Skip to main content
main-content

Über dieses Buch

This book constitutes the refereed proceedings of the First International Workshop on Simulation and Synthesis in Medical Imaging, held in conjunction with MICCAI 2016, in Athens, Greece, in October 2016.

The 17 revised full papers presented together in this book were carefully reviewed and selected from 21 submissions.

The contributions span the following broad categories: fundamental methods for image-based biophysical modeling and image synthesis; biophysical and data-driven models of disease progression or organ development; biophysical and data-driven models of organ motion and deformation; biophysical and data-driven models of image formation and acquisition; segmentation/registration across or within modalities to aid the learning of model parameters; cross modality (PET/MR, PET/CT, CT/MR, etc.) image synthesis; simulation and synthesis from large-scale image databases; automated techniques for quality assessment of simulations and synthetic images; as well as several applications of image synthesis and simulation in medical imaging such as image registration and segmentation; image denoising and information fusion; image reconstruction from sparse data or sparse views; and real-time simulation of biophysical properties. The papers were divided into two general topics named “simulation based approaches for medical imaging” and “synthesis and its applications in computational medical imaging”.

Inhaltsverzeichnis

Frontmatter

Simulation and Its Applications in Computational Medical Imaging

Frontmatter

Software Framework for Realistic MRI Simulations Using the Polyhedral Fourier Transform

This work presents a freely available operating system-independent Matlab software tool for simulation of magnetic resonance imaging (MRI) acquisition and image reconstruction using polyhedral phantoms. The tool is based on an efficient implementation of the closed form solution of the polyhedral Fourier transform (FT). The software tool, named “PolyFT”, can be applied to polyhedral surface and tetrahedral volume meshes. The tool enables the calculation of the Fourier domain representation of physiologically relevant objects with spatially varying intensities, permitting accurate simulation of slice selection and parallel imaging techniques that require coil sensitivity profiles. Several examples of applications are given. Though more computationally intense than the FT, the polyhedral FT allows relevant simulation of both MRI sampling and reconstruction processes. The freely-available software tool should be useful in the same situations in which the standard Shepp-Logan phantom is used, and additionally when analytical Fourier representations of objects with non-uniform intensities are needed.
Shuo Han, Daniel A. Herzka

Covering Population Variability: Morphing of Computation Anatomical Models

We present a method to change the volume of organs or tissues in computational anatomical models by simulating the human body as a biomechanical solid with initial strains causing local volume shrinkage or expansion. The non-linear hyperelastic material behavior is solved with the finite element method. The bone positions are prescribed and treated as rigid bodies surrounded by elastic soft tissue. A multi-domain mesh defines individual bones and at least one soft tissue region. Each region can have different material properties, volume growth rates or mesh settings. The method can be used to deform complex anatomical models, such as the Virtual Population models. The proposed strategy has been used to parametrize models by different BMI levels, change the volume of selected organs, and modify the posture of anatomical models.
Bryn Lloyd, Emilio Cherubini, Silvia Farcito, Esra Neufeld, Christian Baumgartner, Niels Kuster

Image-Based PSF Estimation for Ultrasound Training Simulation

A key aspect for virtual-reality based ultrasound training is the plausible simulation of the characteristic noise pattern known as ultrasonic speckle. The formation of ultrasonic speckle can be approximated efficiently by convolving the ultrasound point-spread function (PSF) with a distribution of point scatterers. Recent work extracts the latter directly from ultrasound images for use in forward simulation, assuming that the PSF can be known, e.g., from experiments. In this paper, we investigate the problem of automatically estimating an unknown PSF for the purpose of ultrasound simulation, such as to use in convolution-based ultrasound image formation. Our method estimates the PSF directly from an ultrasound image, based on homomorphic filtering in the cepstrum domain. It robustly captures local changes in the PSF as a function of depth, and hence is able to reproduce continuous ultrasound beam profiles. We compare our method to numerical simulations as the ground truth to study PSF estimation accuracy, achieving small approximation errors of \({\le }15\,\%\) FWHM. We also demonstrate simulated in-vivo images, with beam profiles estimated from real images.
Oliver Mattausch, Orcun Goksel

