theoretical models at various scales of observation. Given the current lack of in-depth understanding of the neurobiological basis of brain structure changes we emphasize the necessity of a paradigm shift in the investigation and interpretation of use-dependent brain plasticity. Novel quantitative MRI acquisition techniques provide access to brain tissue microstructural properties (e.g., myelin, iron, and water content) in-vivo, thereby allowing unprecedented specific insights into the mechanisms underlying brain plasticity. These quantitative MRI techniques require novel methods for image processing and analysis of longitudinal data allowing for straightforward interpretation and causality inferences.

Atlas-based segmentation of pathological brain MR images

We propose a method for brain atlas deformation inpresence of large space-occupying tumors, based on an apriori model of lesion growth that assumes radialexpansion of the lesion from its starting point. First,an affine registration brings the atlas and the patientinto global correspondence. Then, the seeding of asynthetic tumor into the brain atlas provides a templatefor the lesion. Finally, the seeded atlas is deformed,combining a method derived from optical flow principlesand a model of lesion growth (MLG). Results show that themethod can be applied to the automatic segmentation ofstructures and substructures in brains with grossdeformation, with important medical applications inneurosurgery, radiosurgery and radiotherapy.

Event-related potential analyses via single-subject topographic classification.

Introduction: Responses to external stimuli are typically investigated by averaging peri-stimulus electroencephalography (EEG) epochs in order to derive event-related potentials (ERPs) across the electrode montage, under the assumption that signals that are related to the external stimulus are fixed in time across trials. We demonstrate the applicability of a single-trial model based on patterns of scalp topographies (De Lucia et al, 2007) that can be used for ERP analysis at the single-subject level. The model is able to classify new trials (or groups of trials) with minimal a priori hypotheses, using information derived from a training dataset. The features used for the classification (the topography of responses and their latency) can be neurophysiologically interpreted, because a difference in scalp topography indicates a different configuration of brain generators. An above chance classification accuracy on test datasets implicitly demonstrates the suitability of this model for EEG data. Methods: The data analyzed in this study were acquired from two separate visual evoked potential (VEP) experiments. The first entailed passive presentation of checkerboard stimuli to each of the four visual quadrants (hereafter, "Checkerboard Experiment") (Plomp et al, submitted). The second entailed active discrimination of novel versus repeated line drawings of common objects (hereafter, "Priming Experiment") (Murray et al, 2004). Four subjects per experiment were analyzed, using approx. 200 trials per experimental condition. These trials were randomly separated in training (90%) and testing (10%) datasets in 10 independent shuffles. In order to perform the ERP analysis we estimated the statistical distribution of voltage topographies by a Mixture of Gaussians (MofGs), which reduces our original dataset to a small number of representative voltage topographies. We then evaluated statistically the degree of presence of these template maps across trials and whether and when this was different across experimental conditions. Based on these differences, single-trials or sets of a few single-trials were classified as belonging to one or the other experimental condition. Classification performance was assessed using the Receiver Operating Characteristic (ROC) curve. Results: For the Checkerboard Experiment contrasts entailed left vs. right visual field presentations for upper and lower quadrants, separately. The average posterior probabilities, indicating the presence of the computed template maps in time and across trials revealed significant differences starting at ~60-70 ms post-stimulus. The average ROC curve area across all four subjects was 0.80 and 0.85 for upper and lower quadrants, respectively and was in all cases significantly higher than chance (unpaired t-test, p<0.0001). In the Priming Experiment, we contrasted initial versus repeated presentations of visual object stimuli. Their posterior probabilities revealed significant differences, which started at 250ms post-stimulus onset. The classification accuracy rates with single-trial test data were at chance level. We therefore considered sub-averages based on five single trials. We found that for three out of four subjects' classification rates were significantly above chance level (unpaired t-test, p<0.0001). Conclusions: The main advantage of the present approach is that it is based on topographic features that are readily interpretable along neurophysiologic lines. As these maps were previously normalized by the overall strength of the field potential on the scalp, a change in their presence across trials and between conditions forcibly reflects a change in the underlying generator configurations. The temporal periods of statistical difference between conditions were estimated for each training dataset for ten shuffles of the data. Across the ten shuffles and in both experiments, we observed a high level of consistency in the temporal periods over which the two conditions differed. With this method we are able to analyze ERPs at the single-subject level providing a novel tool to compare normal electrophysiological responses versus single cases that cannot be considered part of any cohort of subjects. This aspect promises to have a strong impact on both basic and clinical research.

