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

698 results found

Schafer S, de Marvao A, Adami E, Fiedler LR, Ng B, Khin E, Rackham O, van Heesch S, Pua CJ, Kui M, Walsh R, Tayal U, Prasad SK, Dawes TJW, Ko NSJ, Sim D, Chan LLH, Chin CWL, Mazzarotto F, Barton PJ, Kreuchwig F, de Kleijn DPV, Totman T, Biffi C, Tee N, Rueckert D, Schneider V, Faber A, Regitz-Zagrosek V, Seidman JG, Seidman CE, Linke WA, Kovalik J, O'Regan D, Ware JS, Hubner N, Cook SAet al., 2016, Titin truncating variants affect heart function in disease cohorts and the general population, Nature Genetics, Vol: 49, Pages: 46-53, ISSN: 1546-1718

Titin-truncating variants (TTNtv) commonly cause dilated cardiomyopathy (DCM). TTNtv are also encountered in ~1% of the general population, where they may be silent, perhaps reflecting allelic factors. To better understand TTNtv, we integrated TTN allelic series, cardiac imaging and genomic data in humans and studied rat models with disparate TTNtv. In patients with DCM, TTNtv throughout titin were significantly associated with DCM. Ribosomal profiling in rat showed the translational footprint of premature stop codons in Ttn, TTNtv-position-independent nonsense-mediated degradation of the mutant allele and a signature of perturbed cardiac metabolism. Heart physiology in rats with TTNtv was unremarkable at baseline but became impaired during cardiac stress. In healthy humans, machine-learning-based analysis of high-resolution cardiac imaging showed TTNtv to be associated with eccentric cardiac remodeling. These data show that TTNtv have molecular and physiological effects on the heart across species, with a continuum of expressivity in health and disease.

Journal article

Rajchl M, Lee MCH, Oktay O, Kamnitsas K, Passerat-Palmbach J, Bai W, Damodaram M, Rutherford MA, Hajnal JV, Kainz B, Rueckert Det al., 2016, DeepCut: object segmentation from bounding box annotations using convolutional neural networks, IEEE Transactions on Medical Imaging, Vol: 36, Pages: 674-683, ISSN: 0278-0062

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in our case bounding boxes. It extends the approach of the well-known GrabCut[1] method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naïve approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.

Journal article

Kamnitsas K, Ledig C, Newcombe VFJ, Simpson JP, Kane AD, Menon DK, Rueckert D, Glocker Bet al., 2016, Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation, Medical Image Analysis, Vol: 36, Pages: 61-78, ISSN: 1361-8423

We propose a dual pathway, 11-layers deep, three-dimensional ConvolutionalNeural Network for the challenging task of brain lesion segmentation. Thedevised architecture is the result of an in-depth analysis of the limitations ofcurrent networks proposed for similar applications. To overcome the computationalburden of processing 3D medical scans, we have devised an efficientand effective dense training scheme which joins the processing of adjacentimage patches into one pass through the network while automatically adaptingto the inherent class imbalance present in the data. Further, we analyzethe development of deeper, thus more discriminative 3D CNNs. In order toincorporate both local and larger contextual information, we employ a dualpathway architecture that processes the input images at multiple scales simultaneously.For post-processing of the network’s soft segmentation, we use a3D fully connected Conditional Random Field which effectively removes falsepositives. Our pipeline is extensively evaluated on three challenging tasks oflesion segmentation in multi-channel MRI patient data with traumatic braininjuries, brain tumors, and ischemic stroke. We improve on the state-of-theartfor all three applications, with top ranking performance on the publicbenchmarks BRATS 2015 and ISLES 2015. Our method is computationallyefficient, which allows its adoption in a variety of research and clinicalsettings. The source code of our implementation is made publicly available

Journal article

Giannakidis A, Kamnitsas K, Spadotto V, Keegan J, Smith G, Glocker B, Rueckert D, Ernst S, Gatzoulis MA, Pennell DJ, Babu-Narayan S, Firmin DNet al., 2017, Fast fully automatic segmentation of the severely abnormal human right ventricle from cardiovascular magnetic resonance images using a multi-scale 3D convolutional neural network, The 12th IEEE International Conference on Signal Image Technology & Internet Systems (IEEE SITIS 2016), Publisher: IEEE

