Abstract:
:Typically, a medical image offers spatial information on the anatomy (and pathology) modulated by imaging specific characteristics. Many imaging modalities including Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) can be interpreted in this way. We can venture further and consider that a medical image naturally factors into some spatial factors depicting anatomy and factors that denote the imaging characteristics. Here, we explicitly learn this decomposed (disentangled) representation of imaging data, focusing in particular on cardiac images. We propose Spatial Decomposition Network (SDNet), which factorises 2D medical images into spatial anatomical factors and non-spatial modality factors. We demonstrate that this high-level representation is ideally suited for several medical image analysis tasks, such as semi-supervised segmentation, multi-task segmentation and regression, and image-to-image synthesis. Specifically, we show that our model can match the performance of fully supervised segmentation models, using only a fraction of the labelled images. Critically, we show that our factorised representation also benefits from supervision obtained either when we use auxiliary tasks to train the model in a multi-task setting (e.g. regressing to known cardiac indices), or when aggregating multimodal data from different sources (e.g. pooling together MRI and CT data). To explore the properties of the learned factorisation, we perform latent-space arithmetic and show that we can synthesise CT from MR and vice versa, by swapping the modality factors. We also demonstrate that the factor holding image specific information can be used to predict the input modality with high accuracy. Code will be made available at https://github.com/agis85/anatomy_modality_decomposition.
journal_name
Med Image Analjournal_title
Medical image analysisauthors
Chartsias A,Joyce T,Papanastasiou G,Semple S,Williams M,Newby DE,Dharmakumar R,Tsaftaris SAdoi
10.1016/j.media.2019.101535subject
Has Abstractpub_date
2019-12-01 00:00:00pages
101535eissn
1361-8415issn
1361-8423pii
S1361-8415(19)30068-4journal_volume
58pub_type
杂志文章abstract::During embryogenesis, a mammalian heart develops from a simple tubular shape into a complex 4-chamber organ, going through four distinct phases: early primitive tubular heart, emergence of trabeculations, trabecular remodeling and development of the compact myocardium. In this paper we propose a framework for standard...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2018.08.001
更新日期:2018-10-01 00:00:00
abstract::In-silico continuum simulations of organ and tissue scale physiology often require a discretisation or mesh of the solution domain. Cubic Hermite meshes provide a smooth representation of anatomy that is well-suited for simulating large deformation mechanics. Models of organ mechanics and deformation have demonstrated...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2011.06.010
更新日期:2011-12-01 00:00:00
abstract::In this paper, we present a generative Bayesian approach for estimating the low-dimensional latent space of diffeomorphic shape variability in a population of images. We develop a latent variable model for principal geodesic analysis (PGA) that provides a probabilistic framework for factor analysis in the space of dif...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.04.009
更新日期:2015-10-01 00:00:00
abstract::The goal of this study is to provide a theoretical framework for accurately optimizing the segmentation energy considering all of the possible shapes generated from the level-set-based statistical shape model (SSM). The proposed algorithm solves the well-known open problem, in which a shape prior may not be optimal in...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.11.003
更新日期:2016-02-01 00:00:00
abstract::Registration of three-dimensional ultrasound (3DUS) volumes is necessary in several applications, such as when stitching volumes to expand the field of view or when stabilizing a temporal sequence of volumes to cancel out motion of the probe or anatomy. Current systems that register 3DUS volumes either use external tr...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2011.10.004
更新日期:2012-02-01 00:00:00
abstract::Creating a feature-preserving average of three dimensional anatomical surfaces extracted from volume image data is a complex task. Unlike individual images, averages present right-left symmetry and smooth surfaces which give insight into typical proportions. Averaging multiple biological surface images requires carefu...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(00)00031-1
更新日期:2000-12-01 00:00:00
abstract::This article describes a combination of interactive classification and super-sampling visualization algorithms that greatly enhances the realism of 3-D reconstructions of the Visible Human data sets. Objects are classified on the basis of ellipsoidal regions in RGB space. The ellipsoids are used for super-sampling in ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(97)85001-3
更新日期:1997-09-01 00:00:00
abstract::In this paper, we present a framework to estimate local ventricular myocardium contractility using clinical MRI, a heart model and data assimilation. First, we build a generic anatomical model of the ventricles including muscle fibre orientations and anatomical subdivisions. Then, this model is deformed to fit a clini...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2006.04.002
更新日期:2006-08-01 00:00:00
abstract::It has previously been demonstrated that freehand 3D ultrasound can be acquired without a position sensor by measuring the elevational speckle decorrelation from frame to frame. However, this requires that the B-scans contain significant amounts of fully developed speckle. In this paper, we show that this condition is...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2005.08.001
更新日期:2006-04-01 00:00:00
abstract::We propose a novel airway segmentation method in volumetric chest computed tomography (CT) and evaluate its performance on multiple datasets. The segmentation is performed voxel-by-voxel by a 2.5D convolutional neural net (2.5D CNN) trained in a supervised manner. To enhance the accuracy of the segmented airway tree, ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2018.10.006
更新日期:2019-01-01 00:00:00
abstract::Ultrasonic techniques are presented for the study of soft biological tissue structure and function. Changes in echo waveforms caused by microscopic variations in the mechanical properties of tissue can reveal disease mechanism, in vivo. On a larger scale, elasticity imaging describes the macroscopic mechanical propert...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(98)80014-5
更新日期:1998-12-01 00:00:00
abstract::Over the past 20 years, the field of medical image registration has significantly advanced from multi-modal image fusion to highly non-linear, deformable image registration for a wide range of medical applications and imaging modalities, involving the compensation and analysis of physiological organ motion or of tissu...