Predicting clinical scores from magnetic resonance scans in Alzheimer's disease.

Machine learning and pattern recognition methods have been used to diagnose Alzheimer's disease (AD) and mild cognitive impairment (MCI) from individual MRI scans. Another application of such methods is to predict clinical scores from individual scans. Using relevance vector regression (RVR), we predicted individuals' performances on established tests from their MRI T1 weighted image in two independent data sets. From Mayo Clinic, 73 probable AD patients and 91 cognitively normal (CN) controls completed the Mini-Mental State Examination (MMSE), Dementia Rating Scale (DRS), and Auditory Verbal Learning Test (AVLT) within 3months of their scan. Baseline MRI's from the Alzheimer's disease Neuroimaging Initiative (ADNI) comprised the other data set; 113 AD, 351 MCI, and 122 CN subjects completed the MMSE and Alzheimer's Disease Assessment Scale-Cognitive subtest (ADAS-cog) and 39 AD, 92 MCI, and 32 CN ADNI subjects completed MMSE, ADAS-cog, and AVLT. Predicted and actual clinical scores were highly correlated for the MMSE, DRS, and ADAS-cog tests (P<0.0001). Training with one data set and testing with another demonstrated stability between data sets. DRS, MMSE, and ADAS-Cog correlated better than AVLT with whole brain grey matter changes associated with AD. This result underscores their utility for screening and tracking disease. RVR offers a novel way to measure interactions between structural changes and neuropsychological tests beyond that of univariate methods. In clinical practice, we envision using RVR to aid in diagnosis and predict clinical outcome.

Assessment of a new MRI classification of spinal stenosis based on cross-sectional morphology of the dural sac : FM2

Introduction: Quantitative measures of degree of lumbar spinal stenosis (LSS) such as antero-posterior diameter of the canal or dural sac cross sectional area vary widely and do not correlate with clinical symptoms or results of surgical decompression. In an effort to improve quantification of stenosis we have developed a grading system based on the morphology of the dural sac and its contents as seen on T2 axial images. The grading comprises seven categories ranging form normal to the most severe stenosis and takes into account the ratio of rootlet/CSF content. Material and methods: Fifty T2 axial MRI images taken at disc level from twenty seven symptomatic lumbar spinal stenosis patients who underwent decompressive surgery were classified into seven categories by five observers and reclassified 2 weeks later by the same investigators. Intra- and inter-observer reliability of the classification were assessed using Cohen's and Fleiss' kappa statistics, respectively. Results: Generally, the morphology grading system itself was well adopted by the observers. Its success in application is strongly influenced by the identification of the dural sac. The average intraobserver Cohen's kappa was 0.53 ± 0.2. The inter-observer Fleiss' kappa was 0.38 ± 0.02 in the first rating and 0.3 ± 0.03 in the second rating repeated after two weeks. Discussion: In this attempt, the teaching of the observers was limited to an introduction to the general idea of the morphology grading system and one example MRI image per category. The identification of the dimension of the dural sac may be a difficult issue in absence of complete T1 T2 MRI image series as it was the case here. The similarity of the CSF to possibly present fat on T2 images was the main reason of mismatch in the assignment of the cases to a category. The Fleiss correlation factors of the five observers are fair and the proposed morphology grading system is promising.

The brain uses single-trial multisensory memories to discriminate without awareness.

