scholarly journals Features Determination from Super-Voxels Obtained with Relative Linear Interactive Clustering

2016 ◽  
Vol 21 (3) ◽  
pp. 69-79 ◽  
Author(s):  
Abdelkhalek Bakkari ◽  
Anna Fabijańska
Keyword(s):  
Computational Cost ◽  
Brain Images ◽  
3D Images ◽  
New Approach ◽  
Magnetic Resonance Imaging Mri ◽  
Ct Brain ◽  
Interactive Clustering ◽  
The Brain ◽  
Low Computational Cost ◽  
3D Magnetic Resonance Imaging

Abstract In this paper, the problem of segmentation of 3D Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) brain images is considered. A supervoxel-based segmentation is regarded. In particular, a new approach called Relative Linear Interactive Clustering (RLIC) is introduced. The method, dedicated to image division into super-voxels, is an extension of the Simple Linear Interactive Clustering (SLIC) super-pixels algorithm. During RLIC execution firstly, the cluster centres and the regular grid size are initialized. These are next clustered by Fuzzy C-Means algorithm. Then, the extraction of the super-voxels statistical features is performed. The method contributes with 3D images and serves fully volumetric image segmentation. Five cases are tested demonstrating that our Relative Linear Interactive Clustering (RLIC) is apt to handle huge size of images with a significant accuracy and a low computational cost. The results of applying the suggested method to segmentation of the brain tumour are exposed and discussed.

The Truth, The Whole Truth, and Statistical Parametric Maps

CNS Spectrums ◽  
2001 ◽  
Vol 6 (8) ◽  
pp. 644-644
Author(s):  
Michael Trimble
Keyword(s):  
Resonance Imaging ◽  
Repeated Testing ◽  
Brain Images ◽  
Technical Developments ◽  
Positron Emission ◽  
Functional Images ◽  
Temporal And Spatial ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain ◽  
Parametric Maps

Over 20 years ago, Monte Buchsbaum first presented metabolic brain images belonging to a patient with schizophrenia at the American Psychiatric Association's annual meeting. This was a truly remarkable achievement brought about by the combined skills of the deoxyglucose technique developed by Lou Sokoloff and colleagues, and the advancement of statistical algorithms for the analysis of computerized images. Positron emission tomography (PET) had arrived, but more importantly, the imaging era of neuropsychiatry was dawning. Since then, we have been treated to a glorious array of technical developments which has seen not only coregistration of functional images (ie, PET) with corresponding structure (magnetic resonance imaging [MRI]), but a proliferation of MRI techniques that allow not only temporal and spatial resolutions undreamed of two decades ago, but permit safe, repeated testing of patients, allowing for experiments of considerable sophistication to be designed.Now, at any neuroscience meeting, many presentations are accompanied by brain images, often PETs. However, more and more often now we are seeing one form or another of MRI. Such images are displayed from various angles, adorned with multiple colors, and garnished with institutional logos, confirming (and less regularly refuting) the presenter's hypothesis about how the brain is supposed to work in relation to various cerebral functions.

Understanding Stroke

2012 ◽  
Author(s):  
Christopher R. Burton ◽  
Caroline Smith
Keyword(s):  
Evidence Synthesis ◽  
Comprehensive Overview ◽  
Focal Neurological Deficit ◽  
Initial Event ◽  
Brain Scan ◽  
Magnetic Resonance Imaging Mri ◽  
Health Nursing ◽  
Ct Brain ◽  
Health Organization ◽  
The Brain

