Classification of Abdominal Visceral and Subcutaneous Fat Distributions by Body Shape Descriptors

Magnetic Resonance ◽

Body Shape ◽

Cross Validation ◽

Abdominal Fat ◽

Support Vector ◽

Shape Descriptors ◽

Resonance Imaging ◽

Selection Scheme ◽

This study aims to explore new categorization that characterizes the distribution clusters of visceral and subcutaneous adipose tissues (VAT and SAT) measured by magnetic resonance imaging (MRI); to analyze the relationship between the VAT-SAT distribution patterns and the novel body shape descriptors (BSDs); and to develop a classifier to predict the fat distribution clusters using the BSDs. 66 male and 54 female participants were scanned by magnetic resonance imaging (MRI) and a stereovision body imaging (SBI) to measure participants’ abdominal VAT and SAT volumes and the BSDs. A fuzzy c-means algorithm was used to form the inherent grouping clusters of abdominal fat distributions. A support-vector-machine (SVM) classifier, with an embedded feature selection scheme, was employed to determine an optimal subset of the BSDs for predicting internal fat distributions. A five-fold cross-validation procedure was used to prevent over-fitting in the classification. The classification results of the BSDs were compared with those of the traditional anthropometric measurements and the Dual Energy X-Ray Absorptiometry (DXA) measurements. Four clusters were identified for abdominal fat distributions: low VAT and SAT, elevated VAT and SAT, higher SAT, and higher VAT. The cross-validation accuracies of the traditional anthropometric, DXA and BSD measurements are 85.0%, 87.5% and 90%, respectively.

A Comprehensive Machine-Learning Model Applied to Magnetic Resonance Imaging (MRI) to Predict Alzheimer’s Disease (AD) in Older Subjects

Journal of Clinical Medicine ◽

10.3390/jcm9072146 ◽

2020 ◽

Vol 9 (7) ◽

pp. 2146

Author(s):

Gopi Battineni ◽

Nalini Chintalapudi ◽

Francesco Amenta ◽

Enea Traini

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Feature Selection ◽

Magnetic Resonance ◽

Neurodegenerative Disorder ◽

Support Vector ◽

Resonance Imaging ◽

Increasing evidence suggests the utility of magnetic resonance imaging (MRI) as an important technique for the diagnosis of Alzheimer’s disease (AD) and for predicting the onset of this neurodegenerative disorder. In this study, we present a sophisticated machine learning (ML) model of great accuracy to diagnose the early stages of AD. A total of 373 MRI tests belonging to 150 subjects (age ≥ 60) were examined and analyzed in parallel with fourteen distinct features related to standard AD diagnosis. Four ML models, such as naive Bayes (NB), artificial neural networks (ANN), K-nearest neighbor (KNN), and support-vector machines (SVM), and the receiver operating characteristic (ROC) curve metric were used to validate the model performance. Each model evaluation was done in three independent experiments. In the first experiment, a manual feature selection was used for model training, and ANN generated the highest accuracy in terms of ROC (0.812). In the second experiment, automatic feature selection was conducted by wrapping methods, and the NB achieved the highest ROC of 0.942. The last experiment consisted of an ensemble or hybrid modeling developed to combine the four models. This approach resulted in an improved accuracy ROC of 0.991. We conclude that the involvement of ensemble modeling, coupled with selective features, can predict with better accuracy the development of AD at an early stage.

Classification on Magnetic Resonance Imaging (MRI) Brain Tumour using BPNN, SVM and CNN

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c6442.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 8601-8607

Keyword(s):

Neural Network ◽

Image Segmentation ◽

Magnetic Resonance ◽

Brain Tumour ◽

Support Vector ◽

Low Grade ◽

Resonance Imaging ◽

Mri Brain ◽

In this works, the main objective is to detect the high grade gliomas (HGG) and low grade gliomas (LGG) from Magnetic Resonance Imaging (MRI) Brain Tumour images by applying the efficient image segmentation and classify among them. So hybrid image segmentation techniques applied in this work, first one is canny edge detection which is used to locate the boundary of the image and second is fuzzy c-mean clustering which is used to clubbed together of the similarity intensity value into clusters. Also further eight feature extracted using Intensity based Histogram and GrayLevel Co-occurrence Matrix (GLCM). Now three classifiers learning algorithm applied in this system, first one is backpropogation neural network (BPNN) which consists of multi-layer perceptrons to solve the complex problem for the given inputs. Second one is convolution neural network (CNN) are the part of neural networks which have very effective in areas such as image recognition and image classification. Third is Support vector machine (SVM) which can be used for both classification and regression challenges. Each of one is evaluated performance based on different techniques. It found that SVM and CNN gives 88% accuracy for this work.

