Unsupervised MR-to-CT Synthesis Using Structure-Constrained CycleGAN.

Abstract:

:Synthesizing a CT image from an available MR image has recently emerged as a key goal in radiotherapy treatment planning for cancer patients. CycleGANs have achieved promising results on unsupervised MR-to-CT image synthesis; however, because they have no direct constraints between input and synthetic images, cycleGANs do not guarantee structural consistency between these two images. This means that anatomical geometry can be shifted in the synthetic CT images, clearly a highly undesirable outcome in the given application. In this paper, we propose a structure-constrained cycleGAN for unsupervised MR-to-CT synthesis by defining an extra structure-consistency loss based on the modality independent neighborhood descriptor. We also utilize a spectral normalization technique to stabilize the training process and a self-attention module to model the long-range spatial dependencies in the synthetic images. Results on unpaired brain and abdomen MR-to-CT image synthesis show that our method produces better synthetic CT images in both accuracy and visual quality as compared to other unsupervised synthesis methods. We also show that an approximate affine pre-registration for unpaired training data can improve synthesis results.

journal_name

IEEE Trans Med Imaging

authors

Yang H,Sun J,Carass A,Zhao C,Lee J,Prince JL,Xu Z

doi

10.1109/TMI.2020.3015379

subject

Has Abstract

pub_date

2020-12-01 00:00:00

pages

4249-4261

issue

12

eissn

0278-0062

issn

1558-254X

journal_volume

39

pub_type

杂志文章
  • Stopping Rule for the MLE Algorithm Based on Statistical Hypothesis Testing.

    abstract::It is known that when the maximum likelihood estimator (MLE) algorithm passes a certain point, it produces images that begin to deteriorate. We propose a quantitative criterion with a simple probabilistic interpretation that allows the user to stop the algorithm just before this effect begins. The MLE algorithm search...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.1987.4307849

    authors: Veklerov E,Llacer J

    更新日期:1987-01-01 00:00:00

  • An Enhanced SMART-RECON Algorithm for Time-Resolved C-Arm Cone-Beam CT Imaging.

    abstract::Temporal resolution in time-resolved cone-beam CT (TR-CBCT) imaging is often limited by the time needed to acquire a complete data set for image reconstruction. With the recent developments of performing nearly limited-view artifact-free reconstruction from data in a limited-view angle range and a prior image, tempora...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2019.2960720

    authors: Li Y,Garrett JW,Li K,Strother C,Chen GH

    更新日期:2020-06-01 00:00:00

  • Simultaneous Photoacoustic Imaging and Cavitation Mapping in Shockwave Lithotripsy.

    abstract::Kidney stone disease is a major health problem worldwide. Shockwave lithotripsy (SWL), which uses high-energy shockwave pulses to break up kidney stones, is extensively used in clinic. However, despite its noninvasiveness, SWL can produce cavitation in vivo. The rapid expansion and violent collapse of cavitation bubbl...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2019.2928740

    authors: Li M,Lan B,Sankin G,Zhou Y,Liu W,Xia J,Wang D,Trahey G,Zhong P,Yao J

    更新日期:2020-02-01 00:00:00

  • Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis.

    abstract::The automatic diagnosis of various retinal diseases from fundus images is important to support clinical decision-making. However, developing such automatic solutions is challenging due to the requirement of a large amount of human-annotated data. Recently, unsupervised/self-supervised feature learning techniques recei...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2020.3008871

    authors: Li X,Jia M,Islam MT,Yu L,Xing L

    更新日期:2020-12-01 00:00:00

  • A wavelet-based multiresolution regularized least squares reconstruction approach for optical tomography.

    abstract::In this paper, we present a wavelet-based multigrid approach to solve the perturbation equation encountered in optical tomography. With this scheme, the unknown image, the data, as well as the weight matrix are all represented by wavelet expansions, thus yielding a multiresolution representation of the original pertur...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/42.563666

    authors: Zhu W,Wang Y,Deng Y,Yao Y,Barbour RL

    更新日期:1997-04-01 00:00:00

  • Magnetic resonance angiography.

