4,501 Hits in 4.6 sec

Early cerebral small vessel disease and brain volume, cognition, and gait

Eric E. Smith, Martin O'Donnell, Gilles Dagenais, Scott A. Lear, Andreas Wielgosz, Mukul Sharma, Paul Poirier, Grant Stotts, Sandra E. Black, Stephen Strother, Michael D. Noseworthy, Oscar Benavente (+12 others)
2015 Annals of Neurology  
Higher volume of supratentorial MRI white matter hyperintensity was associated with slower timed gait and worse performance on DSST, and lower volumes of the supratentorial cortex and white matter, and  ...  covert cerebrovascular disease on magnetic resonance imaging (MRI).  ...  To our knowledge, this is the first population-based study to report on associations between CMBs and brain volumes.  ... 
doi:10.1002/ana.24320 pmid:25428654 pmcid:PMC4338762 fatcat:o227lvliercx7kdah6zzxly72a

An interactive system for muscle and fat tissue identification of the lumbar spine using semantic segmentation

Richard Bieck, David Baur, Johann Berger, Tim Stelzner, Anna Völker, Juliane Neumann, Christoph-E. Heyde, Thomas Neumuth
2021 Current Directions in Biomedical Engineering  
The system comprises a backend component that accepts MRI data from a web-based interactive frontend as REST requests.  ...  The MRI data is passed through a U-net model, fine-tuned on lumbar MRI images, to generate segmentation masks of fat and muscle areas.  ...  All augmentation operations were performed using the Albumentations framework [5] . We used a U-Net with weights pre-trained on the brain MRI dataset provided by [6] .  ... 
doi:10.1515/cdbme-2021-2099 fatcat:wdhr3slzwfht7ofas352pwo3dm

Left Ventricle Segmentation and Volume Estimation on Cardiac MRI using Deep Learning [article]

Ehab Abdelmaguid, Jolene Huang, Sanjay Kenchareddy, Disha Singla, Laura Wilke, Mai H. Nguyen, Ilkay Altintas
2018 arXiv   pre-print
First, image data are reformatted and processed from DICOM and NIfTI formats to raw images in array format.  ...  This analytics pipeline is implemented and runs on a distributed computing environment with a GPU cluster at the San Diego Supercomputer Center at UCSD.  ...  Previous work substituted the arithmetic mean into the formula above for V i based on empirical analysis [7] .  ... 
arXiv:1809.06247v2 fatcat:ovqgoajju5g2lf4taajn6sytqe

A Decoupled Uncertainty Model for MRI Segmentation Quality Estimation [article]

Richard Shaw and Carole H. Sudre and Sebastien Ourselin and M. Jorge Cardoso and Hugh G. Pemberton
2021 arXiv   pre-print
and quantitatively in the form of error bars on volume measurements.  ...  Relating artefact uncertainty to segmentation Dice scores, we observe that our uncertainty predictions provide a better estimate of MRI quality from the point of view of the task (gray matter segmentation  ...  Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense  ... 
arXiv:2109.02413v1 fatcat:24dhe4dqrrgdnnwkiv3cbweva4

A Data Augmentation based Framework to Handle Class Imbalance Problem for Alzheimer's Stage Detection

Sitara Afzal, Muazzam Maqsood, Faria Nazir, Umair Khan, Farhan Aadil, Khalid Mahmood Awan, Irfan Mehmood, Oh-Young Song
2019 IEEE Access  
In this research, we employed a transfer learning-based technique using data augmentation for 3D Magnetic Resonance Imaging (MRI) views from OASIS dataset.  ...  However, the most common problem with deep learning architecture is that large training data is required.  ...  Figure 9 shows the procedure of 3D-view of brain MRI on epoch size 9 with the data augmentation.  ... 
doi:10.1109/access.2019.2932786 fatcat:jh2yfnjpbrgchirr6ecq35yaai

Volumetric breast density estimation on MRI using explainable deep learning regression

Bas H. M. van der Velden, Markus H. A. Janse, Max A. A. Ragusi, Claudette E. Loo, Kenneth G. A. Gilhuijs
2020 Scientific Reports  
SHAP showed that in correct density estimations, the algorithm based its decision on fibroglandular and fatty tissue.  ...  To purpose of this paper was to assess the feasibility of volumetric breast density estimations on MRI without segmentations accompanied with an explainability step.  ...  Other methods to establish breast density on MRI often segment the breast region and fibroglandular tissue.  ... 
doi:10.1038/s41598-020-75167-6 pmid:33093572 fatcat:akb3r7emoneenfiz626bquasu4

Brain Tissue Classification using PCA with Hybrid Clustering Algorithms

Yepuganti Karuna, Saritha Saladi, Budhaditya Bhattacharyya
2018 International Journal of Engineering & Technology  
Distinct algorithms were developed to segment the MRI images, to satisfy the accuracy in segmenting the regions of the brain.  ...  This improves the ability to extract the regions (cluster centres) and cells in the normal and abnormal brain MRI images.  ...  The image segmentation is dividing an image into different anatomical structures based on the various parameters like regions, intensities, pixels, and volume.  ... 
doi:10.14419/ijet.v7i2.24.12155 fatcat:bfmqjro2endk7eplnwdp7bybmq

Brain Tumour Image Segmentation Using Deep Networks

Mahnoor Ali, Syed Omer Gilani, Asim Waris, Kashan Zafar, Mohsin Jamil
2020 IEEE Access  
Deep learning algorithms outperform on tasks of semantic segmentation as opposed to the more conventional, context-based computer vision approaches.  ...  The suggested ensemble achieved dice scores of 0.750, 0.906 and 0.846 for enhancing tumour, whole tumour, and tumour core, respectively, on the validation set, performing favourably in comparison to the  ...  It provides several complimentary 3D MRI modalities acquired based on the degree of excitation and repetition times, i.e.  ... 
doi:10.1109/access.2020.3018160 fatcat:veahn632a5allkot6qxc4e72uu