Cardiac magnetic resonance (CMR) is regardedas the reference examination for cardiac morphology intetralogy of Fallot (ToF) patients allowing images of high spa-tial resolution and high contrast. The detailed knowledge ofthe right ventricular anatomy is critical in ToF management.The segmentation of the right ventricle (RV) in CMR imagesfrom ToF patients is a challenging task due to the high shapeand image quality variability. In this paper we propose a fullyautomatic deep learning-based framework to segment the RVfrom CMR anatomical images of the whole heart. We adopt a3D multi-scale deep convolutional neural network to identifypixels that belong to the RV. Our robust segmentationframework was tested on 26 ToF patients achieving a Dicesimilarity coefficient of 0.8281±0.1010 with reference tomanual annotations performed by expert cardiologists. Theproposed technique is also computationally efficient, whichmay further facilitate its adoption in the clinical routine.

Conference paper

Ktena SI, Parisot S, Passerat-Palmbach J, Rueckert Det al., 2016, Comparison of brain networks with unknown correspondences, MICCAI Workshop on Brain Analysis using COnnectivity Networks (BACON) 2016, Publisher: BACON 2016

Graph theory has drawn a lot of attention in the field of Neuroscience duringthe last decade, mainly due to the abundance of tools that it provides toexplore the interactions of elements in a complex network like the brain. Thelocal and global organization of a brain network can shed light on mechanismsof complex cognitive functions, while disruptions within the network can belinked to neurodevelopmental disorders. In this effort, the construction of arepresentative brain network for each individual is critical for furtheranalysis. Additionally, graph comparison is an essential step for inference andclassification analyses on brain graphs. In this work we explore a method basedon graph edit distance for evaluating graph similarity, when correspondencesbetween network elements are unknown due to different underlying subdivisionsof the brain. We test this method on 30 unrelated subjects as well as 40 twinpairs and show that this method can accurately reflect the higher similaritybetween two related networks compared to unrelated ones, while identifying nodecorrespondences.

Conference paper

Peressutti D, Sinclair M, Bai W, Jackson T, Ruijsink J, Nordsletten D, Asner L, Hadjicharalambous M, Rinaldi CA, Rueckert D, King APet al., 2016, A framework for combining a motion atlas with non-motion information to learn clinically useful biomarkers: Application to cardiac resynchronisation therapy response prediction, MEDICAL IMAGE ANALYSIS, Vol: 35, Pages: 669-684, ISSN: 1361-8415

Journal article

Tong, gray, gao, Rueckertet al., 2017, Multi-modal classification of Alzheimer's disease using nonlinear graph fusion, Pattern Recognition, ISSN: 1873-5142

Journal article

Glocker B, Konukoglu E, Lavdas I, Iglesias JE, Aboagye EO, Rockall AG, Rueckert Det al., 2016, Correction of Fat-Water Swaps in Dixon MRI, 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2016), Publisher: Springer Verlag, ISSN: 0302-9743

Conference paper

Parisot S, Glocker B, Schirmer MD, Rueckert Det al., 2016, GraMPa: Graph-based Multi-modal Parcellation of the Cortex using Fusion Moves, 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2016), Publisher: Springer Verlag, ISSN: 0302-9743

Conference paper

Baumgartner CH, Kamnitsas K, Matthew J, Smith S, Kainz B, Rueckert Det al., 2016, Real-time standard scan plane detection and localisation in fetal ultrasound using fully convolutional neural networks, International Conference on Medical Image Computing and Computer-Assisted Intervention MICCAI 206, Publisher: Springer, Pages: 203-211

