Search results for " Medical imaging"

showing 10 items of 1067 documents

Statistical atlas based exudate segmentation

2013

Diabetic macular edema (DME) is characterized by hard exudates. In this article, we propose a novel statistical atlas based method for segmentation of such exudates. Any test fundus image is first warped on the atlas co-ordinate and then a distance map is obtained with the mean atlas image. This leaves behind the candidate lesions. Post-processing schemes are introduced for final segmentation of the exudate. Experiments with the publicly available HEI-MED data-set shows good performance of the method. A lesion localization fraction of 82.5% at 35% of non-lesion localization fraction on the FROC curve is obtained. The method is also compared to few most recent reference methods.

ExudateComputer scienceFundus imageDiabetic macular edemaHealth Informatics02 engineering and technologyMacular Edema030218 nuclear medicine & medical imaging03 medical and health sciencesAtlases as Topic0302 clinical medicine0202 electrical engineering electronic engineering information engineeringmedicineHumansRadiology Nuclear Medicine and imagingSegmentationComputer visionDiabetic RetinopathyModels StatisticalRadiological and Ultrasound TechnologyAtlas (topology)business.industryExudates and TransudatesComputer Graphics and Computer-Aided DesignUnited StatesHard exudates020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligenceAnatomic Landmarksmedicine.symptombusinessDistance transformComputerized Medical Imaging and Graphics
researchProduct

Learning With Context Feedback Loop for Robust Medical Image Segmentation

2021

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system …

FOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceComputer Vision and Pattern Recognition (cs.CV)Feature vectorComputer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONContext (language use)Convolutional neural networkMachine Learning (cs.LG)Feedback030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicineFOS: Electrical engineering electronic engineering information engineeringImage Processing Computer-Assisted[INFO.INFO-IM]Computer Science [cs]/Medical ImagingSegmentationElectrical and Electronic EngineeringComputingMilieux_MISCELLANEOUSRadiological and Ultrasound TechnologyPixelbusiness.industryDeep learningImage and Video Processing (eess.IV)Pattern recognitionImage segmentationElectrical Engineering and Systems Science - Image and Video ProcessingFeedback loopComputer Science ApplicationsFeature (computer vision)Neural Networks ComputerArtificial intelligencebusinessSoftware
researchProduct

Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data

2021

Whole gland (WG) segmentation of the prostate plays a crucial role in detection, staging and treatment planning of prostate cancer (PCa). Despite promise shown by deep learning (DL) methods, they rely on the availability of a considerable amount of annotated data. Augmentation techniques such as translation and rotation of images present an alternative to increase data availability. Nevertheless, the amount of information provided by the transformed data is limited due to the correlation between the generated data and the original. Based on the recent success of generative adversarial networks (GAN) in producing synthetic images for other domains as well as in the medical domain, we present…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer sciencePipeline (computing)Computer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognition02 engineering and technology030218 nuclear medicine & medical imagingMachine Learning (cs.LG)03 medical and health sciencesProstate cancer0302 clinical medicineProstate020204 information systems0202 electrical engineering electronic engineering information engineeringmedicineFOS: Electrical engineering electronic engineering information engineeringSegmentationbusiness.industryDeep learningImage and Video Processing (eess.IV)Pattern recognitionImage segmentationElectrical Engineering and Systems Science - Image and Video Processingmedicine.diseaseData availabilitymedicine.anatomical_structureArtificial intelligencebusinessT2 weighted
researchProduct

Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

2021

Deep learning methods are the de facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application, which, like many others, requires a large number of annotated data so that a trained network can generalize well. Unfortunately, the process of having a large number of manually curated images by medical experts is both slow and utterly expensive. In this paper, we set out to explore whether expert knowledge is a strict requirement for the creation of annotated data sets on which machine learning can successfully be trained. To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with dif…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceProcess (engineering)GeneralizationIndustrial engineering. Management engineeringComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognitionheartannotated data setT55.4-60.8Machine learningcomputer.software_genre030218 nuclear medicine & medical imagingTheoretical Computer ScienceMachine Learning (cs.LG)Set (abstract data type)03 medical and health sciences0302 clinical medicineFOS: Electrical engineering electronic engineering information engineeringSegmentationNumerical AnalysisArtificial neural networkbusiness.industryDeep learningsegmentationImage and Video Processing (eess.IV)deep learningQA75.5-76.95Electrical Engineering and Systems Science - Image and Video ProcessingComputational MathematicsHausdorff distanceComputational Theory and MathematicsIndex (publishing)Electronic computers. Computer scienceArtificial intelligencebusinesscomputer030217 neurology & neurosurgeryMRI
researchProduct

