Search results for " mr"

showing 10 items of 495 documents

Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging

2021

Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardwar…

Computer scienceGraphics processing unit02 engineering and technologyResiduallcsh:TechnologyArticle030218 nuclear medicine & medical imaginglcsh:Chemistrydeep learning; segmentation; prostate; MRI; ENet; UNet; ERFNet; radiomicsSet (abstract data type)03 medical and health sciences0302 clinical medicineENetERFNet0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceSegmentationlcsh:QH301-705.5InstrumentationSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniFluid Flow and Transfer ProcessesprostateArtificial neural networklcsh:Tbusiness.industryProcess Chemistry and TechnologyDeep learningsegmentationGeneral EngineeringProcess (computing)deep learningUNetPattern recognitionlcsh:QC1-999Computer Science Applicationslcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040radiomics020201 artificial intelligence & image processingArtificial intelligenceCentral processing unitlcsh:Engineering (General). Civil engineering (General)businesslcsh:PhysicsMRIApplied Sciences
researchProduct

Bias artifact suppression on MR volumes.

2007

RF-Inhomogeneity correction is a relevant research topic in the field of Magnetic Resonance Imaging (MRI). A volume corrupted by this artifact exhibits nonuni- form illumination both inside a single slice and between adjacent ones. In this work a bias correction technique is presented, which suppresses this artifact on MR vol- umes scanned from different body parts without any a-priori hypothesis on the artifact model. Theoretical foundations of the method are reported together with experimental results and a comparison is presented with both the 2D version of the algorithm and other techniques that are widely used in MRI literature.

Computer scienceHealth InformaticsSensitivity and SpecificityImaging Three-DimensionalBiasImage Interpretation Computer-AssistedmedicineComputer visionRF-Inhomogeneity Bias Artifact Illumination correction MR Image Homomorphic filterSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniArtifact (error)medicine.diagnostic_testbusiness.industryReproducibility of ResultsMagnetic resonance imagingImage EnhancementMagnetic Resonance ImagingComputer Science ApplicationsArtifact suppressionArtificial intelligenceMr imagesbusinessArtifactsSoftwareAlgorithmsVolume (compression)Computer methods and programs in biomedicine
researchProduct

Fully automatic multispectral MR image segmentation of prostate gland based on the fuzzy C-means clustering algorithm

2017

Prostate imaging is a very critical issue in the clinical practice, especially for diagnosis, therapy, and staging of prostate cancer. Magnetic Resonance Imaging (MRI) can provide both morphologic and complementary functional information of tumor region. Manual detection and segmentation of prostate gland and carcinoma on multispectral MRI data is not easily practicable in the clinical routine because of the long times required by experienced radiologists to analyze several types of imaging data. In this paper, a fully automatic image segmentation method, exploiting an unsupervised Fuzzy C-Means (FCM) clustering technique for multispectral T1-weighted and T2-weighted MRI data processing, is…

Computer scienceMultispectral imageFully automatic segmentation; Multispectral MR imaging; Prostate cancer; Prostate gland; Unsupervised fuzzy C-means clusteringFuzzy logic030218 nuclear medicine & medical imaging03 medical and health sciencesProstate cancer0302 clinical medicineProstatemedicineSegmentationComputer visionCluster analysismedicine.diagnostic_testbusiness.industryINF/01 - INFORMATICAMagnetic resonance imagingfully automatic segmentationImage segmentationmedicine.diseaseprostate cancermultispectral MR imagingunsupervised Fuzzy C-Means clusteringmedicine.anatomical_structureArtificial intelligencebusinessprostate gland030217 neurology & neurosurgery
researchProduct

Discovering Aberrant Patterns of Human Connectome in Alzheimer's Disease via Subgraph Mining

2012

Alzheimer's disease (AD) is the most common cause of age-related dementia, which prominently affects the human connectome. Diffusion weighted imaging (DWI) provides a promising way to explore the organization of white matter fiber tracts in the human brain in a non-invasive way. However, the immense amount of data from millions of voxels of a raw diffusion map prevent an easy way to utilizable knowledge. In this paper, we focus on the question how we can identify disrupted spatial patterns of the human connectome in AD based on a data mining framework. Using diffusion tractography, the human connectomes for each individual subject were constructed based on two diffusion derived attributes: …

Computer sciencebusiness.industryPattern recognitionGraph theoryHuman ConnectomeHuman brainGrey mattercomputer.software_genremedicine.diseaseWhite mattermedicine.anatomical_structureVoxelHuman ConnectomesFractional anisotropymedicineDementiaDiffusion TractographyArtificial intelligencebusinesscomputerDiffusion MRI2012 IEEE 12th International Conference on Data Mining Workshops
researchProduct

Diffusional Kurtosis Imaging in the Diffusion Imaging in Python Project

2021

ABSTRACTDiffusion-weighted magnetic resonance imaging (dMRI) measurements and models provide information about brain connectivity and are sensitive to the physical properties of tissue microstructure. Diffusional Kurtosis Imaging (DKI) quantifies the degree of non-Gaussian diffusion in biological tissue from dMRI. These estimates are of interest because they were shown to be more sensitive to microstructural alterations in health and diseases than measures based on the total anisotropy of diffusion which are highly confounded by tissue dispersion and fiber crossings. In this work, we implemented DKI in the Diffusion in Python (DIPY) project - a large collaborative open-source project which …