The aim of this chapter is to provide nurses with the knowledge to be able to assess, manage, and care for people with stroke in an evidence-based and person-centred way. The chapter will provide a comprehensive overview of the seven stages of stroke, exploring best practice to deliver care, as well as to prevent or minimize further ill-health. Nursing assessments and priorities are highlighted throughout, and the nursing management of the symptoms and common health problems associated with stroke can be found in Chapters 23, 24, and 27, respectively. Stroke is defined as the rapid onset of focal neurological deficit lasting more than 24 hours (in which the patient survives the initial event), with no apparent cause other than disruption of blood supply to the brain (World Health Organization, 1978). As well as being the third commonest cause of death only in middle- and high-income countries (WHO, 1978) (along with cancer and heart disease), stroke is the largest cause of adult physical disability in the world (Bath and Lees, 2000). However, owing to advances in research and evidence synthesis, stroke is now a preventable and treatable disease (National Collaborating Centre for Chronic Conditions (NCCC), 2008). Despite its relative small weight (approximately 2% of body weight), the brain requires 750 ml of bloodflow every minute, and consumes nearly 45% of arterial oxygen (Alexandrov, 2003). Bloodflow to the brain is assured through two circulatory systems (anterior and posterior), which are connected by the circle of Willis, and supplied by the internal carotid and vertebral arteries. Disruption of this bloodflow can be either in the form of a bleed (haemorrhagic stroke) or clot (ischaemic stroke), and the clinical presentation will vary depending on the location of the disruption in the brain. Ischaemic strokes are more common and account for almost 70% of all events (Wolfe et al., 2002). Whilst thorough clinical examination is essential, the only clear tool to identify the type of stroke is to perform a brain scan using either magnetic resonance imaging (MRI) or computed tomography (CT) technology. It is important to note that, often, when a CT brain scan is performed within the first few hours of an event, the scan may not show any significant tissue damage because the changes that occur may take several days to be clearly visible.

scholarly journals Development of brain tumor segmentation of magnetic resonance imaging (MRI) using U-Net deep learning

2021 ◽  
Vol 4 (9(112)) ◽  
pp. 23-31
Author(s):  
Wasan M. Jwaid ◽  
Zainab Shaker Matar Al-Husseini ◽  
Ahmad H. Sabry
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Tumor Segmentation ◽  
Resonance Imaging ◽  
Brain Tumor Segmentation ◽  
Brain Images ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain

Brain tumors are the growth of abnormal cells or a mass in a brain. Numerous kinds of brain tumors were discovered, which need accurate and early detection techniques. Currently, most diagnosis and detection methods rely on the decision of neuro-specialists and radiologists to evaluate brain images, which may be time-consuming and cause human errors. This paper proposes a robust U-Net deep learning Convolutional Neural Network (CNN) model that can classify if the subject has a tumor or not based on Brain Magnetic resonance imaging (MRI) with acceptable accuracy for medical-grade application. The study built and trained the 3D U-Net CNN including encoding/decoding relationship architecture to perform the brain tumor segmentation because it requires fewer training images and provides more precise segmentation. The algorithm consists of three parts; the first part, the downsampling part, the bottleneck part, and the optimum part. The resultant semantic maps are inserted into the decoder fraction to obtain the full-resolution probability maps. The developed U-Net architecture has been applied on the MRI scan brain tumor segmentation dataset in MICCAI BraTS 2017. The results using Matlab-based toolbox indicate that the proposed architecture has been successfully evaluated and experienced for MRI datasets of brain tumor segmentation including 336 images as training data and 125 images for validation. This work demonstrated comparative performance and successful feasibility of implementing U-Net CNN architecture in an automated framework of brain tumor segmentations in Fluid-attenuated inversion recovery (FLAIR) MR Slices. The developed U-Net CNN model succeeded in performing the brain tumor segmentation task to classify the input brain images into a tumor or not based on the MRI dataset.

High-resolution MRI of the ulnar and radial collateral ligaments of the wrist

2017 ◽  
Vol 58 (12) ◽  
pp. 1493-1499 ◽  
Author(s):  
Taiki Nozaki ◽  
Wei Der Wu ◽  
Yasuhito Kaneko ◽  
Gregory Rafijah ◽  
Lily Yang ◽  
...  
Keyword(s):  
High Resolution ◽  
Three Dimensional ◽  
Collateral Ligaments ◽  
Ulnar Styloid ◽  
Accurate Identification ◽  
3D Images ◽  
Observer Reliability ◽  
High Resolution Mri ◽  
Magnetic Resonance Imaging Mri ◽  
3D Magnetic Resonance Imaging