Fetal mid-pregnancy scans are typically carried out accordingto fixed protocols. Accurate detection of abnormalities and correctbiometric measurements hinge on the correct acquisition of clearlydefined standard scan planes. Locating these standard planes requires ahigh level of expertise. However, there is a worldwide shortage of expertsonographers. In this paper, we consider a fully automated system basedon convolutional neural networks which can detect twelve standard scanplanes as defined by the UK fetal abnormality screening programme. Thenetwork design allows real-time inference and can be naturally extendedto provide an approximate localisation of the fetal anatomy in the image.Such a framework can be used to automate or assist with scan planeselection, or for the retrospective retrieval of scan planes from recordedvideos. The method is evaluated on a large database of 1003 volunteermid-pregnancy scans. We show that standard planes acquired in a clinicalscenario are robustly detected with a precision and recall of 69 %and 80 %, which is superior to the current state-of-the-art. Furthermore,we show that it can retrospectively retrieve correct scan planes with anaccuracy of 71 % for cardiac views and 81 % for non-cardiac views.

Conference paper

Alansary A, Kamnitsas K, Davidson A, Khlebnikov R, Rajchl M, Malamateniou C, Rutherford M, Hajnal JV, Glocker B, Rueckert D, Kainz Bet al., 2016, Fast Fully Automatic Segmentation of the Human Placenta from Motion Corrupted MRI, 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2016), Publisher: Springer Verlag, ISSN: 0302-9743

Conference paper

Qin C, Moreno RG, Bowles C, Ledig C, Scheltens P, Barkhof F, Rhodius-Meester H, Tijms B, Lemstra AW, Van Der Flier WM, Glocker B, Rueckert Det al., 2016, A semi-supervised large margin algorithm for white matter hyperintensity segmentation, 7th International Workshop, MLMI 2016, Held in Conjunction with MICCAI 2016, Publisher: Springer Verlag, Pages: 104-112

Precise detection and quantification of white matter hyperintensities (WMH) is of great interest in studies of neurodegenerative diseases (NDs). In this work, we propose a novel semi-supervised large margin algorithm for the segmentation of WMH. The proposed algorithm optimizes a kernel based max-margin objective function which aims to maximize the margin averaged over inliers and outliers while exploiting a limited amount of available labelled data. We show that the learning problem can be formulated as a joint framework learning a classifier and a label assignment simultaneously, which can be solved efficiently by an iterative algorithm. We evaluate our method on a database of 280 brain Magnetic Resonance (MR) images from subjects that either suffered from subjective memory complaints or were diagnosed with NDs. The segmented WMH volumes correlate well with the standard clinical measurement (Fazekas score), and both the qualitative visualization results and quantitative correlation scores of the proposed algorithm outperform other well known methods for WMH segmentation.

Conference paper

Guerrero R, Ledig C, Schmidt-Richberg A, Rueckert Det al., 2016, Group-constrained manifold learning: Application to AD risk assessment, PATTERN RECOGNITION, Vol: 63, Pages: 570-582, ISSN: 0031-3203

Journal article

Kanavati F, Tong T, Misawa K, Fujiwara M, Mori K, Rueckert D, Glocker Bet al., 2016, Supervoxel Classification Forests for Estimating Pairwise Image Correspondences, Pattern Recognition, Vol: 63, Pages: 561-569, ISSN: 0031-3203

This article presents a general method for estimating pairwise image correspondences,which is a fundamental problem in image analysis. The method consistsof over-segmenting a pair of images into supervoxels. A forest classifier is thentrained on one of the images, the source, by using supervoxel indices as voxelwiseclass labels. Applying the forest on the other image, the target, yields asupervoxel labelling, which is then regularised using majority voting within theboundaries of the target’s supervoxels. This yields semi-dense correspondencesin a fully automatic, unsupervised, efficient and robust manner. The advantageof our approach is that no prior information or manual annotations arerequired, making it suitable as a general initialisation component for variousmedical imaging tasks that require coarse correspondences, such as atlas/patchbasedsegmentation, registration, and atlas construction. We demonstrate theeffectiveness of our approach in two different applications: a) initialisation oflongitudinal registration on spine CT data of 96 patients, and b) atlas-basedimage segmentation using 150 abdominal CT images. Comparison to state-ofthe-artmethods demonstrate the potential of supervoxel classification forestsfor estimating image correspondences.