Computer scienceopen-source softwaremicrostructureNeurosciences. Biological psychiatry. NeuropsychiatryGrey matter030218 nuclear medicine & medical imagingWhite matterdiffusion MRI03 medical and health sciencesBehavioral Neuroscience0302 clinical medicinebiophysicsmedicineTechnology and CodeReference implementationDiffusion (business)DKIBiological Psychiatrycomputer.programming_languageGround truthmedicine.diagnostic_testMagnetic resonance imagingHuman NeuroscienceBiological tissueInvariant (physics)Python (programming language)Characterization (materials science)pythonDiffusion imagingPsychiatry and Mental healthmedicine.anatomical_structureNeuropsychology and Physiological PsychologyNeurologyDTIKurtosisAlgorithmcomputer030217 neurology & neurosurgeryRC321-571MRITractographyDiffusion MRIFrontiers in Human Neuroscience
researchProduct

Combined approach to atrial and ventricular function for assessment of diastole through MRI: Hypertrophic Cardiomyopathy (HCM) vs Healthy Controls (H…

2013

Purpose Methods and Materials Results Conclusion References Personal Information

CongenitalCongenital Imaging sequences MR CardiacMRImaging sequencesSettore MED/36 - Diagnostica Per Immagini E RadioterapiaCardiac
researchProduct

CT AND MRI OF THYROGLOSSAL DUCT CYST

2015

Aims and objectives Methods and materials Results Conclusion Personal information References

CongenitalHead and neckgenetic structuresComputer Applications-3DCystsCysts Congenital Computer Applications-3D MR CT Head and neckMRCT
researchProduct

Anatomic variants of the biliary tree at MRCP: still too rarely reported!

2015

Aims and objectives Methods and materials Results Conclusion Personal information References

Congenitalgenetic structuresAbdomenAbdomen MR Cholangiography CongenitalMRCholangiography
researchProduct

Eine Kombination niedrig und hochauflösender dynamischer T1-gewichteter Sequenzen zur besseren Beurteilung der Morphologie Kontrastmittel aufnehmende…

2002

Purpose: Presentation of a new protocol for simultaneous acquisition of both low and high resolution T 1 -weighted images of breast lesions for dynamic contrast-enhanced MR mammography. Demonstration of possible diagnostic improvement with representative measurements in patients with suspected breast cancer by adding morphologic parameters from high resolution sequences to the analysis of the signal-time curve. Materials and Methods: Dynamic MR imaging was performed with a 1.5 T system (Magnetom SONATA, Siemens Medical Systems, Germany) and the manufacturer's double-breast coil. Coronal T 1 -weighted 3D FLASH sequences (spatial resolution 1.25 ×1.25 mm 2 ; slice thickness 1.7 mm) were acqui…

Contrast mediumNuclear magnetic resonanceMaterials sciencePulse (signal processing)Dynamic contrast-enhanced MRIResolution (electron density)Radiology Nuclear Medicine and imagingSensitivity (control systems)Image resolutionSignalImaging phantomBiomedical engineeringRöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren
researchProduct

Graph cut-based method for segmenting the left ventricle from MRI or echocardiographic images

2017

International audience; In this paper, we present a fast and interactive graph cut method for 3D segmentation of the endocardial wall of the left ventricle (LV) adapted to work on two of the most widely used modalities: magnetic resonance imaging (MRI) and echocardiography. Our method accounts for the fundamentally different nature of both modalities: 3D echocardiographic images have a low contrast, a poor signal-to-noise ratio and frequent signal drop, while MR images are more detailed but also cluttered and contain highly anisotropic voxels. The main characteristic of our method is to work in a 3D Bezier coordinate system instead of the original Euclidean space. This comes with several ad…

Convex hullHeart VentriclesEnergy MinimizationCoordinate systemEchocardiography Three-DimensionalHealth InformaticsBézier curve02 engineering and technology[SDV.IB.MN]Life Sciences [q-bio]/Bioengineering/Nuclear medicinecomputer.software_genreAutomated Segmentation030218 nuclear medicine & medical imaging[ SDV.IB.MN ] Life Sciences [q-bio]/Bioengineering/Nuclear medicine03 medical and health sciences0302 clinical medicineVoxelCut0202 electrical engineering electronic engineering information engineering[INFO.INFO-IM]Computer Science [cs]/Medical ImagingMagnetic-Resonance ImagesHumansRadiology Nuclear Medicine and imagingComputer vision[ SDV.IB ] Life Sciences [q-bio]/BioengineeringCardiac MriImage gradientMathematicsWhole MyocardiumLeft ventricular 3-D segmentationRadiological and Ultrasound Technology[ INFO.INFO-IM ] Computer Science [cs]/Medical ImagingEuclidean spacebusiness.industryComputer Graphics and Computer-Aided DesignMagnetic Resonance ImagingEchocardiographyConstrained Level-SetGraph (abstract data type)020201 artificial intelligence & image processing[SDV.IB]Life Sciences [q-bio]/BioengineeringComputer Vision and Pattern RecognitionArtificial intelligencebusiness2d-EchocardiographycomputerAlgorithmsGraph cutMRI
researchProduct