Guiding Multimodal Registration with Learned Optimization Updates
Multimodal image registration is a fundamental task in medical image analysis, consisting in the alignment of two images of a given anatomical location acquired with different modalities. Multimodal registration is an important tool in clinical diagnosis, image-guided interventions, medical augmented reality, as well as in the validation of new imaging modalities (Markelj et al., 2012; Navab et al., 2016). In all these applications multimodal registration plays the key role of bringing and presenting complementary information in a spatially consistent way. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 6, 2017 Category: Radiology Authors: Benjamin Gutierrez-Becker, Diana Mateus, Loic Peter, Nassir Navab Source Type: research
Automatic Online Layer Separation for Vessel Enhancement in X-ray Angiograms for Percutaneous Coronary Interventions
Percutaneous coronary intervention (PCI) is a minimally invasive procedure for patients with advanced coronary artery disease. In this procedure, a stent pre-mounted on a delivery catheter is advanced over a guide-wire and through a guiding catheter at the site of narrowing in a patient ’s coronary arteries. Once the lesion site is reached, the delivery balloon is inflated and the stent is deployed against the coronary wall, assuring optimal patency of the artery. As there is no direct eyesight on the target area, these procedures are commonly performed under image guidance using X-ray angiography (XA), where coronary ar...
Source: Medical Image Analysis - May 5, 2017 Category: Radiology Authors: Hua Ma, Ayla Hoogendoorn, Evelyn Regar, Wiro J. Niessen, Theo van Walsum Source Type: research
Motion-robust parameter estimation in abdominal diffusion-weighted MRI by simultaneous image registration and model estimation
Quantitative diffusion-weighted MRI (DW-MRI) parameters have been increasingly used for the characterization of abnormalities in tissue microstructure of liver, spleen and bowel [4,11,29,26]. The water molecule mobility attenuates the diffusion-weighted MR signal according to the b-value used in the acquisition. Typically, DW-MRI images are acquired at multiple b-values. A signal decay model is then fitted to the measured signal and the signal decay rate parameters are co mputed. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 3, 2017 Category: Radiology Authors: Sila Kurugol, Moti Freiman, Onur Afacan, Liran Domachevsky, Jeannette M. Perez-Rossello, Michael J. Callahan, Simon K. Warfield Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - April 28, 2017 Category: Radiology Source Type: research
Deep Image Mining for Diabetic Retinopathy Screening
Retinal pathologies are responsible for millions of blindness cases worldwide. The leading causes of blindness are glaucoma (4.5 million cases), age-related macular degeneration (3.5 million cases) and diabetic retinopathy (2 million cases).1 Early diagnosis is the key to slowing down the progression of these diseases and therefore preventing the occurrence of blindness. In the case of diabetic retinopathy (DR) screening, diabetic patients have their retinas examined regularly: a trained reader searches for the early signs of the pathology in fundus photographs (see Fig. 1) and decides whether the patient should be refer...
Source: Medical Image Analysis - April 28, 2017 Category: Radiology Authors: Gwenol é Quellec, Katia Charrière, Yassine Boudi, Béatrice Cochener, Mathieu Lamard Source Type: research
Slice-to-volume medical image registration: a survey
Image registration is the process of aligning and combining data coming from more than one image source into a unique coordinate system. This problem has become one of the pillars of computer vision and medical imaging. Slice-to-volume registration, a particular case of image registration problem, has received further attention in the medical imaging community during the last decade. In this case, instead of registering images with same dimension, we seek to determine the slice (corresponding to an arbitrary plane) from a given 3D volume that corresponds to an input 2D image. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 28, 2017 Category: Radiology Authors: Enzo Ferrante, Nikos Paragios Source Type: research
Continuous Representations of Brain Connectivity using Spatial Point Processes
In recent years the study of structural and functional brain connectivity has expanded rapidly. Following the rise of diffusion and functional MRI, connectomics has unlocked a wealth of knowledge to be explored. Almost synonymous with the connectome is the network-theory based representation of the brain (Sporns et al., 2000). In much of the recent literature the quantitative analysis of connectomes has focused on region-to-region connectivity. This paradigm equates physical brain regions with nodes in a graph, and uses observed structural measurements or functional correlations as a proxy for edge strengths between node...
