Imperial College London

ProfessorDanielRueckert

Faculty of EngineeringDepartment of Computing

Head of Department of Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8333d.rueckert Website

 
 
//

Location

 

568Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

693 results found

Baumgartner CF, Kolbitsch C, Balfour DR, Marsden PK, McClelland JR, Rueckert D, King APet al., 2014, High-resolution dynamic MR imaging of the thorax for respiratory motion correction of PET using groupwise manifold alignment, MEDICAL IMAGE ANALYSIS, Vol: 18, Pages: 939-952, ISSN: 1361-8415

Journal article

Makropoulos A, Gousias IS, Ledig C, Aljabar P, Serag A, Hajnal JV, Edwards AD, Counsell SJ, Rueckert Det al., 2014, Automatic Whole Brain MRI Segmentation of the Developing Neonatal Brain, IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 33, Pages: 1818-1831, ISSN: 0278-0062

Journal article

Sohal M, Duckett SG, Zhuang X, Shi W, Ginks M, Shetty A, Sammut E, Kozerke S, Niederer S, Smith N, Ourselin S, Rinaldi CA, Rueckert D, Carr-White G, Razavi Ret al., 2014, A prospective evaluation of cardiovascular magnetic resonance measures of dyssynchrony in the prediction of response to cardiac resynchronization therapy, JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE, Vol: 16, ISSN: 1097-6647

Journal article

Wolz R, Schwarz AJ, Yu P, Cole PE, Rueckert D, Jack CR, Raunig D, Hill Det al., 2014, Robustness of automated hippocampal volumetry across magnetic resonance field strengths and repeat images, ALZHEIMERS & DEMENTIA, Vol: 10, Pages: 430-438, ISSN: 1552-5260

Journal article

Guerrero R, Wolz R, Rao AW, Rueckert Det al., 2014, Manifold population modeling as a neuro-imaging biomarker: Application to ADNI and ADNI-GO, NEUROIMAGE, Vol: 94, Pages: 275-286, ISSN: 1053-8119

Journal article

Tong T, Wolz R, Ga Q, Guerrero R, Hajnal JV, Rueckert Det al., 2014, Multiple instance learning for classification of dementia in brain MRI, MEDICAL IMAGE ANALYSIS, Vol: 18, Pages: 808-818, ISSN: 1361-8415

Journal article

Boardman JP, Walley A, Ball G, Takousis P, Krishnan ML, Hughes-Carre L, Aljabar P, Serag A, King C, Merchant N, Srinivasan L, Froguel P, Hajnal J, Rueckert D, Counsell S, Edwards ADet al., 2014, Common Genetic Variants and Risk of Brain Injury After Preterm Birth, PEDIATRICS, Vol: 133, Pages: E1655-E1663, ISSN: 0031-4005

Journal article

Tenovuo O, Menon D, van Gils M, Rueckert D, Katila A, Coles J, Mattila J, Ledig C, Frantzen J, Outtrim J, Lotjonen J, Siitari Het al., 2014, Improving the individual diagnostics of TBI-The international TBIcare project

Poster

Wright R, Kyriakopoulou V, Ledig C, Rutherford MA, Hajnal JV, Rueckert D, Aljabar Pet al., 2014, Automatic quantification of normal cortical folding patterns from fetal brain MRI, NEUROIMAGE, Vol: 91, Pages: 21-32, ISSN: 1053-8119

Journal article

Kainz B, Voglreiter P, Sereinigg M, Wiederstein-Grasser I, Mayrhauser U, Kostenbauer S, Pollari M, Khlebnikov R, Seise M, Alhonnoro T, Hame Y, Seider D, Flanagan R, Bost C, Muhl J, O Neill D, Peng T, Payne S, Rueckert D, Schmalstieg D, Moche M, Kolesnik M, Stiegler P, Portugaller RHet al., 2014, High-resolution contrast enhanced multi-phase hepatic Computed Tomography data fromaporcine Radio-Frequency Ablation study, 11th International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 81-84