Multisensory experiences enhance perceptions and facilitate memory retrieval processes, even when only unisensory information is available for accessing such memories. Using fMRI, we identified human brain regions involved in discriminating visual stimuli according to past multisensory vs. unisensory experiences. Subjects performed a completely orthogonal task, discriminating repeated from initial image presentations intermixed within a continuous recognition task. Half of initial presentations were multisensory, and all repetitions were exclusively visual. Despite only single-trial exposures to initial image presentations, accuracy in indicating image repetitions was significantly improved by past auditory-visual multisensory experiences over images only encountered visually. Similarly, regions within the lateral-occipital complex-areas typically associated with visual object recognition processes-were more active to visual stimuli with multisensory than unisensory pasts. Additional differential responses were observed in the anterior cingulate and frontal cortices. Multisensory experiences are registered by the brain even when of no immediate behavioral relevance and can be used to categorize memories. These data reveal the functional efficacy of multisensory processing.

Robust T1-Weighted Structural Brain Imaging and Morphometry at 7T Using MP2RAGE.

PURPOSE: To suppress the noise, by sacrificing some of the signal homogeneity for numerical stability, in uniform T1 weighted (T1w) images obtained with the magnetization prepared 2 rapid gradient echoes sequence (MP2RAGE) and to compare the clinical utility of these robust T1w images against the uniform T1w images. MATERIALS AND METHODS: 8 healthy subjects (29.0±4.1 years; 6 Male), who provided written consent, underwent two scan sessions within a 24 hour period on a 7T head-only scanner. The uniform and robust T1w image volumes were calculated inline on the scanner. Two experienced radiologists qualitatively rated the images for: general image quality; 7T specific artefacts; and, local structure definition. Voxel-based and volume-based morphometry packages were used to compare the segmentation quality between the uniform and robust images. Statistical differences were evaluated by using a positive sided Wilcoxon rank test. RESULTS: The robust image suppresses background noise inside and outside the skull. The inhomogeneity introduced was ranked as mild. The robust image was significantly ranked higher than the uniform image for both observers (observer 1/2, p-value = 0.0006/0.0004). In particular, an improved delineation of the pituitary gland, cerebellar lobes was observed in the robust versus uniform T1w image. The reproducibility of the segmentation results between repeat scans improved (p-value = 0.0004) from an average volumetric difference across structures of ≈6.6% to ≈2.4% for the uniform image and robust T1w image respectively. CONCLUSIONS: The robust T1w image enables MP2RAGE to produce, clinically familiar T1w images, in addition to T1 maps, which can be readily used in uniform morphometry packages.

Noise in Brain Activity Engenders Perception and Influences Discrimination Sensitivity.

Behavioral and brain responses to identical stimuli can vary with experimental and task parameters, including the context of stimulus presentation or attention. More surprisingly, computational models suggest that noise-related random fluctuations in brain responses to stimuli would alone be sufficient to engender perceptual differences between physically identical stimuli. In two experiments combining psychophysics and EEG in healthy humans, we investigated brain mechanisms whereby identical stimuli are (erroneously) perceived as different (higher vs lower in pitch or longer vs shorter in duration) in the absence of any change in the experimental context. Even though, as expected, participants' percepts to identical stimuli varied randomly, a classification algorithm based on a mixture of Gaussians model (GMM) showed that there was sufficient information in single-trial EEG to reliably predict participants' judgments of the stimulus dimension. By contrasting electrical neuroimaging analyses of auditory evoked potentials (AEPs) to the identical stimuli as a function of participants' percepts, we identified the precise timing and neural correlates (strength vs topographic modulations) as well as intracranial sources of these erroneous perceptions. In both experiments, AEP differences first occurred ∼100 ms after stimulus onset and were the result of topographic modulations following from changes in the configuration of active brain networks. Source estimations localized the origin of variations in perceived pitch of identical stimuli within right temporal and left frontal areas and of variations in perceived duration within right temporoparietal areas. We discuss our results in terms of providing neurophysiologic evidence for the contribution of random fluctuations in brain activity to conscious perception.

Analysis of acute brain slices by electron microscopy: A correlative light-electron microscopy workflow based on Tokuyasu cryo-sectioning.