Deep Generative Model-Driven Multimodal Prostate Segmentation in Radiotherapy

2019

Deep learning has shown unprecedented success in a variety of applications, such as computer vision and medical image analysis. However, there is still potential to improve segmentation in multimodal images by embedding prior knowledge via learning-based shape modeling and registration to learn the modality invariant anatomical structure of organs. For example, in radiotherapy automatic prostate segmentation is essential in prostate cancer diagnosis, therapy, and post-therapy assessment from T2-weighted MR or CT images. In this paper, we present a fully automatic deep generative model-driven multimodal prostate segmentation method using convolutional neural network (DGMNet). The novelty of …

FOS: Computer and information sciencesComputer scienceComputer Vision and Pattern Recognition (cs.CV)medicine.medical_treatmentProstate segmentationFeature extractionComputer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONConvolutional neural network[SDV.IB.MN]Life Sciences [q-bio]/Bioengineering/Nuclear medicineConvolutional neural network030218 nuclear medicine & medical imaging03 medical and health sciencesProstate cancer0302 clinical medicineFOS: Electrical engineering electronic engineering information engineeringmedicineSegmentationArtificial neural networkbusiness.industryDeep learningImage and Video Processing (eess.IV)NoveltyDeep learningPattern recognitionElectrical Engineering and Systems Science - Image and Video Processingmedicine.diseaseTransfer learning3. Good healthRadiation therapyGenerative model030220 oncology & carcinogenesisEmbeddingArtificial intelligencebusinessCTMRI
researchProduct

Real-time computation of parameter fitting and image reconstruction using graphical processing units

2016

Abstract In recent years graphical processing units (GPUs) have become a powerful tool in scientific computing. Their potential to speed up highly parallel applications brings the power of high performance computing to a wider range of users. However, programming these devices and integrating their use in existing applications is still a challenging task. In this paper we examined the potential of GPUs for two different applications. The first application, created at Paul Scherrer Institut (PSI), is used for parameter fitting during data analysis of μ SR (muon spin rotation, relaxation and resonance) experiments. The second application, developed at ETH, is used for PET (Positron Emission T…

FOS: Computer and information sciencesMulti-core processorSpeedup010308 nuclear & particles physicsComputer scienceComputationFOS: Physical sciencesGeneral Physics and AstronomyIterative reconstructionComputational Physics (physics.comp-ph)Supercomputer01 natural sciences030218 nuclear medicine & medical imagingComputational science03 medical and health sciencesRange (mathematics)CUDA0302 clinical medicineComputer Science - Distributed Parallel and Cluster ComputingHardware and Architecture0103 physical sciencesSingle-coreDistributed Parallel and Cluster Computing (cs.DC)Physics - Computational PhysicsComputer Physics Communications
researchProduct

Depth-Adapted CNN for RGB-D cameras

2020

Conventional 2D Convolutional Neural Networks (CNN) extract features from an input image by applying linear filters. These filters compute the spatial coherence by weighting the photometric information on a fixed neighborhood without taking into account the geometric information. We tackle the problem of improving the classical RGB CNN methods by using the depth information provided by the RGB-D cameras. State-of-the-art approaches use depth as an additional channel or image (HHA) or pass from 2D CNN to 3D CNN. This paper proposes a novel and generic procedure to articulate both photometric and geometric information in CNN architecture. The depth data is represented as a 2D offset to adapt …

FOS: Computer and information sciencesOffset (computer science)Computer scienceComputer Vision and Pattern Recognition (cs.CV)Coordinate systemComputer Science::Neural and Evolutionary ComputationComputer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyConvolutional neural network030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineering[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionInvariant (mathematics)business.industry[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO]020207 software engineeringWeightingSpatial coherenceComputer Science::Computer Vision and Pattern RecognitionRGB color modelArtificial intelligencebusinessLinear filter
researchProduct

A rule‐based method to model myocardial fiber orientation in cardiac biventricular geometries with outflow tracts

2019

Rule-based methods are often used for assigning fiber orientation to cardiac anatomical models. However, existing methods have been developed using data mostly from the left ventricle. As a consequence, fiber information obtained from rule-based methods often does not match histological data in other areas of the heart such as the right ventricle, having a negative impact in cardiac simulations beyond the left ventricle. In this work, we present a rule-based method where fiber orientation is separately modeled in each ventricle following observations from histology. This allows to create detailed fiber orientation in specific regions such as the endocardium of the right ventricle, the inter…

