Wenzhe Shi

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

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.

A Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR Images

The evaluation of ventricular function is important for the diagnosis of cardiovascular diseases. It typically involves measurement of the left ventricular (LV) mass and LV cavity volume. Manual delineation of the myocardial contours is time-consuming and dependent on the subjective experience of the expert observer. In this paper, a multi-atlas method is proposed for cardiac magnetic resonance (MR) image segmentation. The proposed method is novel in two aspects. First, it formulates a patch-based label fusion model in a Bayesian framework. Second, it improves image registration accuracy by utilizing label information, which leads to improvement of segmentation accuracy. The proposed method was evaluated on a cardiac MR image set of 28 subjects. The average Dice overlap metric of our segmentation is 0.92 for the LV cavity, 0.89 for the right ventricular cavity and 0.82 for the myocardium. The results show that the proposed method is able to provide accurate information for clinical diagnosis.

Benchmarking framework for myocardial tracking and deformation algorithms: An open access database

In this paper we present a benchmarking framework for the validation of cardiac motion analysis algorithms. The reported methods are the response to an open challenge that was issued to the medical imaging community through a MICCAI workshop. The database included magnetic resonance (MR) and 3D ultrasound (3DUS) datasets from a dynamic phantom and 15 healthy volunteers. Participants processed 3D tagged MR datasets (3DTAG), cine steady state free precession MR datasets (SSFP) and 3DUS datasets, amounting to 1158 image volumes. Ground-truth for motion tracking was based on 12 landmarks (4 walls at 3 ventricular levels). They were manually tracked by two observers in the 3DTAG data over the whole cardiac cycle, using an in-house application with 4D visualization capabilities. The median of the inter-observer variability was computed for the phantom dataset (0.77 mm) and for the volunteer datasets (0.84 mm). The ground-truth was registered to 3DUS coordinates using a point based similarity transform. Four institutions responded to the challenge by providing motion estimates for the data: Fraunhofer MEVIS (MEVIS), Bremen, Germany; Imperial College London - University College London (IUCL), UK; Universitat Pompeu Fabra (UPF), Barcelona, Spain; Inria-Asclepios project (INRIA), France. Details on the implementation and evaluation of the four methodologies are presented in this manuscript. The manually tracked landmarks were used to evaluate tracking accuracy of all methodologies. For 3DTAG, median values were computed over all time frames for the phantom dataset (MEVIS=1.20mm, IUCL=0.73 mm, UPF=1.10mm, INRIA=1.09 mm) and for the volunteer datasets (MEVIS=1.33 mm, IUCL=1.52 mm, UPF=1.09 mm, INRIA=1.32 mm). For 3DUS, median values were computed at end diastole and end systole for the phantom dataset (MEVIS=4.40 mm, UPF=3.48 mm, INRIA=4.78 mm) and for the volunteer datasets (MEVIS=3.51 mm, UPF=3.71 mm, INRIA=4.07 mm). For SSFP, median values were computed at end diastole and end systole for the phantom dataset(UPF=6.18 mm, INRIA=3.93 mm) and for the volunteer datasets (UPF=3.09 mm, INRIA=4.78 mm). Finally, strain curves were generated and qualitatively compared. Good agreement was found between the different modalities and methodologies, except for radial strain that showed a high variability in cases of lower image quality.

Evaluation of current algorithms for segmentation of scar tissue from late Gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge

BackgroundLate Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging can be used to visualise regions of fibrosis and scarring in the left atrium (LA) myocardium. This can be important for treatment stratification of patients with atrial fibrillation (AF) and for assessment of treatment after radio frequency catheter ablation (RFCA). In this paper we present a standardised evaluation benchmarking framework for algorithms segmenting fibrosis and scar from LGE CMR images. The algorithms reported are the response to an open challenge that was put to the medical imaging community through an ISBI (IEEE International Symposium on Biomedical Imaging) workshop.MethodsThe image database consisted of 60 multicenter, multivendor LGE CMR image datasets from patients with AF, with 30 images taken before and 30 after RFCA for the treatment of AF. A reference standard for scar and fibrosis was established by merging manual segmentations from three observers. Furthermore, scar was also quantified using 2, 3 and 4 standard deviations (SD) and full-width-at-half-maximum (FWHM) methods. Seven institutions responded to the challenge: Imperial College (IC), Mevis Fraunhofer (MV), Sunnybrook Health Sciences (SY), Harvard/Boston University (HB), Yale School of Medicine (YL), King’s College London (KCL) and Utah CARMA (UTA, UTB). There were 8 different algorithms evaluated in this study.ResultsSome algorithms were able to perform significantly better than SD and FWHM methods in both pre- and post-ablation imaging. Segmentation in pre-ablation images was challenging and good correlation with the reference standard was found in post-ablation images. Overlap scores (out of 100) with the reference standard were as follows: Pre: IC = 37, MV = 22, SY = 17, YL = 48, KCL = 30, UTA = 42, UTB = 45; Post: IC = 76, MV = 85, SY = 73, HB = 76, YL = 84, KCL = 78, UTA = 78, UTB = 72.ConclusionsThe study concludes that currently no algorithm is deemed clearly better than others. There is scope for further algorithmic developments in LA fibrosis and scar quantification from LGE CMR images. Benchmarking of future scar segmentation algorithms is thus important. The proposed benchmarking framework is made available as open-source and new participants can evaluate their algorithms via a web-based interface.