Data below 1 mm voxel size is getting more and more common in the clinical practice but it is still hard to obtain a consistent collection of such datasets for medical image processing research. With this paper we provide a large collection of Contrast Enhanced (CE) Computed Tomography (CT) data from porcine animal experiments and describe their acquisition procedure and peculiarities. We have acquired three CE-CT phases at the highest available scanner resolution of 57 porcine livers during induced respiratory arrest. These phases capture contrast enhanced hepatic arteries, portal venous veins and hepatic veins. Therefore, we provide scan data that allows for a highly accurate reconstruction of hepatic vessel trees. Several datasets have been acquired during Radio-Frequency Ablation (RFA) experiments. Hence, many datasets show also artificially induced hepatic lesions, which can be used for the evaluation of structure detection methods.

Conference paper

Kainz B, Keraudren K, Kyriakopoulou V, Rutherford M, Hajnal JV, Rueckert Det al., 2014, Fast fully automatic brain detection in fetal MRI using dense rotation invariant image descriptors, 11th International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 1230-1233

Automatic detection of the fetal brain in Magnetic Resonance (MR) Images is especially difficult due to arbitrary orientation of the fetus and possible movements during the scan. In this paper, we propose a method to facilitate fully automatic brain voxel classification by means of rotation invariant volume descriptors. We calculate features for a set of 50 prenatal fast spin echo T2 volumes of the uterus and learn the appearance of the fetal brain in the feature space. We evaluate our novel classification method and show that we can localize the fetal brain with an accuracy of 100% and classify fetal brain voxels with an accuracy above 97%. Furthermore, we show how the classification process can be used for a direct segmentation of the brain by simple refinement methods within the raw MR scan data leading to a final segmentation with a Dice score above 0.90.

Conference paper

karim R, 2014, A Method to Standardize Quantification of Left Atrial Scar From Delayed-Enhancement MR Images, IEEE Journal of Translational Engineering in Health and Medicine, ISSN: 2168-2372

Journal article

Zang KY, Kedgley AE, Donoghue CD, Rueckert D, Bull AMet al., 2014, MORPHOLOGICAL STUDY OF LATERAL MENISCUS USING STATISTICAL SHAPE MODELLING: A STUDY USING DATA FROM THE OSTEOARTHRITIS INITIATIVE, World Congress of the Osteoarthritis-Research-Society-International (OARSI)

Poster

Caballero J, Price AN, Rueckert D, Hajnal JVet al., 2014, Dictionary learning and time sparsity for dynamic MR data reconstruction, IEEE Transactions on Medical Imaging, Vol: 33, Pages: 979-994, ISSN: 1558-254X

Journal article

Newcombe V, Ledig C, Abate G, Outtrim J, Chatfield D, Geeraerts T, Manktelow A, Hutchinson PJ, Coles J, Williams G, Rueckert D, Menon DKet al., 2014, DYNAMIC EVOLUTION OF ATROPHY AFTER MODERATE TO SEVERE TRAUMATIC BRAIN INJURY, 11th Symposium of the International-Neurotrauma-Society

Poster

de Marvao A, Dawes TJW, Shi W, Minas C, Keenan NG, Diamond T, Durighel G, Montana G, Rueckert D, Cook SA, O'Regan DPet al., 2014, Population-based studies of myocardial hypertrophy: high resolution cardiovascular magnetic resonance atlases improve statistical power, Journal of Cardiovascular Magnetic Resonance, Vol: 16, ISSN: 1532-429X