    abstract::This paper describes several methods for magnetic resonance angiography that create projection images based solely on flowing blood. To both remove static tissue from the image and generate signals from blood, two classes of methods considered are temporal subtraction and cancelling excitation. Temporal subtraction, a...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.1986.4307763

    authors: Nishimura DG,Macovski A,Pauly JM

    更新日期:1986-01-01 00:00:00

  • Anti-aliasing weighting functions for single-slice helical CT.

    abstract::Spatially variant longitudinal aliasing plagues most volumes reconstructed from single-slice helical computed tomography data, and its presence can degrade resolution and distort image structures. We have recently developed a Fourier-based approach to longitudinal interpolation in helical computed tomography that can,...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2002.803104

    authors: La Rivière PJ,Pan X

    更新日期:2002-08-01 00:00:00

  • Ovarian ultrasound image analysis: follicle segmentation.

    abstract::Ovarian ultrasound is an effective tool in infertility treatment. Repeated measurements of the size and shape of follicles over several days are the primary means of evaluation by physicians. Currently, follicle wall segmentation is achieved by manual tracing which is time consuming and susceptible to inter-operator v...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/42.746626

    authors: Krivanek A,Sonka M

    更新日期:1998-12-01 00:00:00

  • Automatic Cataract Classification Using Deep Neural Network With Discrete State Transition.

    abstract::Cataract is the clouding of lens, which affects vision and it is the leading cause of blindness in the world's population. Accurate and convenient cataract detection and cataract severity evaluation will improve the situation. Automatic cataract detection and grading methods are proposed in this paper. With prior know...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2019.2928229

    authors: Zhou Y,Li G,Li H

    更新日期:2020-02-01 00:00:00

  • Lumen segmentation and motion estimation in B-mode and contrast-enhanced ultrasound images of the carotid artery in patients with atherosclerotic plaque.

    abstract::In standard B-mode ultrasound (BMUS), segmentation of the lumen of atherosclerotic carotid arteries and studying the lumen geometry over time are difficult owing to irregular lumen shapes, noise, artifacts, and echolucent plaques. Contrast enhanced ultrasound (CEUS) improves lumen visualization, but lumen segmentation...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2014.2372784

    authors: Carvalho DD,Akkus Z,van den Oord SC,Schinkel AF,van der Steen AF,Niessen WJ,Bosch JG,Klein S

    更新日期:2015-04-01 00:00:00

  • Selection of a convolution function for Fourier inversion using gridding [computerised tomography application].

    abstract::In the technique known as gridding, the data samples are weighted for sampling density and convolved with a finite kernel, then resampled on a grid preparatory to a fast Fourier transform. The authors compare the artifact introduced into the image for various convolving functions of different sizes, including the Kais...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/42.97598

    authors: Jackson JI,Meyer CH,Nishimura DG,Macovski A

    更新日期:1991-01-01 00:00:00

  • A spatiotemporal model of cyclic kinematics and its application to analyzing nonrigid motion with MR velocity images.

    abstract::We present a method (DMESH) for nonrigid cyclic motion analysis using a series of velocity images covering the cycle acquired, for example, from phase-contrast magnetic resonance imaging. The method is based on fitting a dynamic finite-element mesh model to velocity samples of an extended region, at all time frames. T...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/42.790456

    authors: Zhu Y,Pelc NJ

    更新日期:1999-07-01 00:00:00

  • Hybrid feature-based diffeomorphic registration for tumor tracking in 2-D liver ultrasound images.

    abstract::Real-time ultrasound image acquisition is a pivotal resource in the medical community, in spite of its limited image quality. This poses challenges to image registration methods, particularly to those driven by intensity values. We address these difficulties in a novel diffeomorphic registration technique for tumor tr...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2013.2262055

    authors: Cifor A,Risser L,Chung D,Anderson EM,Schnabel JA

    更新日期:2013-09-01 00:00:00

  • Automatic Segmentation of Wrist Bones in CT Using a Statistical Wrist Shape + Pose Model.

    abstract::Segmentation of the wrist bones in CT images has been frequently used in different clinical applications including arthritis evaluation, bone age assessment and image-guided interventions. The major challenges include non-uniformity and spongy textures of the bone tissue as well as narrow inter-bone spaces. In this wo...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2016.2529500

    authors: Anas EM,Rasoulian A,Seitel A,Darras K,Wilson D,John PS,Pichora D,Mousavi P,Rohling R,Abolmaesumi P