Microstructure Imaging Sequence Simulation Toolbox

This work describes Microstructure Imaging Sequence Simulation Toolbox (MISST), a practical diffusion MRI simulator for development, testing, and optimisation of novel MR pulse sequences for microstructure imaging. Diffusion MRI measures molecular displacement at microscopic level and provides a non-invasive tool for probing tissue microstructure. The measured signal is determined by various cellular features such as size, shape, intracellular volume fraction, orientation, etc., as well as the acquisition parameters of the diffusion sequence. Numerical simulations are a key step in understanding the effect of various parameters on the measured signal, which is important when developing new techniques for characterizing tissue microstructure using diffusion MRI. Here we present MISST - a semi-analytical simulation software, which is based on a matrix method approach and computes diffusion signal for fully general, user specified pulse sequences and tissue models. Its key purpose is to provide a deep understanding of the restricted diffusion MRI signal for a wide range of realistic, fully flexible scanner acquisition protocols, in practical computational time.
Andrada Ianuş, Daniel C. Alexander, Ivana Drobnjak

From Image-Based Modeling to the Modeling of Imaging with the Virtual Population

Image data has been used to create the Virtual Population models, a range of highly detailed anatomical models (male/female, neonates/children/adults/elderly, average build/obese) which have been found to be useful for a wide range of computational life sciences applications. They are at the core of the Sim4Life simulation platform. Different image modalities provide a wealth of information enabling model functionalization by facilitating anatomy parameterization and animation, consideration of tissue inhomogeneity, imposition of realistic boundary conditions, and integration of dynamic physiological models. Closing the circle, these functionalized anatomical models have also been used to generate virtual image data, particularly by simulating MR imaging. Thus, image data can be produced under controlled conditions and with known base-anatomy for different pulse sequences. Virtual imaging has been used to study different imaging artefacts.
Esra Neufeld, Bryn Lloyd, Niels Kuster

Numerical Simulation of Ultrasonic Backscattering During Fracture Healing Using Numerical Models Based on Scanning Acoustic Microscopy Images

Quantitative ultrasound has been used as a monitoring means of osteoporosis and fracture healing by several research groups worldwide applying experimental and computational techniques. However, fracture healing is a complex biological process and an interdisciplinary knowledge is required to fully comprehend the pathways of bone regeneration and gene expression as well as the structural and material changes occurring at different healing stages. Over the last decade, the incorporation of computational tools and the illustration of bone microstructure and material properties at different hierarchical levels using micro-computed tomography and scanning acoustic microscopy (SAM) have paved the way for the investigation of complex wave propagation phenomena which cannot be observed via traditional experimental procedures. In this study, we use the boundary element method to perform simulations of ultrasound propagation at successive bone healing stages. Bone healing is simulated as a three stage process and numerical models are established based on SAM images derived from week 3, week 6 and week 9 after the osteotomy. Callus is considered as a two-dimensional medium and its composite nature is integrated in the models via the combination of SAM images and an iterative effective medium approximation. We use a plane wave excitation at 1 MHz to investigate the interaction with cortical and callus tissues. The scattering amplitude variation is calculated in the backward and forward direction, as well. It was found that the scattering amplitude derived from appropriate directions and excitation frequencies could convey significant quantitative information for the evaluation of fracture healing.
Vassiliki T. Potsika, Konstantinos N. Grivas, Theodoros Gortsas, Vasilios C. Protopappas, Demosthenes Polyzos, Dimitrios I. Fotiadis

GBM Modeling with Proliferation and Migration Phenotypes: A Proposal of Initialization for Real Cases

Glioblastoma is the most aggressive tumor originated in the central nervous system. Modeling its evolution is of great interest for therapy planning and early response to treatment assessment. Using a continuous multi-scale growth model, which considers the angiogenic process, oxygen supply and different phenotype expressions, a new method is proposed for setting the initial values of the celular variables, based on a spatiotemporal characterization of their distribution in controlled synthetic simulations. The method is applied to a real case showing an improvement on the dynamic stability, compared to the usual method.
Juan Ortiz-Pla, Elies Fuster-Garcia, Javier Juan-Albarracin, Juan Miguel Garcia-Gomez