Background Accurate diagnosis of injuries to the collateral ligaments of the wrist is technically challenging on MRI. Purpose To investigate usefulness of high-resolution two-dimensional (2D) and isotropic three-dimensional (3D) magnetic resonance imaging (MRI) for identifying and classifying the morphology of the ulnar and radial collateral ligaments (UCL and RCL) of the wrist. Material and Methods Thirty-seven participants were evaluated using 3T coronal 2D and isotropic 3D images by two radiologists independently. The UCL was classified into four types: 1a, narrow attachment to the tip of the ulnar styloid (Tip); 1b, broad attachment to the Tip; 2a, narrow attachment to the medial base of the ulnar styloid (Base); and 2b, broad attachment to the Base. The RCL was also classified into four types: 1a, separate radioscaphoid and scaphotrapezial ligaments (RS + ST) with narrow scaphoid attachment; 1b, RS + ST with broad scaphoid attachment; 2a, continuous radio-scapho-trapezial ligaments (RST) with narrow scaphoid attachment; and 2b, RST with broad scaphoid attachment. The inter-observer reliability of these classifications was calculated. Results Type 1a was the most common of both collateral ligaments. Of UCL classifications, 31.4% were revised after additional review of multiplanar reconstruction (MPR) images from isotropic data. The inter-observer reliability of UCL classification was substantial (k = 0.62) without MPR, and almost perfect (k = 0.84) with MPR. The inter-observer reliability of RCL classification was almost perfect (k = 0.89). Anatomic delineation between the two sequences was not statistically different. Conclusion The UCL and RCL were each identified on high-resolution 2D and isotropic 3D MRI equally well. MPR allows accurate identification of the UCL attachment to the ulnar styloid.

scholarly journals MRI Brain Image Enhancement Using an Improved Contrast Enhancement Method

2021 ◽  
Vol 11 (2) ◽  
pp. 607-615
Author(s):  
A. Vijaya Lakshmi ◽  
Vella Satynarayana ◽  
Dr.P. Mohanaiah
Keyword(s):  
Brain Tumors ◽  
Dynamic Range ◽  
Second Phase ◽  
Brain Images ◽  
Mri Brain ◽  
Mapping Process ◽  
Enhancement Method ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain ◽  
Human Death

The uncontrollable cells growth in the brain portion is the main reason for cancer deaths nowadays. So, effective detection of brain tumors is more important in the medical field to analyze the tumor portion. Detecting tumors prior and diagnosis of tumors can play a major role in preventing human death due to brain tumors. To detect the tumor portion, many segmentation and classification methods have been proposed. For the effect segmentation process, enhancing brain images is necessary. In this present paper, Magnetic resonance imaging (MRI) brain images have been taken as test images. The proposed enhancement method has two major phases. The first phase contains a regularization process in two steps to equalize the test images' intensities, and the second phase contains a mapping process of two steps to enhance the contrast of the image and remap their intensity values to the natural dynamic range.

scholarly journals A Robust Method for MR Image Segmentation and Multiple Scleroses Detection

2019 ◽  
Vol 9 (6) ◽  
pp. 1119-1130
Author(s):  
H. Zouaoui ◽  
A. Moussaoui ◽  
M. Oussalah ◽  
A. Taleb-Ahmed
Keyword(s):  
White Matter ◽  
Automatic Segmentation ◽  
Fuzzy Model ◽  
Mr Images ◽  
New Approach ◽  
Magnetic Resonance Imaging Mri ◽  
Mr Image Segmentation ◽  
The Brain

In the present article, we propose a new approach for the segmentation of the MR images of the Multiple Sclerosis (MS). The Magnetic Resonance Imaging (MRI) allows the visualization of the brain and it is widely used in the diagnosis and the follow-up of the patients suffering from MS. Aiming to automate a long and tedious process for the clinician, we propose the automatic segmentation of the MS lesions. Our algorithm of segmentation is composed of three stages: segmentation of the brain into regions using the algorithm Fuzzy Particle Swarm Optimization (FPSO) in order to obtain the characterization of the different healthy tissues (White matter, grey matter and cerebrospinal fluid (CSF)) after the extraction of white matter (WM), the elimination of the atypical data (outliers) of the white matter by the algorithm Fuzzy C-Means (FCM), finally, the use of a Mamdani-type fuzzy model to extract the MS lesions among all the absurd data.

scholarly journals Learning stable reduced-order models for hybrid twins

2021 ◽  
Vol 2 ◽  
Author(s):  
Abel Sancarlos ◽  
Morgan Cameron ◽  
Jean-Marc Le Peuvedic ◽  
Juliette Groulier ◽  
Jean-Louis Duval ◽  
...  
Keyword(s):  
Data Science ◽  
Time Integration ◽  
Computational Cost ◽  
Main Idea ◽  
Order Reduction ◽  
Machine Learning Techniques ◽  
Model Order ◽  
New Approach ◽  
Learning Techniques ◽  
Low Computational Cost