Journal article

Oktay O, Bai W, Guerrero R, Rajchl M, de Marvao A, O Regan D, Cook S, Heinrich M, Glocker B, Rueckert D, Oktay O, Bai W, Guerrero R, Rajchl M, de Marvao A, O'Regan D, Cook S, Heinrich M, Glocker B, Rueckert Det al., 2016, Stratified decision forests for accurate anatomical landmark localization, IEEE Transactions on Medical Imaging, Vol: 36, Pages: 332-342, ISSN: 0278-0062

Accurate localization of anatomical landmarks is an important step in medical imaging, as it provides useful prior information for subsequent image analysis and acquisition methods. It is particularly useful for initialization of automatic image analysis tools (e.g. segmentation and registration) and detection of scan planes for automated image acquisition. Landmark localization has been commonly performed using learning based approaches, such as classifier and/or regressor models. However, trained models may not generalize well in heterogeneous datasets when the images contain large differences due to size, pose and shape variations of organs. To learn more data-adaptive and patient specific models, we propose a novel stratification based training model, and demonstrate its use in a decision forest. The proposed approach does not require any additional training information compared to the standard model training procedure and can be easily integrated into any decision tree framework. The proposed method is evaluated on 1080 3D highresolution and 90 multi-stack 2D cardiac cine MR images. The experiments show that the proposed method achieves state-of-theart landmark localization accuracy and outperforms standard regression and classification based approaches. Additionally, the proposed method is used in a multi-atlas segmentation to create a fully automatic segmentation pipeline, and the results show that it achieves state-of-the-art segmentation accuracy.

Journal article

Cajanus A, Hall A, Liu Y, Urhemaa T, Koikkalainen J, Rueckert D, Hasselbalch S, Mecocci P, van der Flier W, Soininen H, Lotjonen J, Remes Aet al., 2016, Analysis of frontotemporal lobar degeneration patients using automated magnetic resonance imaging analyzing tool: the MRI characteristics of C9ORF72 expansion carriers, 10th International Conference on Frontotemporal Dementias, Publisher: WILEY-BLACKWELL, Pages: 387-387, ISSN: 0022-3042

Conference paper

Cnossen MC, Polinder S, Lingsma HF, Maas AIR, Menon D, Steyerberg EW, Adams H, Alessandro M, Allanson J, Amrein K, Andaluz N, Andelic N, Andrea N, Andreassen L, Anke A, Antoni A, Ardon H, Audibert G, Auslands K, Azouvi P, Baciu C, Bacon A, Badenes R, Baglin T, Bartels R, Barzó P, Bauerfeind U, Beer R, Belda FJ, Bellander BM, Belli A, Bellier R, Benali H, Benard T, Berardino M, Beretta L, Beynon C, Bilotta F, Binder H, Biqiri E, Blaabjerg M, Borgen LS, Bouzat P, Bragge P, Brazinova A, Brehar F, Brorsson C, Buki A, Bullinger M, Bučková V, Calappi E, Cameron P, Carbayo LG, Carise E, Carpenter C, Castaño-León AM, Causin F, Chevallard G, Chieregato A, Citerio G, Coburn MC, Coles J, Cooper JD, Correia M, Covic A, Curry N, Czeiter E, Czosnyka M, Dahyot-Fizelier C, Damas F, Damas P, Dawes H, De Keyser V, Della Corte F, Depreitere B, Ding S, Dippel D, Dizdarevic K, Dulière GL, Dzeko A, Eapen G, Engemann H, Ercole A, Esser P, Ezer E, Fabricius M, Feigin VL, Feng J, Foks K, Fossi F, Francony G, Frantzén J, Freo U, Frisvold Set al., 2016, Variation in structure and process of care in traumatic brain injury: Provider profiles of European Neurotrauma Centers participating in the CENTER-TBI study, PLoS ONE, Vol: 11