Robust Automatic Whole Brain Extraction on Magnetic Resonance Imaging of Brain Tumor Patients using Dense-Vnet [article]

Sara Ranjbar
2020 arXiv   pre-print
Overall, DeepBrain yielded an average dice score of 94.5%, sensitivity of 96.4%, and specificity of 98.5% on brain tumor data.  ...  To assess data efficiency, we retrained our models using progressively fewer training data examples and calculated average dice scores on the test set for the models trained in each round.  ...  No augmentation was performed on our data. During training, model checkpoints were locally saved every 20 epochs.  ... 
arXiv:2006.02627v1 fatcat:trb6vy6a7bh3hebz3ody7a65jy

Locally linear embedding (LLE) for MRI based Alzheimer's disease classification

Xin Liu, Duygu Tosun, Michael W. Weiner, Norbert Schuff
2013 NeuroImage  
Specifically, we used the unsupervised learning algorithm of locally linear embedding (LLE) to transform multivariate MRI data of regional brain volume and cortical thickness to a locally linear space  ...  The embedded brain features were then used to train a classifier for predicting future conversion to AD based on a baseline MRI.  ...  Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904).  ... 
doi:10.1016/j.neuroimage.2013.06.033 pmid:23792982 pmcid:PMC3815961 fatcat:4smwhlkjcnhxlgynkjhdezpotq

Multi-Modality Cardiac Image Analysis with Deep Learning [article]

Lei Li, Fuping Wu, Sihang Wang, Xiahai Zhuang
2021 arXiv   pre-print
This chapter aims to summarize the state-of-the-art and our recent advanced contributions on deep learning based multi-modality cardiac image analysis.  ...  Firstly, we introduce two benchmark works for multi-sequence cardiac MRI based myocardial and pathology segmentation.  ...  For data augmentation, UB leverages CycleGAN strategy [13] to convert bSSFP images into LGE-like ones and utilizes region rotation of scars, while HIT uses histogram matching for augmentation.  ... 
arXiv:2111.04736v1 fatcat:pdxoa7p23jhknc7rvtdydurqma

Dynamic contrast-enhanced magnetic resonance imaging of prostate cancer: A review of current methods and applications

Yousef Mazaheri, Oguz Akin, Hedvig Hricak
2017 World Journal of Radiology  
This review will discuss the current status of DCE-MRI in cancer imaging, with a focus on its use in imaging prostate malignancies as well as weaknesses that limit its widespread clinical use.  ...  Classic models for dynamic contrastenhanced MRI.  ...  cancer regions and tumor stage, Gleason score, patient age, tumor volume, or prostate-specific antigen. Alonzi et al Mazaheri Y et al .  ... 
doi:10.4329/wjr.v9.i12.416 pmid:29354207 pmcid:PMC5746645 fatcat:2asksscitbbr7gznu2awobdg4m

Analysis of Various Automated Structural Computing Methods Inpatient with Early Traumatic Brain Injury

Neeraj Upadhyay, Ashok Munivenkatappa, Bhagavatula Indira Devi, D. K. Subbakrishna, Jamuna Rajeswaran
2014 Open Access Journal of Science and Technology  
Aim: To assess Surface Based Morphometry (SBM) and Voxel Based Morphometry (VBM), the automated computation methods to demonstrate volume and thickness changes in brain among early Traumatic Brain Injury  ...  However, on correlating neuropsychological score with structural changes, SBM demonstrated significant voxels survived in animal naming and Token Test after correcting for multiple comparisons.  ...  In effect, an analysis of modulated data tests for regional differences in the absolute amount (volume) of grey matter, whereas analysis of unmodulated data tests for regional differences in concentration  ... 
doi:10.11131/2014/101069 fatcat:mnlbq5bxwvav3mnx3hm63azmyy

Automatic Segmentation of Left Ventricle in Cardiac Magnetic Resonance Images [article]

Garvit Chhabra, J. H. Gagan, J. R. Harish Kumar
2022 arXiv   pre-print
The proposed technique is based on traditional image processing techniques with a performance on par with the deep learning techniques.  ...  Segmentation of the left ventricle in cardiac magnetic resonance imaging MRI scans enables cardiologists to calculate the volume of the left ventricle and subsequently its ejection fraction.  ...  [19] proposed two data augmentation methods i.e., resolution augmentation to rescale images to different resolutions and factor-based augmentation to decompose scans into two lateral representations  ... 
arXiv:2201.12805v1 fatcat:7qxylovxojaa5agajzrvonu3ay

Estimation of the Volume of the Left Ventricle From MRI Images Using Deep Neural Networks

Fangzhou Liao, Xi Chen, Xiaolin Hu, Sen Song
2017 IEEE Transactions on Cybernetics  
We designed a system based on neural networks to solve this problem.  ...  In 2016, Kaggle organized a competition to estimate the volume of LV from MRI images. The dataset consisted of a large number of cases, but only provided systole and diastole volumes as labels.  ...  As a simple way of data augmentation, all positive samples were rotated by 90 • , 180 • , 270 • .  ... 
doi:10.1109/tcyb.2017.2778799 pmid:29990055 fatcat:qbaiaacmlvborpjqiyfj3dapkm
« Previous Showing results 1 — 15 out of 4,501 results