    更新日期:2016-08-01 00:00:00

  • Parameterization-invariant shape comparisons of anatomical surfaces.

    abstract::We consider 3-D brain structures as continuous parameterized surfaces and present a metric for their comparisons that is invariant to the way they are parameterized. Past comparisons of such surfaces involve either volume deformations or nonrigid matching under fixed parameterizations of surfaces. We propose a new mat...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2010.2099130

    authors: Kurtek S,Klassen E,Ding Z,Jacobson SW,Jacobson JL,Avison MJ,Srivastava A

    更新日期:2011-03-01 00:00:00

  • Semiautomated border tracking of cine echocardiographic ventnrcular images.

    abstract::Two-dimensional ultrasound sector scans of the left ventricle (LV) are commonly used to diagnose cardiac mechanical function. Present quantification procedures of wall motion by this technique entail inaccuracies, mainly due to relatively poor image quality and the absence of a definition of the relative position of t...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.1987.4307836

    authors: Adam D,Hareuveni O,Sideman S

    更新日期:1987-01-01 00:00:00

  • Dynamic PET reconstruction using wavelet regularization with adapted basis functions.

    abstract::Tomographic reconstruction from positron emission tomography (PET) data is an ill-posed problem that requires regularization. An attractive approach is to impose an l(1) -regularization constraint, which favors sparse solutions in the wavelet domain. This can be achieved quite efficiently thanks to the iterative algor...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2008.923698

    authors: Verhaeghe J,Van de Ville D,Khalidov I,D'Asseler Y,Lemahieu I,Unser M

    更新日期:2008-01-01 00:00:00

  • Improving Blood Vessel Tortuosity Measurements via Highly Sampled Numerical Integration of the Frenet-Serret Equations.

    abstract::Measures of vascular tortuosity-how curved and twisted a vessel is-are associated with a variety of vascular diseases. Consequently, measurements of vessel tortuosity that are accurate and comparable across modality, resolution, and size are greatly needed. Yet in practice, precise and consistent measurements are prob...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2020.3025467

    authors: Brummer AB,Hunt D,Savage V

    更新日期:2021-01-01 00:00:00

  • MDM-PCCT: Multiple Dynamic Modulations for High-Performance Spectral PCCT Imaging.

    abstract::Photon counting computed tomography (PCCT) has the ability to identify individual photons, resulting in quantitative material identification. Meanwhile, several technical challenges still exist in current PCCT imaging systems, including increased noise and suboptimal bin selection. These nonideal effects can substanti...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2020.3001616

    authors: Li D,Zeng D,Li S,Ge Y,Bian Z,Huang J,Ma J

    更新日期:2020-11-01 00:00:00

  • On Bayesian image reconstruction from projections: uniform and nonuniform a priori source information.

    abstract::A method that incorporates a priori uniform or nonuniform source distribution probabilistic information and data fluctuations of a Poisson nature is presented. The source distributions are modeled in terms of a priori source probability density functions. Maximum a posteriori probability solutions, as determined by a ...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/42.34711

    authors: Liang Z,Jaszczak R,Greer K

    更新日期:1989-01-01 00:00:00

  • Combined volumetric and surface registration.

    abstract::In this paper, we propose a novel method for the registration of volumetric images of the brain that optimizes the alignment of both cortical and subcortical structures. In order to achieve this, relevant geometrical information is extracted from a surface-based morph and diffused into the volume using the Navier oper...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2008.2004426

    authors: Postelnicu G,Zollei L,Fischl B

    更新日期:2009-04-01 00:00:00

  • Classification of malignant and benign masses based on hybrid ART2LDA approach.

    abstract::A new type of classifier combining an unsupervised and a supervised model was designed and applied to classification of malignant and benign masses on mammograms. The unsupervised model was based on an adaptive resonance theory (ART2) network which clustered the masses into a number of separate classes. The classes we...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/42.819327

    authors: Hadjiiski L,Sahiner B,Chan HP,Petrick N,Helvie M

    更新日期:1999-12-01 00:00:00

  • The hypervolume under the ROC hypersurface of "near-guessing" and "near-perfect" observers in N-class classification tasks.