© 2016 Cnossen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.Introduction: The strength of evidence underpinning care and treatment recommendations in traumatic brain injury (TBI) is low. Comparative effectiveness research (CER) has been proposed as a framework to provide evidence for optimal care for TBI patients. The first step in CER is to map the existing variation. The aim of current study is to quantify variation in general structural and process characteristics among centers participating in the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study. Methods: We designed a set of 11 provider profiling questionnaires with 321 questions about various aspects of TBI care, chosen based on literature and expert opinion. After pilot testing, questionnaires were disseminated to 71 centers from 20 countries participating in the CENTER-TBI study. Reliability of questionnaires was estimated by calculating a concordance rate among 5% duplicate questions. Results: All 71 centers completed the questionnaires. Median concordance rate among duplicate questions was 0.85. The majority of centers were academic hospitals (n = 65, 92%), designated as a level I trauma center (n = 48, 68%) and situated in an urban location (n = 70, 99%). The availability of facilities for neuro-trauma care varied across centers; e.g. 40 (57%) had a dedicated neuro-intensive care unit (ICU), 36 (51%) had an in-hospital rehabilitation unit and the organization of the ICU was closed in 64% (n = 45) of the centers. In addition, we found wide variation in processes of care, such as the ICU admission policy and intracranial pressure monitoring policy among centers. Conclusion: Even among high-volume, specialized neurotrauma centers there is substantial variat

Journal article

Tong T, Caballero J, Bhatia K, Rueckert Det al., 2016, Dictionary learning for medical image denoising, reconstruction, and segmentation, Machine Learning and Medical Imaging, Pages: 153-181, ISBN: 9780128040768

© 2016 Elsevier Inc. All rights reserved. Modeling data as sparse linear combinations of basis elements from a learnt dictionary has been widely used in signal processing and machine learning. The learnt dictionary, which is well adapted to specific data, has proven to be very effective in image restoration and classification tasks. In this chapter, we will review the most popular dictionary learning techniques such as K-SVD and online dictionary learning. We will also demonstrate how these techniques can be applied to medical imaging applications including image denoising, reconstruction, super-resolution and segmentation.

Book chapter

Maier O, Menze BH, von der Gablentz J, Häni L, Heinrich MP, Liebrand M, Winzeck S, Basit A, Bentley P, Chen L, Christiaens D, Dutil F, Egger K, Feng C, Glocker B, Götz M, Haeck T, Halme HL, Havaei M, Iftekharuddin KM, Jodoin PM, Kamnitsas K, Kellner E, Korvenoja A, Larochelle H, Ledig C, Lee JH, Maes F, Mahmood Q, Maier-Hein KH, McKinley R, Muschelli J, Pal C, Pei L, Rangarajan JR, Reza SM, Robben D, Rueckert D, Salli E, Suetens P, Wang CW, Wilms M, Kirschke JS, Krämer UM, Münte TF, Schramm P, Wiest R, Handels H, Reyes Met al., 2016, ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI, Medical Image Analysis, Vol: 35, Pages: 250-269, ISSN: 1361-8423

Ischemic stroke is the most common cerebrovascular disease, and its diagnosis, treatment, and study relies on non-invasive imaging. Algorithms for stroke lesion segmentation from magnetic resonance imaging (MRI) volumes are intensely researched, but the reported results are largely incomparable due to different datasets and evaluation schemes. We approached this urgent problem of comparability with the Ischemic Stroke Lesion Segmentation (ISLES) challenge organized in conjunction with the MICCAI 2015 conference. In this paper we propose a common evaluation framework, describe the publicly available datasets, and present the results of the two sub-challenges: Sub-Acute Stroke Lesion Segmentation (SISS) and Stroke Perfusion Estimation (SPES). A total of 16 research groups participated with a wide range of state-of-the-art automatic segmentation algorithms. A thorough analysis of the obtained data enables a critical evaluation of the current state-of-the-art, recommendations for further developments, and the identification of remaining challenges. The segmentation of acute perfusion lesions addressed in SPES was found to be feasible. However, algorithms applied to sub-acute lesion segmentation in SISS still lack accuracy. Overall, no algorithmic characteristic of any method was found to perform superior to the others. Instead, the characteristics of stroke lesion appearances, their evolution, and the observed challenges should be studied in detail. The annotated ISLES image datasets continue to be publicly available through an online evaluation system to serve as an ongoing benchmarking resource (www.isles-challenge.org).