journal_title:Medical image analysis
pub_type: 社论
doi:10.1016/j.media.2016.06.031
更新日期:2016-10-01 00:00:00
abstract::Synthesized medical images have several important applications. For instance, they can be used as an intermedium in cross-modality image registration or used as augmented training samples to boost the generalization capability of a classifier. In this work, we propose a generic cross-modality synthesis approach with t...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2018.12.002
更新日期:2019-02-01 00:00:00
abstract::Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.09.005
更新日期:2016-01-01 00:00:00
abstract::The Insight Toolkit (ITK) initiative from the National Library of Medicine has provided a suite of state-of-the-art segmentation and registration algorithms ideally suited to volume visualization and analysis. A volume visualization application that effectively utilizes these algorithms provides many benefits: it allo...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2005.04.009
更新日期:2005-12-01 00:00:00
abstract::We describe a new 3-D statistical shape model of the heart consisting of atria, ventricles and epicardium. The model was constructed by combining information on standard short- and long-axis cardiac MR images. In the model, the variability of the shape was modeled with PCA- and ICA-based shape models as well as with n...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2004.06.013
更新日期:2004-09-01 00:00:00
abstract::We introduce a new approach to medical image analysis that combines deformable model methodologies with concepts from the field of artificial life. In particular, we propose "deformable organisms", autonomous agents whose task is the automatic segmentation, labeling, and quantitative analysis of anatomical structures ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(02)00083-x
更新日期:2002-09-01 00:00:00
abstract::To analyze dynamic positron emission tomography (PET) images, various generic multivariate data analysis techniques have been considered in the literature, such as principal component analysis (PCA), independent component analysis (ICA), factor analysis and nonnegative matrix factorization (NMF). Nevertheless, these c...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2018.07.011
更新日期:2018-10-01 00:00:00
abstract::In this paper, we propose a novel automated pipeline for extraction of sulcal fundi from triangulated cortical surfaces. This method consists of four consecutive steps. Firstly, we adopt a finite difference method to estimate principal curvatures, principal directions and curvature derivatives, along the principal dir...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2010.01.005
更新日期:2010-06-01 00:00:00
abstract::Pseudo-healthy synthesis is the task of creating a subject-specific 'healthy' image from a pathological one. Such images can be helpful in tasks such as anomaly detection and understanding changes induced by pathology and disease. In this paper, we present a model that is encouraged to disentangle the information of p...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2020.101719
更新日期:2020-08-01 00:00:00
abstract::The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thu...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2014.05.004
更新日期:2014-10-01 00:00:00
abstract::Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is chal...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2019.101561
更新日期:2020-01-01 00:00:00
abstract::In this paper an automatic atlas-based segmentation algorithm for 4D cardiac MR images is proposed. The algorithm is based on the 4D extension of the expectation maximisation (EM) algorithm. The EM algorithm uses a 4D probabilistic cardiac atlas to estimate the initial model parameters and to integrate a priori inform...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2004.06.005
更新日期:2004-09-01 00:00:00
abstract::Accurate automated segmentation and detection of ovarian cancer metastases may improve the diagnosis and prognosis of women with ovarian cancer. In this paper, we focus on an important subset of ovarian cancer metastases that spread to the surface of the liver and spleen. Automated ovarian cancer metastasis detection ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2014.04.001
更新日期:2014-07-01 00:00:00
abstract::Diffusion magnetic resonance imaging (dMRI) offers a unique tool for noninvasively assessing tissue microstructure. However, accurate estimation of tissue microstructure described by complicated signal models can be challenging when a reduced number of diffusion gradients are used. Deep learning based microstructure e...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2019.04.006
更新日期:2019-07-01 00:00:00
abstract::This paper describes a new robust and fully automatic method for calibration of three-dimensional (3D) freehand ultrasound called Confhusius (CalibratiON for FreeHand UltraSound Imaging USage). 3D Freehand ultrasound consists in mounting a position sensor on a standard probe. The echographic B-scans can be localized i...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2004.06.021
更新日期:2005-02-01 00:00:00
abstract::In this work a new statistic deformable model for 3D segmentation of anatomical organs in medical images is proposed. A statistic discriminant snake performs a supervised learning of the object boundary in an image slice to segment the next slice of the image sequence. Each part of the object boundary is projected in ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(03)00014-8
更新日期:2003-09-01 00:00:00
abstract::Percutaneous coronary intervention is a minimally invasive procedure that is usually performed under image guidance using X-ray angiograms in which coronary arteries are opacified with contrast agent. In X-ray images, 3D objects are projected on a 2D plane, generating semi-transparent layers that overlap each other. T...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2017.04.011
更新日期:2017-07-01 00:00:00
abstract::Human brain alignment based on imaging data has long been an intriguing research topic. One of the challenges is the huge inter-individual variabilities, which are pronounced not only in cortical folding patterns, but also in the underlying structural and functional patterns. Also, it is still not fully understood how...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2020.101700
更新日期:2020-07-01 00:00:00
abstract::Three dimensional Polarized Light Imaging (3D-PLI) is an optical technique which allows mapping the spatial fiber architecture of fibrous postmortem tissues, at sub-millimeter resolutions. Here, we propose an analytical and fast approach to compute the fiber orientation distribution (FOD) from high-resolution vector d...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2020.101760
更新日期:2020-10-01 00:00:00