    abstract::We express the performance of the N-class "guessing" observer in terms of the N2-N conditional probabilities which make up an N-class receiver operating characteristic (ROC) space, in a formulation in which sensitivities are eliminated in constructing the ROC space (equivalent to using false-negative fraction and fals...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/tmi.2004.841227

    authors: Edwards DC,Metz CE,Nishikawa RM

    更新日期:2005-03-01 00:00:00

  • Imaging of cardiac movement using ratiometric and nonratiometric optical mapping: effects of ischemia and 2, 3-butaneodione monoxime.

    abstract::Transmembrane voltage-sensitive fluorescent dyes are used to study electrical activity in hearts. Green and red fluorescence emissions from di-4-ANEPPS excited with 488 nm light indicate both transmembrane voltage changes and heart movement. We have previously shown that the ratio, green fluorescence divided by red fl...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2005.861019

    authors: Himel HD 4th,Knisley SB

    更新日期:2006-01-01 00:00:00

  • Dynamic Cell Imaging in PET With Optimal Transport Regularization.

    abstract::We propose a novel dynamic image reconstruction method from PET listmode data that could be particularly suited to tracking single or small numbers of cells. In contrast to conventional PET reconstruction our method combines the information from all detected events not only to reconstruct the dynamic evolution of the ...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2019.2953773

    authors: Schmitzer B,Schafers KP,Wirth B

    更新日期:2020-05-01 00:00:00

  • Analysis of the role of lead resistivity in specific absorption rate for deep brain stimulator leads at 3T MRI.

    abstract::Magnetic resonance imaging (MRI) on patients with implanted deep brain stimulators (DBSs) can be hazardous because of the antenna-effect of leads exposed to the incident radio-frequency field. This study evaluated electromagnetic field and specific absorption rate (SAR) changes as a function of lead resistivity on an ...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2010.2040624

    authors: Angelone LM,Ahveninen J,Belliveau JW,Bonmassar G

    更新日期:2010-04-01 00:00:00

  • Multi-scale tubular structure detection in ultrasound imaging.

    abstract::We propose a novel, physics-based method for detecting multi-scale tubular features in ultrasound images. The detector is based on a Hessian-matrix eigenvalue method, but unlike previous work, our detector is guided by an optimal model of vessel-like structures with respect to the ultrasound-image formation process. O...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2014.2340912

    authors: Hennersperger C,Baust M,Waelkens P,Karamalis A,Ahmadi SA,Navab N

    更新日期:2015-01-01 00:00:00

  • A maximum a posteriori probability expectation maximization algorithm for image reconstruction in emission tomography.

    abstract::The expectation maximization method for maximum likelihood image reconstruction in emission tomography, based on the Poisson distribution of the statistically independent components of the image and measurement vectors, is extended to a maximum aposteriori image reconstruction using a multivariate Gaussian a priori pr...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.1987.4307826

    authors: Levitan E,Herman GT

    更新日期:1987-01-01 00:00:00

  • Vulnerable atherosclerotic plaque elasticity reconstruction based on a segmentation-driven optimization procedure using strain measurements: theoretical framework.

    abstract::It is now recognized that prediction of the vulnerable coronary plaque rupture requires not only an accurate quantification of fibrous cap thickness and necrotic core morphology but also a precise knowledge of the mechanical properties of plaque components. Indeed, such knowledge would allow a precise evaluation of th...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2009.2012852

    authors: Le Floc'h S,Ohayon J,Tracqui P,Finet G,Gharib AM,Maurice RL,Cloutier G,Pettigrew RI

    更新日期:2009-07-01 00:00:00

  • Surface Reconstruction for free-space 360 degrees fluorescence molecular tomography and the effects of animal motion.

    abstract::Complete projection (360 degrees ) free-space fluorescence tomography of opaque media is poised to enable 3-D imaging through entire small animals in vivo with improved depth resolution compared to 360 degrees -projection fiber-based systems or limited-view angle systems. This approach can lead to a new generation of ...

    journal_title:IEEE transactions on medical imaging

    pub_type: 杂志文章

    doi:10.1109/TMI.2007.904662

    authors: Lasser T,Soubret A,Ripoll J,Ntziachristos V

    更新日期:2008-02-01 00:00:00