Journal article

Xu Z, Lee CP, Heinrich MP, Modat M, Rueckert D, Ourselin S, Abramson RG, Landman BAet al., 2016, Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT, IEEE Transactions on Biomedical Engineering, Vol: 63, Pages: 1563-1572, ISSN: 1558-2531

Objective: This work evaluates current 3-D image registrationtools on clinically acquired abdominal computed tomography(CT) scans. Methods: Thirteen abdominal organs were manuallylabeled on a set of 100 CT images, and the 100 labeled images(i.e., atlases) were pairwise registered based on intensity informationwith six registration tools (FSL, ANTS-CC, ANTS-QUICKMI,IRTK, NIFTYREG, and DEEDS). The Dice similarity coeffi-cient (DSC), mean surface distance, and Hausdorff distance werecalculated on the registered organs individually. Permutation testsand indifference-zone ranking were performed to examine the statisticaland practical significance, respectively. Results: The resultssuggest that DEEDS yielded the best registration performance.However, due to the overall low DSC values, and substantial portionof low-performing outliers, great care must be taken whenimage registration is used for local interpretation of abdominalCT. Conclusion: There is substantial room for improvement inimage registration for abdominal CT. Significance: All data andsource code are available so that innovations in registration canbe directly compared with the current generation of tools withoutexcessive duplication of effort.

Journal article

Guerrero R, Schmidt-Richberg A, Ledig C, Tong T, Wolz R, Rueckert D, The Alzheimer's Disease Neuroimaging Initiative ADNIet al., 2016, Instantiated mixed effects modeling of Alzheimer's disease markers, NeuroImage, Vol: 142, Pages: 113-125, ISSN: 1053-8119

The assessment and prediction of a subject's current and future risk of developing neurodegenerative diseases like Alzheimer's disease are of great interest in both the design of clinical trials as well as in clinical decision making. Exploring the longitudinal trajectory of markers related to neurodegeneration is an important task when selecting subjects for treatment in trials and the clinic, in the evaluation of early disease indicators and the monitoring of disease progression. Given that there is substantial intersubject variability, models that attempt to describe marker trajectories for a whole population will likely lack specificity for the representation of individual patients. Therefore, we argue here that individualized models provide a more accurate alternative that can be used for tasks such as population stratification and a subject-specific prognosis. In the work presented here, mixed effects modeling is used to derive global and individual marker trajectories for a training population. Test subject (new patient) specific models are then instantiated using a stratified “marker signature” that defines a subpopulation of similar cases within the training database. From this subpopulation, personalized models of the expected trajectory of several markers are subsequently estimated for unseen patients. These patient specific models of markers are shown to provide better predictions of time-to-conversion to Alzheimer's disease than population based models.

Journal article

Ktena SI, Rueckert D, 2016, A topological graph kernel for gender classification of functional brain networks, 22nd Annual Meeting of the Organization for Human Brain Mapping

Network science encompasses the study of the human brain and can lead to fundamental insights into the organization of the healthy and diseased brain, while incorporating knowledge of elementary system components as well as the interactions between them and their emerging properties. In this study, we propose a different way of analysing functional brain networks based on functional MRI data of 100 subjects from the Human Connectome Project (http://www.humanconnectome.org) and attempt to identify the differences between the two genders, since sex has demonstrated a substantial influence on many areas of brain and behavior.

Conference paper

Shi W, Caballero J, Huszár F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Zet al., 2016, Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network, CVPR 2016, Publisher: IEEE, Pages: 1874-1883, ISSN: 1063-6919

Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly bicubic interpolation, before reconstruction. This means that the super-resolution (SR) operation is performed in HR space. We demonstrate that this is sub-optimal and adds computational complexity. In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. To achieve this, we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. By doing so, we effectively replace the handcrafted bicubic filter in the SR pipeline with more complex upscaling filters specifically trained for each feature map, whilst also reducing the computational complexity of the overall SR operation. We evaluate the proposed approach using images and videos from publicly available datasets and show that it performs significantly better (+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude faster than previous CNN-based methods.