PURE: Panoramic Ultrasound Reconstruction by Seamless Stitching of Volumes

For training sonographers in navigating, acquiring, and interpreting ultrasound images, virtual-reality based simulation offers a safe, flexible, and standardized environment. In data-based training simulations, images from a-priori acquired volumes are displayed to the trainee. To understand the relationship between organs, it is necessary to allow for free exploration of the entire anatomy, which is often not possible with the limited field-of-view (FOV) of a single ultrasound volume. Thus, large FOV ultrasound volumes are of paramount importance. Combining several volumes into one larger volume has also potential utility in many other applications, such as diagnostic and operative guidance. In this work, we propose a method for combining several ultrasound volumes with tracked positions into a single large volume by stitching them in a seamless fashion. For stitching, we determine an optimal cut interface such that each pixel value comes from a single image; preserving the inherent speckle texture and preventing any blurring and degradation from common mean/median binning approaches to combining volumes. The cut interface is found based on image content using graphical models optimized by graph-cut. We show that our method produces panoramic reconstructions with seamless transitions between individual 3D acquisitions. Regarding standard deviation in homogeneous regions we get 1–19% loss of ultrasound texture compared to small 3D volumes while mean value interpolation gives a loss of 15–68%. The histograms of our reconstruction match the original histograms of the small 3D volumes almost perfectly with a \(\chi ^2\)-distance of less than 0.01.
Barbara Flach, Maxim Makhinya, Orcun Goksel

Synthesis and Its Applications in Computational Medical Imaging

Frontmatter

Pseudo-healthy Image Synthesis for White Matter Lesion Segmentation

White matter hyperintensities (WMH) seen on FLAIR images are established as a key indicator of Vascular Dementia (VD) and other pathologies. We propose a novel modality transformation technique to generate a subject-specific pathology-free synthetic FLAIR image from a T\(_1\) -weighted image. WMH are then accurately segmented by comparing this synthesized FLAIR image to the actually acquired FLAIR image. We term this method Pseudo-Healthy Image Synthesis (PHI-Syn). The method is evaluated on data from 42 stroke patients where we compare its performance to two commonly used methods from the Lesion Segmentation Toolbox. We show that the proposed method achieves superior performance for a number of metrics. Finally, we show that the features extracted from the WMH segmentations can be used to predict a Fazekas lesion score that supports the identification of VD in a dataset of 468 dementia patients. In this application the automatically calculated features perform comparably to clinically derived Fazekas scores.
Christopher Bowles, Chen Qin, Christian Ledig, Ricardo Guerrero, Roger Gunn, Alexander Hammers, Eleni Sakka, David Alexander Dickie, Maria Valdés Hernández, Natalie Royle, Joanna Wardlaw, Hanneke Rhodius-Meester, Betty Tijms, Afina W. Lemstra, Wiesje van der Flier, Frederik Barkhof, Philip Scheltens, Daniel Rueckert

Registration of Pathological Images

This paper proposes an approach to improve atlas-to-image registration accuracy with large pathologies. Instead of directly registering an atlas to a pathological image, the method learns a mapping from the pathological image to a quasi-normal image, for which more accurate registration is possible. Specifically, the method uses a deep variational convolutional encoder-decoder network to learn the mapping. Furthermore, the method estimates local mapping uncertainty through network inference statistics and uses those estimates to down-weight the image registration similarity measure in areas of high uncertainty. The performance of the method is quantified using synthetic brain tumor images and images from the brain tumor segmentation challenge (BRATS 2015).
Xiao Yang, Xu Han, Eunbyung Park, Stephen Aylward, Roland Kwitt, Marc Niethammer

Generation of Realistic 4D Synthetic CSPAMM Tagged MR Sequences for Benchmarking Cardiac Motion Tracking Algorithms