Background: Cardiac phenotypes, such as left ventricular (LV) mass, demonstrate high heritability although mostgenes associated with these complex traits remain unidentified. Genome-wide association studies (GWAS) haverelied on conventional 2D cardiovascular magnetic resonance (CMR) as the gold-standard for phenotyping.However this technique is insensitive to the regional variations in wall thickness which are often associated with leftventricular hypertrophy and require large cohorts to reach significance. Here we test whether automated cardiacphenotyping using high spatial resolution CMR atlases can achieve improved precision for mapping wall thicknessin healthy populations and whether smaller sample sizes are required compared to conventional methods.Methods: LV short-axis cine images were acquired in 138 healthy volunteers using standard 2D imaging and 3Dhigh spatial resolution CMR. A multi-atlas technique was used to segment and co-register each image. Theagreement between methods for end-diastolic volume and mass was made using Bland-Altman analysis in 20subjects. The 3D and 2D segmentations of the LV were compared to manual labeling by the proportion ofconcordant voxels (Dice coefficient) and the distances separating corresponding points. Parametric andnonparametric data were analysed with paired t-tests and Wilcoxon signed-rank test respectively. Voxelwise powercalculations used the interstudy variances of wall thickness.Results: The 3D volumetric measurements showed no bias compared to 2D imaging. The segmented 3D imageswere more accurate than 2D images for defining the epicardium (Dice: 0.95 vs 0.93, P < 0.001; mean error 1.3 mmvs 2.2 mm, P < 0.001) and endocardium (Dice 0.95 vs 0.93, P < 0.001; mean error 1.1 mm vs 2.0 mm, P < 0.001). The3D technique resulted in significant differences in wall thickness assessment at the base, septum and apex of theLV compared to 2D (P < 0.001). Fewer subjects were required for 3D imaging to detect a 1 mm d

Journal article

Bhatia KK, Rao A, Price AN, Wolz R, Hajnal JV, Rueckert Det al., 2014, Hierarchical manifold learning for regional image analysis., IEEE Trans Med Imaging, Vol: 33, Pages: 444-461

We present a novel method of hierarchical manifold learning which aims to automatically discover regional properties of image datasets. While traditional manifold learning methods have become widely used for dimensionality reduction in medical imaging, they suffer from only being able to consider whole images as single data points. We extend conventional techniques by additionally examining local variations, in order to produce spatially-varying manifold embeddings that characterize a given dataset. This involves constructing manifolds in a hierarchy of image patches of increasing granularity, while ensuring consistency between hierarchy levels. We demonstrate the utility of our method in two very different settings: 1) to learn the regional correlations in motion within a sequence of time-resolved MR images of the thoracic cavity; 2) to find discriminative regions of 3-D brain MR images associated with neurodegenerative disease.

Journal article

Rueckert D, Schnabel JA, 2014, Registration and segmentation in medical imaging, Pages: 137-156, ISBN: 9783642449062

The analysis of medical images plays an increasingly important role in many clinical applications. Different imaging modalities often provide complementary anatomical information about the underlying tissues such as the X-ray attenuation coefficients from X-ray computed tomography (CT), and proton density or proton relaxation times from magnetic resonance (MR) imaging. The images allow clinicians to gather information about the size, shape and spatial relationship between anatomical structures and any pathology, if present. Other imaging modalities provide functional information such as the blood flow or glucose metabolism from positron emission tomography (PET) or single-photon emission tomography (SPECT), and permit clinicians to study the relationship between anatomy and physiology. Finally, histological images provide another important source of information which depicts structures at a microscopic level of resolution. © 2014 Springer-Verlag Berlin Heidelberg.