Abstract The concept of “hybrid twin” (HT) has recently received a growing interest thanks to the availability of powerful machine learning techniques. This twin concept combines physics-based models within a model order reduction framework—to obtain real-time feedback rates—and data science. Thus, the main idea of the HT is to develop on-the-fly data-driven models to correct possible deviations between measurements and physics-based model predictions. This paper is focused on the computation of stable, fast, and accurate corrections in the HT framework. Furthermore, regarding the delicate and important problem of stability, a new approach is proposed, introducing several subvariants and guaranteeing a low computational cost as well as the achievement of a stable time-integration.

scholarly journals The Opercular-Subopercular Syndrome: Four Cases with Review of the Literature

1998 ◽  
Vol 11 (2) ◽  
pp. 97-103 ◽  
Author(s):  
M. Bakar ◽  
H. S. Kirshner ◽  
F. Niaz
Keyword(s):  
Right Hemisphere ◽  
Cortical Lesions ◽  
Review Of The Literature ◽  
Case Histories ◽  
Brain Images ◽  
Frontal Operculum ◽  
Opercular Syndrome ◽  
Ct Brain ◽  
Bilateral Lesions ◽  
The Brain

We present four cases of the ‘opercular syndrome’ of volitional paresis of the facial, lingual, and laryngeal muscles (bilateral facio-glosso-pharyngo-masticatory paresis). Case histories and CT brain images are presented, along with a review of the literature concerning this long-recognized but little-known syndrome. The neuroanatomic basis of the syndrome classically involves bilateral lesions of the frontal operculum. We propose, on the basis of our cases and others, that the identical syndrome can arise from lesions of the corticobulbar tracts, not involving the cortical operculum. Our cases included one with bilateral subcortical lesions, one with a unilateral left opercular lesion and a possible, non-visualized right hemisphere lesion, one with unilateral cortical and unilateral subcortical pathology, and one with bilateral cortical lesions. These lesion localizations suggest that any combination of cortical or subcortical lesions of the operculum or its connections on both sides of the brain can produce a syndrome indistinguishable from the classical opercular syndrome. We propose the new term ‘opercular-subopercular syndrome’ to encompass cases with predominantly or partially subcortical lesions.

Segmentation and clustering in brain MRI imaging

2018 ◽  
Vol 30 (1) ◽  
pp. 31-44 ◽  
Author(s):  
Golrokh Mirzaei ◽  
Hojjat Adeli
Keyword(s):  
Grey Matter ◽  
State Of The Art ◽  
Brain Mri ◽  
Brain Regions ◽  
Mri Imaging ◽  
Resonance Imaging ◽  
Brain Images ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain ◽  
Different Parts

AbstractClustering is a vital task in magnetic resonance imaging (MRI) brain imaging and plays an important role in the reliability of brain disease detection, diagnosis, and effectiveness of the treatment. Clustering is used in processing and analysis of brain images for different tasks, including segmentation of brain regions and tissues (grey matter, white matter, and cerebrospinal fluid) and clustering of the atrophy in different parts of the brain. This paper presents a state-of-the-art review of brain MRI studies that use clustering techniques for different tasks.

scholarly journals Conflict Generalisation in ASP: Learning Correct and Effective Non-Ground Constraints

2020 ◽  
Vol 20 (5) ◽  
pp. 799-814
Author(s):  
RICHARD TAUPE ◽  
ANTONIUS WEINZIERL ◽  
GERHARD FRIEDRICH
Keyword(s):  
Computational Cost ◽  
Problem Instance ◽  
Test Cases ◽  
New Approach ◽  
Deductive Logic ◽  
Significant Performance ◽  
Speed Up ◽  
Problem Instances ◽  
Low Computational Cost ◽  
Additional Constraints

AbstractGeneralising and re-using knowledge learned while solving one problem instance has been neglected by state-of-the-art answer set solvers. We suggest a new approach that generalises learned nogoods for re-use to speed-up the solving of future problem instances. Our solution combines well-known ASP solving techniques with deductive logic-based machine learning. Solving performance can be improved by adding learned non-ground constraints to the original program. We demonstrate the effects of our method by means of realistic examples, showing that our approach requires low computational cost to learn constraints that yield significant performance benefits in our test cases. These benefits can be seen with ground-and-solve systems as well as lazy-grounding systems. However, ground-and-solve systems suffer from additional grounding overheads, induced by the additional constraints in some cases. By means of conflict minimization, non-minimal learned constraints can be reduced. This can result in significant reductions of grounding and solving efforts, as our experiments show.

Sign in / Sign up

Export Citation Format

Share Document