This paper introduces a novel pipeline for synthesizing realistic 3D+t CSPAMM cardiac tagged magnetic resonance (MR) images. The proposed framework is based on the combination of an electro-mechanical model for generating cardiac deformation fields and a template tagging recording for assigning realistic voxel intensities. We developed a spatio-temporal alignment strategy for mapping voxel positions in the simulation space to the template recording space. As a preliminary result, we generated a synthetic dataset of a normal heart, and further compared the performance of two state-of-the-art cardiac motion tracking algorithms using this synthetic data. In this study, we aim at showing the capability of the proposed pipeline to simulate realistic cardiac tagged MR images, and its extension to more synthetic cases especially pathological ones are currently left to future work.
Yitian Zhou, Mathieu De Craene, Oudom Somphone, Maxime Sermesant, Olivier Bernard

Geometry Regularized Joint Dictionary Learning for Cross-Modality Image Synthesis in Magnetic Resonance Imaging

Multi-sequence MRI protocols are used in comprehensive examinations of various pathologies in both clinical diagnosis and medical research. Various MRI techniques provide complementary information about living tissue. However, a comprehensive examination covering all modalities is rarely achieved due to considerations of cost, patient comfort, and scanner time availability. This may lead to incomplete records owing to image artifacts or corrupted or lost data. In this paper, we explore the problem of synthesizing images for one MRI modality from an image of another MRI modality of the same subject using a novel geometry regularized joint dictionary learning framework for non-local patch reconstruction. Firstly, we learn a cross-modality joint dictionary from a multi-modality image database. Training image pairs are first co-registered. A cross-modality dictionary pair is then jointly learned by minimizing the cross-modality divergence via a Maximum Mean Discrepancy term in the objective function of the learning scheme. This guarantees that the distribution of both image modalities is taken jointly into account when building the resulting sparse representation. In addition, in order to preserve intrinsic geometrical structure of the synthesized image patches, we further introduced a graph Laplacian regularization term into the objective function. Finally, we present a patch-based non-local reconstruction scheme, providing further fidelity of the synthesized images. Experimental results demonstrate that our method achieves significant performance gains over previously published techniques.
Yawen Huang, Leandro Beltrachini, Ling Shao, Alejandro F. Frangi

Whole Image Synthesis Using a Deep Encoder-Decoder Network

The synthesis of medical images is an intensity transformation of a given modality in a way that represents an acquisition with a different modality (in the context of MRI this represents the synthesis of images originating from different MR sequences). Most methods follow a patch-based approach, which is computationally inefficient during synthesis and requires some sort of ‘fusion’ to synthesize a whole image from patch-level results. In this paper, we present a whole image synthesis approach that relies on deep neural networks. Our architecture resembles those of encoder-decoder networks, which aims to synthesize a source MRI modality to an other target MRI modality. The proposed method is computationally fast, it doesn’t require extensive amounts of memory, and produces comparable results to recent patch-based approaches.
Vasileios Sevetlidis, Mario Valerio Giuffrida, Sotirios A. Tsaftaris

Automated Quality Assessment of Cardiac MR Images Using Convolutional Neural Networks

Image quality assessment (IQA) is crucial in large-scale population imaging so that high-throughput image analysis can extract meaningful imaging biomarkers at scale. Specifically, in this paper, we address a seemingly basic yet unmet need: the automatic detection of missing (apical and basal) slices in Cardiac Magnetic Resonance Imaging (CMRI) scans, which is currently performed by tedious visual assessment. We cast the problem as classification tasks, where the bottom and top slices are tested for the presence of typical basal and apical patterns. Inspired by the success of deep learning methods, we train Convolutional Neural Networks (CNN) to construct a set of discriminative features. We evaluated our approach on a subset of the UK Biobank datasets. Precision and Recall figures for detecting missing apical slice (MAS) (81.61 % and 88.73 %) and missing basal slice (MBS) (74.10 % and 88.75 %) are superior to other state-of-the-art deep learning architectures. Cross-dataset experiments show the generalization ability of our approach.
Le Zhang, Ali Gooya, Bo Dong, Rui Hua, Steffen E. Petersen, Pau Medrano-Gracia, Alejandro F. Frangi