Book chapter

Rueckert D, Wolz R, Aljabar P, 2014, Machine learning meets medical imaging: Learning and discovery of clinically useful information from images, 4th Eccomas Thematic Conference on Computational Vision and Medical Image Processing (VipIMAGE)

Poster

Gao Q, Asthana A, Tong T, Rueckert D, Edwards PEet al., 2014, Multi-scale Feature Learning on Pixels and Super-pixels for Seminal Vesicles MRI Segmentation, Conference on Medical Imaging - Image Processing, Publisher: SPIE-INT SOC OPTICAL ENGINEERING, ISSN: 0277-786X

Conference paper

Gao Q, Tong T, Rueckert D, Edwards PJEet al., 2014, Multi-Atlas Propagation via a Manifold Graph on a Database of Both Labeled and Unlabeled Images, Conference on Medical Imaging - Computer-Aided Diagnosis, Publisher: SPIE-INT SOC OPTICAL ENGINEERING, ISSN: 0277-786X

Conference paper

Bentley P, Ganesalingam J, Jones ALC, Mahady K, Epton S, Rinne P, Sharma P, Halse O, Mehta A, Rueckert Det al., 2014, Prediction of stroke thrombolysis outcome using CT brain machine learning, NEUROIMAGE-CLINICAL, Vol: 4, Pages: 635-640, ISSN: 2213-1582

Journal article

Wu X, Housden RJ, Varma N, Ma Y, Rhode KS, Rueckert Det al., 2014, Fast catheter tracking in echocardiographic sequences for cardiac catheterization interventions, Pages: 171-179, ISSN: 0302-9743

For most cardiac catheterization interventions, X-ray imaging is currently used as a standard imaging technique. However, lack of 3D soft tissue information and harmful radiation mean that X-ray imaging is not an ideal modality. In contrast, 3D echocardiography can overcome these disadvantages. In this paper, we propose a fast catheter tracking strategy for 3D ultrasound sequences. The main advantage of our strategy is low use of X-ray imaging, which significantly decreases the radiation exposure. In addition, 3D soft tissue imaging can be introduced by using ultrasound. To enable the tracking procedure, initialization is carried out on the first ultrasound frame. Given the location of the catheter in the previous frame, which is in the form of a set of ordered landmarks, 3D Speeded-Up Robust Feature (SURF) responses are calculated for candidate voxels in the surrounding region of each landmark on the next frame. One candidate is selected among all voxels for each landmark based on Fast Primal-Dual optimization (Fast-PD). As a result, a new set of ordered landmarks is extracted, corresponding to the potential location of the catheter on the next frame. In order to adapt the tracking to the changing length of the catheter in the view, landmarks which may not be located on the catheter are ruled out. Then a catheter growing strategy is performed to extend the tracked part of the catheter to the untracked part. Based on 10 ultrasound phantom sequences and two clinical sequences, comprising more than 1300 frames, our experimental results show that the tracking system can track catheters with an error of less than 2.5mm and a speed of more than 3 fps. © Springer-Verlag Berlin Heidelberg 2014.

Conference paper

Zhang KY, Kedgley AE, Donoghue CR, Rueckert D, Bull AMJet al., 2014, The relationship between lateral meniscus shape and joint contact parameters in the knee: a study using data from the Osteoarthritis Initiative, ARTHRITIS RESEARCH & THERAPY, Vol: 16, ISSN: 1478-6354

Journal article

Xi J, Shi W, Rueckert D, Razavi R, Smith NP, Lamata Pet al., 2014, Understanding the need of ventricular pressure for the estimation of diastolic biomarkers, Biomechanics and Modeling in Mechanobiology, Vol: 13, Pages: 747-757, ISSN: 1617-7959