Source: Medical Image Analysis - April 28, 2017 Category: Radiology Authors: Daniel Moyer, Boris A. Gutman, Joshua Faskowitz, Neda Jahanshad, Paul M. Thompson Source Type: research
ShapeCut: Bayesian Surface Estimation Using Shape-Driven Graph
Medical image segmentation typically deals with partitioning an image into multiple regions representing anatomical objects of interest. A three-dimensional segmentation can be viewed as either apixel classification (defining regions) or a surface estimation (boundaries of regions), and in this paper we deal with the latter approach. Heterogeneous pixel intensities, noisy diffuse boundaries and irregular shapes are some factors that make it difficult to develop accurate, robust segmentation algorithms for certain classes of images and anatomy. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 27, 2017 Category: Radiology Authors: Gopalkrishna Veni, Shireen Y. Elhabian, Ross T. Whitaker Source Type: research
A Hybrid Patient-Specific Biomechanical Model Based Image Registration Method for the Motion Estimation of Lungs
Respiratory motion can cause artefacts in images during thorax and abdomen imaging. Accurate estimation and correction for the effects of respiratory motion can potentially increase the applications of medical images in diagnosis, treatment planning and image-guided interventions etc. (McClelland et al., 2013). A wide range of different techniques including biomechanical models, intensity-based image registration or hybrid methods have been proposed for estimating lung motion (Murphy et al., 2011; Fuerst et al., 2015), but most research efforts are put on intensity-based image registration techniques. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 19, 2017 Category: Radiology Authors: Lianghao Han, Hua Dong, Jamie McClelland, L.X. Han, David Hawkes, Dean Barratt Source Type: research
Fully-Automatic Left Ventricular Segmentation from Long-Axis Cardiac Cine MR Scans
Cardiovascular related complications are quite common throughout the world (Mendis et al., 2011; Celermajer et al., 2012). For better understanding of cardiovascular diseases and screening, large population-based cohort studies are gaining popularity (Fox et al., 2009; Hegenscheid et al., 2009; Jefferson et al., 2011; Bamberg et al., 2015). Cardiac magnetic resonance (CMR) doe s not have harmful ionizing radiation, does not require contrast materials and can be used to obtain a number of anatomical and functional parameters. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 14, 2017 Category: Radiology Authors: Rahil Shahzad, Qian Tao, Oleh Dzyubachyk, Marius Staring, Boudewijn P.F. Lelieveldt, Rob J. van der Geest Source Type: research
Learning Non-rigid Deformations for Robust, Constrained Point-based Registration in Image-Guided MR-TRUS Prostate Intervention
Accurate and robust non-rigid image registration is critical for image-guided interventions. Non-rigid registration is a challenging task that is further complicated if the fusion involves images of different modalities. Intensity-based registration algorithms must deal with complex intensity relationships, which makes finding the optimal solution difficult. As an alternative to maximizing an intensity-based similarity metric, such as mutual information, anatomical structures of interest may first be segmented from the images, and then be registered to each other to perform the image fusion. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 13, 2017 Category: Radiology Authors: John A. Onofrey, Lawrence H. Staib, Saradwata Sarkar, Rajesh Venkataraman, Cayce B. Nawaf, Preston C. Sprenkle, Xenophon Papademetris Source Type: research
Convolutional neural network regression for short-axis left ventricle segmentation in cardiac cine MR sequences
Cardiovascular diseases (CVDs) are the most common cause of death globally; it is estimated that 31% of all global deaths in 2012 were due to CVDs (Low et al., 2014; Mendis, 2014). Cardiac MRI is currently considered the gold standard for the assessment of various aspects of CVDs, particularly congenital heart diseases (Faridah Abdul Aziz et al., 2013). Quantification of key cardiac MR images is now recommended as a standard diagnostic procedure by cardiovascular expert groups (Schulz-Menger et al., 2013), including the calculation of left ventricular (LV) end-diastolic (ED) and end-systolic (ES) volumes. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 13, 2017 Category: Radiology Authors: Li Kuo Tan, Yih Miin Liew, Einly Lim, Robert A. McLaughlin Source Type: research
Maximum likelihood estimation of cardiac fiber bundle orientation from arbitrarily spaced diffusion weighted images
Diffusion Weighted Magnetic Resonance Imaging (DW-MRI) is capable to measure the fiber architecture of tissues non-invasively (Basser et al., 1994). Based on the relation between gray values within a pulsed gradient spin echo experiment (Stejskal and Tanner, 1965):
the tissue anisotropy information – represented as diffusion tensor – can be connected with the diffusion encoding directions and the measured gray values . Since the diffusion tensor is symmetric positive definite, at least 6 gray value measurements plus one non-weighted reference measurement are required to estimate all diffusion tensor components, but u...
Source: Medical Image Analysis - April 4, 2017 Category: Radiology Authors: Andreas Nagler, Crist óbal Bertoglio, Christian T. Stoeck, Sebastian Kozerke, Wolfgang A. Wall Source Type: research
Quantifying the brain's sheet structure with normalized convolution
A recent debate on the existence of ‘sheet structures’ in the brain has gained much attention from the neuroscience and diffusion MRI (dMRI) communities (Catani et al., 2012; Wedeen et al., 2012a; Wedeen et al., 2012b). While the term sheets had already been suggested in several contexts before (Kindlmann et al., 2007; Schultz et al., 2010; Smith et al., 2006; Vilanova et al., 2004; Yushkevich et al., 2008; Zhang et al., 2003), Wedeen et al. (2012b) proposed a different and specific definition of brain sheet structure: a composition of two sets of tracts that locally cross each other on the same surface. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 4, 2017 Category: Radiology Authors: Chantal M.W. Tax, Carl-Fredrik Westin, Tom Dela Haije, Andrea Fuster, Max A. Viergever, Evan Calabrese, Luc Florack, Alexander Leemans Source Type: research
Geodesic Shape Regression with Multiple Geometries and Sparse Parameters
The analysis and monitoring of change over time is fundamental to many problems in medicine, where anatomical change is often driven by a continuous dynamic process, such as in early childhood development, aging, or disease progression. Measuring and understanding change over time is required to assess development. For example, head circumference is measured during pediatric examination and compared to a standardized model to determine if a child is developing along a normative trajectory. In addition to assessment, measuring change over time is essential to monitor treatment, or the effectiveness of drug therapy. (Source:...
Source: Medical Image Analysis - March 31, 2017 Category: Radiology Authors: James Fishbaugh, Stanley Durrleman, Marcel Prastawa, Guido Gerig Source Type: research