Acute brain slices are slices of brain tissue that are kept vital in vitro for further recordings and analyses. This tool is of major importance in neurobiology and allows the study of brain cells such as microglia, astrocytes, neurons and their inter/intracellular communications via ion channels or transporters. In combination with light/fluorescence microscopies, acute brain slices enable the ex vivo analysis of specific cells or groups of cells inside the slice, e.g. astrocytes. To bridge ex vivo knowledge of a cell with its ultrastructure, we developed a correlative microscopy approach for acute brain slices. The workflow begins with sampling of the tissue and precise trimming of a region of interest, which contains GFP-tagged astrocytes that can be visualised by fluorescence microscopy of ultrathin sections. The astrocytes and their surroundings are then analysed by high resolution scanning transmission electron microscopy (STEM). An important aspect of this workflow is the modification of a commercial cryo-ultramicrotome to observe the fluorescent GFP signal during the trimming process. It ensured that sections contained at least one GFP astrocyte. After cryo-sectioning, a map of the GFP-expressing astrocytes is established and transferred to correlation software installed on a focused ion beam scanning electron microscope equipped with a STEM detector. Next, the areas displaying fluorescence are selected for high resolution STEM imaging. An overview area (e.g. a whole mesh of the grid) is imaged with an automated tiling and stitching process. In the final stitched image, the local organisation of the brain tissue can be surveyed or areas of interest can be magnified to observe fine details, e.g. vesicles or gold labels on specific proteins. The robustness of this workflow is contingent on the quality of sample preparation, based on Tokuyasu's protocol. This method results in a reasonable compromise between preservation of morphology and maintenance of antigenicity. Finally, an important feature of this approach is that the fluorescence of the GFP signal is preserved throughout the entire preparation process until the last step before electron microscopy.

Reliability of the image evaluation system PGMI

Purpose: Many countries used the PGMI (P=perfect, G=good, M=moderate, I=inadequate) classification system for assessing the quality of mammograms. Limits inherent to the subjectivity of this classification have been shown. Prior to introducing this system in Switzerland, we wanted to better understand the origin of this subjectivity in order to minimize it. Our study aimed at identifying the main determinants of the variability of the PGMI system and which criteria are the most subjected to subjectivity. Methods and Materials: A focus group composed of 2 experienced radiographers and 2 radiologists specified each PGMI criterion. Ten raters (6 radiographers and 4 radiologists) evaluated twice a panel of 40 randomly selected mammograms (20 analogic and 20 digital) according to these specified PGMI criteria. The PGMI classification was assessed and the intra- and inter-rater reliability was tested for each professional group (radiographer vs radiologist), image technology (analogic vs digital) and PGMI criterion. Results: Some 3,200 images were assessed. The intra-rater reliability appears to be weak, particularly in respect to inter-rater variability. Subjectivity appears to be largely independent of the professional group and image technology. Aspects of the PGMI classification criteria most subjected to variability were identified. Conclusion: Post-test discussions enabled to specify more precisely some criteria. This should reduce subjectivity when applying the PGMI classification system. A concomitant, important effort in training radiographers is also necessary.

Atlas-based segmentation of pathological MR brain images using a model of lesion growth.

We propose a method for brain atlas deformation in the presence of large space-occupying tumors, based on an a priori model of lesion growth that assumes radial expansion of the lesion from its starting point. Our approach involves three steps. First, an affine registration brings the atlas and the patient into global correspondence. Then, the seeding of a synthetic tumor into the brain atlas provides a template for the lesion. The last step is the deformation of the seeded atlas, combining a method derived from optical flow principles and a model of lesion growth. Results show that a good registration is performed and that the method can be applied to automatic segmentation of structures and substructures in brains with gross deformation, with important medical applications in neurosurgery, radiosurgery, and radiotherapy.

Dense deformation field estimation for atlas-based segmentation of pathological MR brain images.