FOS: Computer and information sciencesmedicine.medical_specialtyHeart VentriclesBiomedical EngineeringFOS: Physical sciencesVolume mesh030204 cardiovascular system & hematology[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]030218 nuclear medicine & medical imagingComputational Engineering Finance and Science (cs.CE)03 medical and health sciences0302 clinical medicineRule-based methodInternal medicine[INFO.INFO-IM]Computer Science [cs]/Medical ImagingmedicineHumansComputer SimulationElectrophysiological simulationsInterventricular septumOutflow tractComputer Science - Computational Engineering Finance and ScienceMolecular BiologyEndocardiumFiber (mathematics)Orientation (computer vision)MyocardiumApplied MathematicsFiber orientationOutflow tract ventricular arrhythmiaModels CardiovascularRule-based systemSeptumMagnetic Resonance Imaging[INFO.INFO-MO]Computer Science [cs]/Modeling and SimulationPhysics - Medical PhysicsElectrophysiological Phenomenamedicine.anatomical_structureComputational Theory and MathematicsVentricleModeling and Simulationcardiovascular systemCardiologyOutflowMedical Physics (physics.med-ph)SoftwareGeologyInternational Journal for Numerical Methods in Biomedical Engineering
researchProduct

Fast PET Scan Tumor Segmentation Using Superpixels, Principal Component Analysis and K-Means Clustering

2018

Positron Emission Tomography scan images are extensively used in radiotherapy planning, clinical diagnosis, assessment of growth and treatment of a tumor. These all rely on fidelity and speed of detection and delineation algorithm. Despite intensive research, segmentation remained a challenging problem due to the diverse image content, resolution, shape, and noise. This paper presents a fast positron emission tomography tumor segmentation method in which superpixels are extracted first from the input image. Principal component analysis is then applied on the superpixels and also on their average. Distance vector of each superpixel from the average is computed in principal components coordin…

FOS: Computer and information sciencespositron emission tomographyprincipal component analysisComputer scienceComputer Vision and Pattern Recognition (cs.CV)k-meansCoordinate systemComputer Science - Computer Vision and Pattern RecognitionFOS: Physical sciences02 engineering and technologyBenchmarkQuantitative Biology - Quantitative MethodsBiochemistry Genetics and Molecular Biology (miscellaneous)030218 nuclear medicine & medical imagingsuperpixels03 medical and health sciences0302 clinical medicineStructural Biology0202 electrical engineering electronic engineering information engineeringmedicineSegmentationComputer visionTissues and Organs (q-bio.TO)Cluster analysisQuantitative Methods (q-bio.QM)Pixelmedicine.diagnostic_testbusiness.industrysegmentationk-means clusteringQuantitative Biology - Tissues and OrgansPattern recognitionPhysics - Medical PhysicsPositron emission tomographyFOS: Biological sciencesPhysics - Data Analysis Statistics and ProbabilityPrincipal component analysis020201 artificial intelligence & image processingMedical Physics (physics.med-ph)Artificial intelligenceNoise (video)businessData Analysis Statistics and Probability (physics.data-an)BiotechnologyMethods and Protocols
researchProduct

Fast Estimation of Diffusion Tensors under Rician noise by the EM algorithm

2016

Diffusion tensor imaging (DTI) is widely used to characterize, in vivo, the white matter of the central nerve system (CNS). This biological tissue contains much anatomic, structural and orientational information of fibers in human brain. Spectral data from the displacement distribution of water molecules located in the brain tissue are collected by a magnetic resonance scanner and acquired in the Fourier domain. After the Fourier inversion, the noise distribution is Gaussian in both real and imaginary parts and, as a consequence, the recorded magnitude data are corrupted by Rician noise. Statistical estimation of diffusion leads a non-linear regression problem. In this paper, we present a f…

FOS: Computer and information sciencesreduced computationGaussianModels NeurologicalDatasets as Topicta3112Statistics - ComputationStatistics - ApplicationsTime030218 nuclear medicine & medical imagingMethodology (stat.ME)Diffusion03 medical and health sciencessymbols.namesake0302 clinical medicineScoring algorithmRician fadingPrior probabilityExpectation–maximization algorithmImage Processing Computer-AssistedMaximum a posteriori estimationHumansApplications (stat.AP)Computer SimulationComputation (stat.CO)Statistics - MethodologyMathematicsta112Likelihood FunctionsGeneral NeuroscienceBrainEstimatormaximum likelihood estimatorFisher scoringMagnetic Resonance ImagingWhite MatterRician likelihoodDiffusion Tensor ImagingFourier transformNonlinear Dynamicssymbolsmaximum a posteriori estimatorAlgorithmAlgorithms030217 neurology & neurosurgerydata augmentation
researchProduct