Patch Based Synthesis of Whole Head MR Images: Application To EPI Distortion Correction

Different magnetic resonance imaging pulse sequences are used to generate image contrasts based on physical properties of tissues, which provide different and often complementary information about them. Therefore multiple image contrasts are useful for multimodal analysis of medical images. Often, medical image processing algorithms are optimized for particular image contrasts. If a desirable contrast is unavailable, contrast synthesis (or modality synthesis) methods try to “synthesize” the unavailable constrasts from the available ones. Most of the recent image synthesis methods generate synthetic brain images, while whole head magnetic resonance (MR) images can also be useful for many applications. We propose an atlas based patch matching algorithm to synthesize \(T_2-\)w whole head (including brain, skull, eyes etc.) images from \(T_1-\)w images for the purpose of distortion correction of diffusion weighted MR images. The geometric distortion in diffusion MR images due to inhomogeneous \(B_0\) magnetic field are often corrected by non-linearly registering the corresponding \(b=0\) image with zero diffusion gradient to an undistorted \(T_2-\)w image. We show that our synthetic \(T_2-\)w images can be used as a template in absence of a real \(T_2-\)w image. Our patch based method requires multiple atlases with \(T_1\) and \(T_2\) to be registered to a given target \(T_1\). Then for every patch on the target, multiple similar looking matching patches are found on the atlas \(T_1\) images and corresponding patches on the atlas \(T_2\) images are combined to generate a synthetic \(T_2\) of the target. We experimented on image data obtained from 44 patients with traumatic brain injury (TBI), and showed that our synthesized \(T_2\) images produce more accurate distortion correction than a state-of-the-art registration based image synthesis method.
Snehashis Roy, Yi-Yu Chou, Amod Jog, John A. Butman, Dzung L. Pham

MRI-TRUS Image Synthesis with Application to Image-Guided Prostate Intervention

Accurate and robust fusion of pre-procedure magnetic resonance imaging (MRI) to intra-procedure trans-rectal ultrasound (TRUS) imaging is necessary for image-guided prostate cancer biopsy procedures. The current clinical standard for image fusion relies on non-rigid surface-based registration between semi-automatically segmented prostate surfaces in both the MRI and TRUS. This surface-based registration method does not take advantage of internal anatomical prostate structures, which have the potential to provide useful information for image registration. However, non-rigid, multi-modal intensity-based MRI-TRUS registration is challenging due to highly non-linear intensities relationships between MRI and TRUS. In this paper, we present preliminary work using image synthesis to cast this problem into a mono-modal registration task by using a large database of over 100 clinical MRI-TRUS image pairs to learn a joint model of MR-TRUS appearance. Thus, given an MRI, we use this learned joint appearance model to synthesize the patient’s corresponding TRUS image appearance with which we could potentially perform mono-modal intensity-based registration. We present preliminary results of this approach.
John A. Onofrey, Ilkay Oksuz, Saradwata Sarkar, Rajesh Venkataraman, Lawrence H. Staib, Xenophon Papademetris

Automatic Generation of Synthetic Retinal Fundus Images: Vascular Network

This work is part of an ongoing project aimed to generate synthetic retinal fundus images. This paper concentrates on the generation of synthetic vascular networks with realistic shape and texture characteristics. An example-based method, the Active Shape Model, is used to synthesize reliable vessels’ shapes. An approach based on Kalman Filtering combined with an extension of a Multiresolution Hermite vascular cross-section model has been developed for the simulation of vessels’ textures. The proposed method is able to generate realistic synthetic vascular networks with morphological properties that guarantee the correct flow of the blood and the oxygenation of the retinal surface as observed with fundus cameras. The validity of our synthetic retinal images is demonstrated by qualitative assessment and quantitative analysis.
Elisa Menti, Lorenza Bonaldi, Lucia Ballerini, Alfredo Ruggeri, Emanuele Trucco

Backmatter

Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!

Bildnachweise