Atlas registration is a recognized paradigm for the automatic segmentation of normal MR brain images. Unfortunately, atlas-based segmentation has been of limited use in presence of large space-occupying lesions. In fact, brain deformations induced by such lesions are added to normal anatomical variability and they may dramatically shift and deform anatomically or functionally important brain structures. In this work, we chose to focus on the problem of inter-subject registration of MR images with large tumors, inducing a significant shift of surrounding anatomical structures. First, a brief survey of the existing methods that have been proposed to deal with this problem is presented. This introduces the discussion about the requirements and desirable properties that we consider necessary to be fulfilled by a registration method in this context: To have a dense and smooth deformation field and a model of lesion growth, to model different deformability for some structures, to introduce more prior knowledge, and to use voxel-based features with a similarity measure robust to intensity differences. In a second part of this work, we propose a new approach that overcomes some of the main limitations of the existing techniques while complying with most of the desired requirements above. Our algorithm combines the mathematical framework for computing a variational flow proposed by Hermosillo et al. [G. Hermosillo, C. Chefd'Hotel, O. Faugeras, A variational approach to multi-modal image matching, Tech. Rep., INRIA (February 2001).] with the radial lesion growth pattern presented by Bach et al. [M. Bach Cuadra, C. Pollo, A. Bardera, O. Cuisenaire, J.-G. Villemure, J.-Ph. Thiran, Atlas-based segmentation of pathological MR brain images using a model of lesion growth, IEEE Trans. Med. Imag. 23 (10) (2004) 1301-1314.]. Results on patients with a meningioma are visually assessed and compared to those obtained with the most similar method from the state-of-the-art.

Efficiency and safety of bilateral contemporaneous pallidal stimulation (deep brain stimulation) in levodopa-responsive patients with Parkinson's disease with severe motor fluctuations: a 2-year follow-up review.

OBJECT: The aim of this study was to evaluate the long-term safety and efficacy of bilateral contemporaneous deep brain stimulation (DBS) in patients who have levodopa-responsive parkinsonism with untreatable motor fluctuations. Bilateral pallidotomy carries a high risk of corticobulbar and cognitive dysfunction. Deep brain stimulation offers new alternatives with major advantages such as reversibility of effects, minimal permanent lesions, and adaptability to individual needs, changes in medication, side effects, and evolution of the disease. METHODS: Patients in whom levodopa-responsive parkinsonism with untreatable severe motor fluctuations has been clinically diagnosed underwent bilateral pallidal magnetic resonance image-guided electrode implantation while receiving a local anesthetic. Pre- and postoperative evaluations at 3-month intervals included Unified Parkinson's Disease Rating Scale (UPDRS) scoring, Hoehn and Yahr staging, 24-hour self-assessments, and neuropsychological examinations. Six patients with a mean age of 55 years (mean 42-67 years), a mean duration of disease of 15.5 years (range 12-21 years), a mean "on/off' Hoehn and Yahr stage score of 3/4.2 (range 3-5), and a mean "off' time of 40% (range 20-50%) underwent bilateral contemporaneous pallidal DBS, with a minimum follow-up period lasting 24 months (range 24-30 months). The mean dose of levodopa in these patients could not be changed significantly after the procedure and pergolide was added after 12 months in five patients because of recurring fluctuations despite adjustments in stimulation parameters. All but two patients had no fluctuations until 9 months. Two of the patients reported barely perceptible fluctuations at 12 months and two at 15 months; however, two patients remain without fluctuations at 2 years. The mean improvements in the UPDRS motor score in the off time and the activities of daily living (ADL) score were more than 50%; the mean off time decreased from 40 to 10%, and the mean dyskinesia and complication of treatment scores were reduced to one-third until pergolide was introduced at 12 months. No significant improvement in "on" scores was observed. A slight worsening after 1 year was observed and three patients developed levodopa- and stimulation-resistant gait ignition failure and minimal fluctuations at 1 year. Side effects, which were controlled by modulation of stimulation, included dysarthria, dystonia, and confusion. CONCLUSIONS: Bilateral pallidal DBS is safe and efficient in patients who have levodopa-responsive parkinsonism with severe fluctuations. Major improvements in motor score, ADL score, and off time persisted beyond 2 years after the operation, but signs of decreased efficacy started to be seen after 12 months.