Conference paper

Huizinga W, Poot DHJ, Roshchupkin G, Bron EE, Ikram MA, Vernooij MW, Rueckert D, Niessen WJ, Klein Set al., 2016, Modeling the brain morphology distribution in the general aging population, SPIE Biomedical Applications in Molecular, Structural and Functional Imaging Conference, Publisher: SPIE-INT SOC OPTICAL ENGINEERING, ISSN: 0277-786X

Both normal aging and neurodegenerative diseases such as Alzheimer’s disease cause morphological changes of the brain. To better distinguish between normal and abnormal cases, it is necessary to model changes in brain morphology owing to normal aging. To this end, we developed a method for analyzing and visualizing these changes for the entire brain morphology distribution in the general aging population. The method is applied to 1000 subjects from a large population imaging study in the elderly, from which 900 were used to train the model and 100 were used for testing. The results of the 100 test subjects show that the model generalizes to subjects outside the model population. Smooth percentile curves showing the brain morphology changes as a function of age and spatiotemporal atlases derived from the model population are publicly available via an interactive web application at agingbrain.bigr.nl.

Conference paper

Rueckert D, Glocker B, Kainz B, 2016, Learning clinically useful information from images: Past, present and future, Medical Image Analysis, Vol: 33, Pages: 13-18, ISSN: 1361-8423

Over the last decade, research in medical imaging has made significantprogress in addressing challenging tasks such as image registration and imagesegmentation. In particular, the use of model-based approaches has been keyin numerous, successful advances in methodology. The advantage of modelbasedapproaches is that they allow the incorporation of prior knowledgeacting as a regularisation that favours plausible solutions over implausibleones. More recently, medical imaging has moved away from hand-crafted, andoften explicitly designed models towards data-driven, implicit models thatare constructed using machine learning techniques. This has led to majorimprovements in all stages of the medical imaging pipeline, from acquisitionand reconstruction to analysis and interpretation. As more and more imagingdata is becoming available, e.g., from large population studies, this trend islikely to continue and accelerate. At the same time new developments inmachine learning, e.g., deep learning, as well as significant improvementsin computing power, e.g., parallelisation on graphics hardware, offer newpotential for data-driven, semantic and intelligent medical imaging. Thisarticle outlines the work of the BioMedIA group in this area and highlightssome of the challenges and opportunities for future work.

Journal article

Parpas P, Rustem, Duy VN Luong, Rueckert, Parpas P, Luong, Rustem, Rueckertet al., 2016, A weighted Mirror Descent algorithm for nonsmooth convex optimization problem, Journal of Optimization Theory and Applications, Vol: 170, Pages: 900-915, ISSN: 1573-2878

Large scale nonsmooth convex optimization is a common problemfor a range of computational areas including machine learning and computer vision. Problems in these areas contain special domain structures and characteristics. Special treatment of such problem domains, exploiting their structures, can significantly reduce the computational burden. In this paper, we consider a Mirror Descent method with a special choice of distance function for solving nonsmooth optimization problems over a Cartesian product of convex sets. We propose to use a nonlinear weighted distance in the projectionstep. The convergence analysis identifies optimal weighting parameters that, eventually, lead to the optimally weighted step-size strategy for every projection on a corresponding convex set. We show that the optimality bound of the Mirror Descent algorithm using the weighted distance is either an improvement to, or in the worst-case as good as, the optimality bound of the Mirror Descent using unweighted distances. We demonstrate the efficiency of the algorithm by solving the Markov Random Fields (MRF) optimization problem. In order to exploit the domain of the MRF problem, we use a weighted logentropy distance and a weighted Euclidean distance. Promising experimentalresults demonstrate the effectiveness of the proposed method.

Journal article

Baumgartner CF, Kolbitsch C, McClelland JR, Rueckert D, King APet al., 2016, Autoadaptive motion modelling for MR-based respiratory motion estimation, Medical Image Analysis, Vol: 35, Pages: 83-100, ISSN: 1361-8423

