Ω-Net (Omega-Net): Fully Automatic, Multi-View Cardiac MR Detection, Orientation, and Segmentation with Deep Neural Networks
Pixelwise segmentation of the left ventricular (LV) myocardium and the four cardiac chambers in 2-D steady state free precession (SSFP) cine sequences is an essential preprocessing step for volume estimation (e.g., ejection fraction, stroke volume, and cardiac output); morphological characterization (e.g., myocardial mass, regional wall thickness and thickening, and eccentricity); and strain analysis (Peng et al., 2016). However, automatic cardiac segmentation remains a notoriously difficult problem, given: (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 22, 2018 Category: Radiology Authors: Davis M. Vigneault, Weidi Xie, Carolyn Y. Ho, David A. Bluemke, J. Alison Noble Source Type: research
Superpixel and multi-atlas based fusion entropic model for the segmentation of X-ray images
X-ray images are used by physicians all over the world for the preliminary diagnosis of several bone diseases, to plan surgical intervention, and for pre and post-operative treatments. In this context, accurate extraction of bone contours or regions from these 2D X-ray images, is often the preliminary, and also crucial, step for three-dimensional (3D) bone reconstruction which can then be a great help in determining the extent of a fracture or for improving the diagnosis, follow-up, and treatment of major bone diseases, such as osteoporosis and osteoarthritis. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 18, 2018 Category: Radiology Authors: D.C.T. Nguyen, S. Benameur, M. Mignotte, F. Lavoie Source Type: research
Automated Comprehensive Adolescent Idiopathic Scoliosis Assessment using MVC-Net
Adolescent Idiopathic Scoliosis (AIS) is the most common type of spinal deformity that occurs in children at the onset of puberty (Weinstein et al., 2008). Large cross-continental studies have shown that the prevalence of AIS can be as high as 5.2% and progression of large spinal deformities leads to poor quality of life and complications from injury to the heart and lungs (Asher and Burton, 2006). Clinicians currently make treatment deci sions by assessing the degree of spinal deformity. It is therefore essential to have a reliable way of measuring spinal deformations. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 18, 2018 Category: Radiology Authors: Hongbo Wu, Chris Bailey, Parham Rasoulinejad, Shuo Li Source Type: research
The challenge of cerebral magnetic resonance imaging in neonates: A new method using mathematical morphology for the segmentation of structures including diffuse excessive high signal intensities.
Thanks to the progress in neonatology, more than 85% of premature newborns survive (Victora et al., 2016). However, premature birth remains a leading cause of morbidity and mortality. The brain develops rapidly during the third trimester of pregnancy and can be explored precisely by magnetic resonance imaging (MRI) in the prenatal and the postnatal periods (Parazzini et al., 2008; Tilea et al., 2009; Viola et al., 2011). Indeed, automated quantification of the cortical folding in a population of preterms, newborns and infants has been investigated in (Dubois et al., 2016), showing promising results. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 17, 2018 Category: Radiology Authors: Yongchao Xu, Baptiste Morel, Sonia Dahdouh, Élodie Puybareau, Alessio Virzí, Héléne Urien, Thierry Géraud, Catherine Adamsbaum, Isabelle Bloch Source Type: research
Complex networks reveal early MRI markers of Parkinson ’s disease
Parkinson ’s disease (PD) is a heterogeneous progressive neurological disorder, firstly described almost two centuries ago, basically related with early death of dopaminergic neurons in the substantia nigra and characterized by both motor and non-motor features (Gibb and Lees, 1988; Jankovic, 2008). It is r ecognized that age is the greatest risk factor for PD, its incidence reaches a maximum at about 80 years of age, thus the rising life expectancy is expected to increase the number of patients at more than 30% by 2030 (Dorsey et al., 2007). (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 17, 2018 Category: Radiology Authors: Nicola Amoroso, Marianna La Rocca, Alfonso Monaco, Roberto Bellotti, Sabina Tangaro Source Type: research
Quantifying the Uncertainty in Model Parameters Using Gaussian Process-Based Markov Chain Monte Carlo in Cardiac Electrophysiology
Model personalization requires the estimation of patient-specific tissue properties in the form of model parameters from indirect and sparse measurement data. Moreover, a low-dimensional representation of the parameter space is needed, which often has a limited ability to reveal the underlying tissue heterogeneity. As a result, significant uncertainty can be associated with the estimated values of the model parameters which, if left unquantified, will lead to unknown variability in model outputs that will hinder their reliable clinical adoption. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 17, 2018 Category: Radiology Authors: Jwala Dhamala, Hermenegild J. Arevalo, John Sapp, B. Milan Hor ácek, Katherine C. Wu, Natalia A. Trayanova, Linwei Wang Source Type: research
