Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

https://wiki.biac.duke.edu/lib/exe/fetch.php?media=biac:jones_etal_2012_the_do_s_and_don_ts_of_diffusion_mri.pdf

White matter integrity, fiber count, and other fallacies: The do's and don'ts of diffusion MRI

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Thank you very much for reading statistical parametric mapping the analysis of functional brain images. As you may know, people have search numerous times for their chosen novels like this statistical parametric mapping the analysis of functional brain images, but end up in malicious downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they cope with some infectious bugs inside their desktop computer.

Statistical Parametric Mapping The Analysis Of Functional Brain Images

Motoneurons (MNs) are neuronal cells involved in several central nervous system (CNS) diseases. In order to develop new treatments and therapies, there is a need to understand MN organization and differentiation. Although recently developed embryo mouse models have enabled the investigation of the MN specialization process, more robust and reproducible methods are required to evaluate the topology and structure of the neuron bundles. In this article, we propose a new fully automatic approach to identify MN clusters from stained histological slices. We developed a specific workflow including inter-slice intensity normalization and slice registration for 3D volume reconstruction, which enables the segmentation, mapping and 3D visualization of MN bundles. Such tools will facilitate the understanding of MN organization, differentiation and function.

/pdf/robust-3d-reconstruction-and-mean-shift-clustering-of-1lgx2h4i11.pdf

Robust 3D reconstruction and mean-shift clustering of motoneurons from serial histological images

Early diagnosis is one of the most important challenges related to Alzheimer's disease (AD). To address this issue, numerous studies proposed biomarkers based on anatomical MRI. Among them, patch-based grading demonstrated state-of-the-art results when applied to T1-weighted MRI. In this work, we propose to use a similar framework on dierent diusion parameters extracted from DTI. We also propose to use a fast patch-based search strategy to provide novel biomarkers for the early detection of AD. We intensively compare our new grading-based DTI features with basic MRI/DTI biomarkers and evaluate our method within a cross validation classication framework. Finally, we demonstrate that the proposed biomarkers obtain competitive results for the identication of the dierent stages of AD.

https://hal.archives-ouvertes.fr/hal-01395487/document

Patch-based DTI grading: Application to Alzheimer's disease classication

Brain imaging studies have shown that progressive cerebral atrophy characterized the development of Alzheimer9s Disease (AD). The key question is how long before the diagnosis of AD the neurodegenerative process started leading to these structural alterations. To answer this question, we proposed an innovative way by inferring brain structure volume trajectories across the entire lifespan using massive number of MRI (N=4714). Our study provides evidences of early divergence of the AD model from the control model for the hippocampus before 40 years, followed by the lateral ventricles and the amygdala around 40 years for the AD model. Moreover, our lifespan investigation reveals the dynamic of the evolution of these biomarkers and suggest close abnormality trajectories for the hippocampus and the amygdala. Finally, our results highlight that the temporal lobe atrophy, a key biomarker in AD, is a very early pathophysiological event potentially associated to early life exposures to risk factors.

/pdf/timeline-of-brain-alterations-in-alzheimer-s-disease-across-hokiu4my7m.pdf

Timeline of brain alterations in alzheimer’s disease across the entire lifespan

An image processing device comprises a store ( 110 ) for receiving image data ( 8 ) with a pixel identifier and at least one piece of associated intensity data and a pilot ( 100 ) which is provided to call a reduction unit ( 120 ) with pixels to be weighted and, for each pixel, in order to define a first neighborhood and a plurality of second neighborhoods with a neighborhood selection unit ( 130 ), in order to obtain a weighting value for the second neighborhood with a weighting unit ( 140 ) with the first neighborhood and a neighborhood among the plurality of second neighborhoods, in order to define each time a piece of weighted intensity data of a working pixel as the weighting value of the second neighborhood multiplied by the intensity data of the associated working pixel, and in order to define a piece of weighted intensity data of the pixel to be weighted by adding each of the pieces of weighted intensity data of a working pixel. The weighting unit ( 140 ) is provided to calculate the distance between first and second neighborhoods on the basis of a sum, where each square of the difference between the respective intensity data of these neighborhoods is modulated by a quantity which is inversely proportional to the intensity data in the second neighborhood.

Image denoising device

The improvements in magnetic resonance imaging have led to the development of numerous techniques to better detect structural alterations caused by neurodegenerative diseases. Among these, the patch-based grading framework has been proposed to model local patterns of anatomical changes. This approach is attractive because of its low computational cost and its competitive performance. Other studies have proposed to analyze the deformations of brain structures using tensor-based morphometry, which is a highly interpretable approach. In this work, we propose to combine the advantages of these two approaches by extending the patch-based grading framework with a new tensor-based grading method that enables us to model patterns of local deformation using a log-Euclidean metric. We evaluate our new method in a study of the putamen for the classification of patients with pre-manifest Huntington's disease and healthy controls. Our experiments show a substantial increase in classification accuracy (87.5 ± 0.5 vs. 81.3 ± 0.6) compared to the existing patch-based grading methods, and a good complement to putamen volume, which is a primary imaging-based marker for the study of Hunting-ton's disease.

https://hal.archives-ouvertes.fr/hal-02450401/document

Pierrick Coupé

Papers

Robust 3D reconstruction and mean-shift clustering of motoneurons from serial histological images

Patch-based DTI grading: Application to Alzheimer's disease classication

Timeline of brain alterations in alzheimer’s disease across the entire lifespan

Image denoising device

Tensor-Based Grading: A Novel Patch-Based Grading Approach for the Analysis Of Deformation Fields in Huntington's Disease