The diastolic function (i.e., blood filling) of the left ventricle (LV) is determined by its capacity for relaxation, or the decay in residual active tension (AT) generated during systole, and its constitutive material properties, or myocardial stiffness. The clinical determination of these two factors (diastolic residual AT and stiffness) is thus essential for assessing LV diastolic function. To quantify these two factors, in our previous work, a novel model-based parameter estimation approach was proposed and successfully applied to multiple cases using clinically acquired motion and invasively measured ventricular pressure data. However, the need to invasively acquire LV pressure limits the wide application of this approach. In this study, we address this issue by analyzing the feasibility of using two kinds of non-invasively available pressure measurements for the purpose of inverse mechanical parameter estimation. The prescription of pressure based on a generic pressure-volume (P-V) relationship reported in literature is first evaluated in a set of 18 clinical cases (10 healthy and 8 diseased), finding reasonable results for stiffness but not for residual active tension. We then investigate the use of non-invasive pressure measures, now available through imaging techniques and limited by unknown or biased offset values. Specifically, three sets of physiologically realistic synthetic data with three levels of diastolic residual active tension (i.e., impaired relaxation capability) are designed to quantify the percentage error in the parameter estimation against the possible pressure offsets within the physiological limits. Maximum errors are quantified as 11 % for the magnitude of stiffness and 22 % for AT, with averaged 0.17 kPa error in pressure measurement offset using the state-of-the-art non-invasive pressure estimation method. The main cause for these errors is the limited temporal resolution of clinical imaging data currently available. These results demo

Journal article

Rueckert D, Schnabel JA, 2014, Registration and segmentation in medical imaging, Studies in Computational Intelligence, Vol: 532, Pages: 137-156, ISSN: 1860-949X

The analysis of medical images plays an increasingly important role in many clinical applications. Different imaging modalities often provide complementary anatomical information about the underlying tissues such as the X-ray attenuation coefficients from X-ray computed tomography (CT), and proton density or proton relaxation times from magnetic resonance (MR) imaging. The images allow clinicians to gather information about the size, shape and spatial relationship between anatomical structures and any pathology, if present. Other imaging modalities provide functional information such as the blood flow or glucose metabolism from positron emission tomography (PET) or single-photon emission tomography (SPECT), and permit clinicians to study the relationship between anatomy and physiology. Finally, histological images provide another important source of information which depicts structures at a microscopic level of resolution. © 2014 Springer-Verlag Berlin Heidelberg.

Journal article

Schirmer MD, Ball G, Counsell SJ, Edwards AD, Rueckert D, Hajnal JV, Aljabar Pet al., 2014, Parcellation-independent multi-scale framework for brain network analysis, Pages: 23-32, ISSN: 1612-3786

© Springer International Publishing Switzerland 2014. Structural brain connectivity can be characterised by studies employing diffusion MR, tractography and the derivation of network measures. However, in some subject populations, such as neonates, the lack of a generally accepted paradigm for how the brain should be segmented or parcellated leads to the application of a variety of atlas- and random-based parcellation methods. The resulting challenge of comparing graphs with differing numbers of nodes and uncertain node correspondences has yet to be resolved, in order to enable more meaningful intraand inter-subject comparisons. This work proposes a parcellation-independent multi-scale analysis of commonly used network measures to describe changes in the brain. As an illustration, we apply our framework to a neonatal serial diffusion MRI data set and show its potential in characterising developmental changes. Furthermore, we use the measures provided by the framework to investigate the inter-dependence between network measures and apply an hierarchical clustering algorithm to determine a subset of measures for characterising the brain.

Conference paper

Wu X, Housden J, Ma Y, Rhode K, Rueckert Det al., 2014, A FAST CATHETER SEGMENTATION AND TRACKING FROM ECHOCARDIOGRAPHIC SEQUENCES BASED ON CORRESPONDING X-RAY FLUOROSCOPIC IMAGE SEGMENTATION AND HIERARCHICAL GRAPH MODELLING, 11th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 951-954, ISSN: 1945-7928

Conference paper

Koikkalainen J, Lotjonen J, Ledig C, Rueckert D, Tenovuo O, Menon Det al., 2014, AUTOMATIC QUANTIFICATION OF CT IMAGES FOR TRAUMATIC BRAIN INJURY, 11th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 125-128, ISSN: 1945-7928

Conference paper

Baumgartner CE, Kolbitsch C, McClelland JR, Rueckert D, King APet al., 2014, AUTOADAPTIVE MOTION MODELLING, 11th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 457-460, ISSN: 1945-7928

Conference paper

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: id=00172041&limit=30&person=true&page=10&respub-action=search.html