Respiratory motion poses significant challenges in image-guided interventions. In emerging treatments such as MR-guided HIFU or MR-guided radiotherapy, it may cause significant misalignments between interventional road maps obtained pre-procedure and the anatomy during the treatment, and may affect intra-procedural imaging such as MR-thermometry. Patient specific respiratory motion models provide a solution to this problem. They establish a correspondence between the patient motion and simpler surrogate data which can be acquired easily during the treatment. Patient motion can then be estimated during the treatment by acquiring only the simpler surrogate data.In the majority of classical motion modelling approaches once the correspondence between the surrogate data and the patient motion is established it cannot be changed unless the model is recalibrated. However, breathing patterns are known to significantly change in the time frame of MR-guided interventions. Thus, the classical motion modelling approach may yield inaccurate motion estimations when the relation between the motion and the surrogate data changes over the duration of the treatment and frequent recalibration may not be feasible.We propose a novel methodology for motion modelling which has the ability to automatically adapt to new breathing patterns. This is achieved by choosing the surrogate data in such a way that it can be used to estimate the current motion in 3D as well as to update the motion model. In particular, in this work, we use 2D MR slices from different slice positions to build as well as to apply the motion model. We implemented such an autoadaptive motion model by extending our previous work on manifold alignment.We demonstrate a proof-of-principle of the proposed technique on cardiac gated data of the thorax and evaluate its adaptive behaviour on realistic synthetic data containing two breathing types generated from 6 volunteers, and real data from 4 volunteers. On synthetic data the

Journal article

Rajchl M, Lee M, Schrans F, Davidson A, Passerat-Palmbach J, Tarroni G, Alansary A, Oktay O, Kainz B, Rueckert Det al., 2016, Learning under Distributed Weak Supervision

The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks and collect such annotations from a crowd of non-expert raters. The crowd annotations are subsequently used for training a fully convolutional neural network to address the problem of fetal brain segmentation in T2-weighted MR images. Using this approach we report encouraging results compared to highly targeted, fully supervised methods and potentially address a frequent problem impeding image analysis research.

Working paper

Tolonen A, Rhodius-Meester H, Bruun M, Baroni M, Koikkalainen J, Barkhof F, Tijms B, Lemstra A, Tong T, Guerrero R, Schuh A, Ledig C, Rueckert D, Soininen H, Remes A, Waldemar G, Hasselbalch S, Mecocci P, van der Flier W, Lotjonen Jet al., 2016, Data-driven differential diagnostics of neurodegenerative diseases, Publisher: WILEY, Pages: 347-347, ISSN: 1351-5101

Conference paper

Corden B, de Marvao A, Dawes T, Shi W, Rueckert D, Cook S, O'Regan DPet al., 2016, Relationship between body composition and left ventricular geometry using three dimensional cardiovascular magnetic resonance, Journal of Cardiovascular Magnetic Resonance, Vol: 18, ISSN: 1532-429X

BackgroundAlthough obesity is associated with alterations in left ventricular (LV) mass and volume which are of prognostic significance, widely differing patterns of remodelling have been attributed to adiposity. Our aim was to define the relationship between body composition and LV geometry using three-dimensional cardiovascular magnetic resonance.MethodsIn an observational study 1530 volunteers (55 % female, mean age 41.3 years) without known cardiovascular disease underwent investigation including breath-hold high spatial resolution 3D cines. Atlas-based segmentation and co-registration was used to create a statistical model of wall thickness (WT) and relative wall thickness (RWT) throughout the LV. The relationship between bio-impedence body composition and LV geometry was assessed using 3D regression models adjusted for age, systolic blood pressure (BP), gender, race and height, with correction to control the false discovery rate.ResultsLV mass was positively associated with fat mass in women but not in men (LV mass: women β = 0.11, p < 0.0001; men β = −0.01, p = 0.82). The 3D models revealed that in males fat mass was strongly associated with a concentric increase in relative wall thickness (RWT) throughout most of the LV (β = 0.37, significant area = 96 %) and a reduced mid-ventricular cavity (β = −0.22, significant area = 91 %). In women the regional concentric hypertrophic association was weaker, and the basal lateral wall showed an inverse relationship between RWT and fat mass (β = −0.11, significant area = 4.8 %).ConclusionsIn an adult population without known cardiovascular disease increasing body fat is predominately associated with asymmetric concentric hypertrophy independent of systolic BP, with women demonstrating greater cavity dilatation than men. Conventional mass

Journal article

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=6&respub-action=search.html