The estimation of patient-specific cardiac diastolic functions from clinical measurements

An unresolved issue in patients with diastolic dysfunction is that the estimation of myocardial stiffness cannot be decoupled from diastolic residual active tension (AT) because of the impaired ventricular relaxation during diastole. To address this problem, this paper presents a method for estimating diastolic mechanical parameters of the left ventricle (LV) from cine and tagged MRI measurements and LV cavity pressure recordings, separating the passive myocardial constitutive properties and diastolic residual AT. Dynamic C1-continuous meshes are automatically built from the anatomy and deformation captured from dynamic MRI sequences. Diastolic deformation is simulated using a mechanical model that combines passive and active material properties. The problem of non-uniqueness of constitutive parameter estimation using the well known Guccione law is characterized by reformulation of this law. Using this reformulated form, and by constraining the constitutive parameters to be constant across time points during diastole, we separate the effects of passive constitutive properties and the residual AT during diastolic relaxation. Finally, the method is applied to two clinical cases and one control, demonstrating that increased residual AT during diastole provides a potential novel index for delineating healthy and pathological cases.

A Comprehensive Cardiac Motion Estimation Framework Using Both Untagged and 3-D Tagged MR Images Based on Nonrigid Registration

In this paper, we present a novel technique based on nonrigid image registration for myocardial motion estimation using both untagged and 3-D tagged MR images. The novel aspect of our technique is its simultaneous usage of complementary information from both untagged and 3-D tagged MR images. To estimate the motion within the myocardium, we register a sequence of tagged and untagged MR images during the cardiac cycle to a set of reference tagged and untagged MR images at end-diastole. The similarity measure is spatially weighted to maximize the utility of information from both images. In addition, the proposed approach integrates a valve plane tracker and adaptive incompressibility into the framework. We have evaluated the proposed approach on 12 subjects. Our results show a clear improvement in terms of accuracy compared to approaches that use either 3-D tagged or untagged MR image information alone. The relative error compared to manually tracked landmarks is less than 15% throughout the cardiac cycle. Finally, we demonstrate the automatic analysis of cardiac function from the myocardial deformation fields.

Cardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch

The accurate measurement of 3D cardiac function is an important task in the analysis of cardiac magnetic resonance (MR) images. However, short-axis image acquisitions with thick slices are commonly used in clinical practice due to constraints of acquisition time, signal-to-noise ratio and patient compliance. In this situation, the estimation of a high-resolution image can provide an approximation of the underlaying 3D measurements. In this paper, we develop a novel algorithm for the estimation of high-resolution cardiac MR images from single short-axis cardiac MR image stacks. First, we propose to use a novel approximate global search approach to find patch correspondence between the short-axis MR image and a set of atlases. Then, we propose an innovative super-resolution model which does not require explicit motion estimation. Finally, we build an expectation-maximization framework to optimize the model. We validate the proposed approach using images from 19 subjects with 200 atlases and show that the proposed algorithm significantly outperforms conventional interpolation such as linear or B-spline interpolation. In addition, we show that the super-resolved images can be used for the reproducible estimation of 3D cardiac functional indices.

Temporal sparse free-form deformations

FFD represent a widely used model for the non-rigid registration of medical images. The balance between robustness to noise and accuracy in modelling localised motion is typically controlled by the control point grid spacing and the amount of regularisation. More recently, TFFD have been proposed which extend the FFD approach in order to recover smooth motion from temporal image sequences. In this paper, we revisit the classic FFD approach and propose a sparse representation using the principles of compressed sensing. The sparse representation can model both global and local motion accurately and robustly. We view the registration as a deformation reconstruction problem. The deformation is reconstructed from a pair of images (or image sequences) with a sparsity constraint applied to the parametric space. Specifically, we introduce sparsity into the deformation via L1 regularisation, and apply a bending energy regularisation between neighbouring control points within each level to encourage a grouped sparse solution. We further extend the sparsity constraint to the temporal domain and propose a TSFFD which can capture fine local details such as motion discontinuities in both space and time without sacrificing robustness. We demonstrate the capabilities of the proposed framework to accurately estimate deformations in dynamic 2D and 3D image sequences. Compared to the classic FFD and TFFD approach, a significant increase in registration accuracy can be observed in natural images as well as in cardiac images.

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

Atlases encode valuable anatomical and functional information from a population. In this work, a bi-ventricular cardiac atlas was built from a unique data set, which consists of high resolution cardiac MR images of 1000+ normal subjects. Based on the atlas, statistical methods were used to study the variation of cardiac shapes and the distribution of cardiac motion across the spatio-temporal domain. We have shown how statistical parametric mapping (SPM) can be combined with a general linear model to study the impact of gender and age on regional myocardial wall thickness. Finally, we have also investigated the influence of the population size on atlas construction and atlas-based analysis. The high resolution atlas, the statistical models and the SPM method will benefit more studies on cardiac anatomy and function analysis in the future.