Intensity warping for multisite MRI harmonization

10.1101/679357 ◽

2019 ◽

Cited By ~ 1

Author(s):

J Wrobel ◽

ML Martin ◽

R Bakshi ◽

PA Calabresi ◽

M Elliot ◽

...

Keyword(s):

Magnetic Resonance ◽

Cross Validation ◽

Biological Effects ◽

Brain Magnetic Resonance Imaging ◽

Time Frame ◽

Resonance Imaging ◽

Biological Features ◽

Magnetic Resonance Imaging Mri ◽

Short Time

AbstractIn multisite neuroimaging studies there is often unwanted technical variation across scanners and sites. These “scanner effects” can hinder detection of biological features of interest, produce inconsistent results, and lead to spurious associations. We assess scanner effects in two brain magnetic resonance imaging (MRI) studies where subjects were measured on multiple scanners within a short time frame, so that one could assume any differences between images were due to technical rather than biological effects. We propose mica (multisite image harmonization by CDF alignment), a tool to harmonize images taken on different scanners by identifying and removing within-subject scanner effects. Our goals in the present study were to (1) establish a method that removes scanner effects by leveraging multiple scans collected on the same subject, and, building on this, (2) develop a technique to quantify scanner effects in large multisite trials so these can be reduced as a preprocessing step. We found that unharmonized images were highly variable across site and scanner type, and our method effectively removed this variability by warping intensity distributions. We further studied the ability to predict intensity harmonization results for a scan taken on an existing subject at a new site using cross-validation.

Use of Transcranial Magnetic Stimulation (TMS) and Magnetic Resonance Imaging (MRI) to Study Visual Attention

PsycEXTRA Dataset ◽

10.1037/e655432010-001 ◽

2009 ◽

Keyword(s):

Transcranial Magnetic Stimulation ◽

Magnetic Resonance ◽

Visual Attention ◽

Magnetic Stimulation ◽

Resonance Imaging ◽

Detection of cholangiocarcinoma (CC) with positron emission tomography (PET) and magnetic resonance imaging (MRI)

Journal of Hepatology ◽

10.1016/s0168-8278(01)80852-7 ◽

2001 ◽

Vol 34 (0) ◽

pp. 229

Author(s):

F Berr

Keyword(s):

Positron Emission Tomography ◽

Magnetic Resonance ◽

Emission Tomography ◽

Resonance Imaging ◽

Positron Emission ◽

Safety and Practicality of Magnetic Resonance Imaging (MRI) for Non-invasive Assessment of Coronary Stents

Journal of the American College of Cardiology ◽

10.1016/s0735-1097(97)85365-x ◽

1998 ◽

Vol 31 (2) ◽

pp. 382A

Author(s):

S Rosario

Keyword(s):

Magnetic Resonance ◽

Coronary Stents ◽

Resonance Imaging ◽

Non Invasive ◽

Top-Ten Tips for Imaging the Brachial Plexus with Ultrasound and MRI

Seminars in Musculoskeletal Radiology ◽

10.1055/s-0039-1694753 ◽

2019 ◽

Vol 23 (04) ◽

pp. 405-418 ◽

Cited By ~ 1

Author(s):

James F. Griffith ◽

Radhesh Krishna Lalam

Keyword(s):

Magnetic Resonance ◽

Brachial Plexus ◽

Muscle Denervation ◽

Resonance Imaging ◽

Neural Injury ◽

Clinical Indications ◽

Magnetic Resonance Imaging Mri ◽

High Level ◽

Extensive Involvement

AbstractWhen it comes to examining the brachial plexus, ultrasound (US) and magnetic resonance imaging (MRI) are complementary investigations. US is well placed for screening most extraforaminal pathologies, whereas MRI is more sensitive and accurate for specific clinical indications. For example, MRI is probably the preferred technique for assessment of trauma because it enables a thorough evaluation of both the intraspinal and extraspinal elements, although US can depict extraforaminal neural injury with a high level of accuracy. Conversely, US is probably the preferred technique for examination of neurologic amyotrophy because a more extensive involvement beyond the brachial plexus is the norm, although MRI is more sensitive than US for evaluating muscle denervation associated with this entity. With this synergy in mind, this review highlights the tips for examining the brachial plexus with US and MRI.