Joint Spatial-Angular Sparse Coding for dMRI with Separable Dictionaries
Diffusion magnetic resonance imaging (dMRI) is a medical imaging modality used to analyze neuroanatomical biomarkers for brain diseases such as Alzheimer ’s. dMRI are 6D signals consisting of a set of 3D spatial MRI volumes acquired in k-space that are each weighted with a different diffusion signal measured in q-space. In each voxel of a brain dMRI, the q-space diffusion signals are reconstructed to estimate orientations and integrity of neuronal fiber tracts, in vivo. Different dMRI protocols measure q-space in different ways. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 15, 2018 Category: Radiology Authors: Evan Schwab, Ren é Vidal, Nicolas Charon Source Type: research
Monitoring Tool Usage in Surgery Videos using Boosted Convolutional and Recurrent Neural Networks
With the emergence of imaging devices in the operating room, the automated analysis of videos recorded during the surgery is becoming a hot research topic. In particular, videos can be used to monitor the surgery, for instance by recognizing which surgical tools are being used at every moment. An immediate application of surgery monitoring is report generation. If automatic reports are available for many surgeries, then the automatic analysis of these reports can help optimize the surgical workflow or evaluate surgical skills. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 9, 2018 Category: Radiology Authors: Hassan Al Hajj, Mathieu Lamard, Pierre-Henri Conze, B éatrice Cochener, Gwenolé Quellec Source Type: research
Weighted Regularized statistical shape space projection for breast 3D model reconstruction
During last years, 3D reconstruction has been of great interest for researchers due to the great variety of applications in which it can be used such as medical image analysis, video games, film industry, virtual reality or animation. The literature about the different areas in computer vision that are involved in 3D reconstruction has been considerably increased. One of the fields where this technology can be applied and where 3D reconstruction has gained popularity is in the plastic and reconstructive surgery sector. (Source: Medical Image Analysis)
Source: Medical Image Analysis - May 2, 2018 Category: Radiology Authors: Guillermo Ruiz, Eduard Ramon, Jaime Garc ía, Federico M. Sukno, Miguel A. González Ballester Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - April 27, 2018 Category: Radiology Source Type: research
Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization
Reconstructing concurrent functional brain networks from fMRI blood oxygen level dependent (BOLD) data has been investigated for decades. The reconstructed concurrent functional brain networks help us better understand functional human brain activities and their underlying neural substrates. Traditionally, independent component analysis (ICA) (Cole et al., 2010; McKeown et al., 2003) and general linear model (GLM) (Friston et al., 1994; Logothetis, 2008) have been widely utilized for resting state functional networks and task-evoked functional networks, respectively. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 27, 2018 Category: Radiology Authors: Yu Zhao, Fangfei Ge, Tianming Liu Source Type: research
A Work Flow to Build and Validate Patient Specific Left Atrium Electrophysiology Models from Catheter Measurements
Atrial fibrillation (AF) is a supra-ventricular tachyarrhythmia that is characterised by an uncoordinated activation of the atrial tissue (Skanes et al. (1998); Konings et al. (1994)), with a consequent deterioration of mechanical function, Reant et al. (2005). AF is associated with an increased incidence of other cardiovascular diseases, stroke and premature death, Chugh et al. (2013). In drug refractory patients, AF is commonly treated by radio-frequency ablation Haïssaguerre et al. (2000); Oral et al. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 27, 2018 Category: Radiology Authors: Cesare Corrado, Steven Williams, Rashed Karim, Gernot Plank, Mark O ’Neill, Steven Niederer Source Type: research
VP-Nets : Efficient Automatic Localization of Key Brain Structures in 3D Fetal Neurosonography
Highlights (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 23, 2018 Category: Radiology Authors: Ruobing Huang, Weidi Xie, J.Alison Noble Source Type: research
A Probabilistic Approach to Joint Cell Tracking and Segmentation in High-Throughput Microscopy Videos
Thanks to advances in automation, thousands of cell populations can be perturbed and recorded by an automated microscope, making live cell imaging a widespread and versatile platform for quantitative analysis of cellular processes. Nevertheless, the pace of modern imaging far outstrips the capability of biologists to manually analyse the resulting movies. Automated image processing can extract a richness of quantitative measures far beyond what a human can observe. Yet, to fully exploit the power of live-cell imaging, a spatiotemporal tracing of multiple cells in a dynamic environment is required. (Source: Medical Image Analysis)
Source: Medical Image Analysis - April 20, 2018 Category: Radiology Authors: Assaf Arbelle, Jose Reyes, Jia-Yun Chen, Galit Lahav, Tammy Riklin Raviv Source Type: research
