Supervised learning for bone shape and cortical thickness estimation from CT images for finite element analysis
Hip fracture is a common injury among the elderly population (Cauley, 2013). Associated with high morbidity and mortality rates, such incident in hip fractures are particularly debilitating, often leads to a loss of independence and are responsible for substantial health-care costs (Cauley et al., 2016). Aside from alterations of the trabecular structure and density (Taghizadeh et al., 2017), mounting evidence suggests that the fracture risk is also largely amplified by the local thinning of the cortex resulting from osteoporosis (Mayhew et al., 2005; Poole et al., 2017). (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 16, 2018 Category: Radiology Authors: Vimal Chandran, Ghislain Maquer, Thomas Gerig, Philippe Zysset, Mauricio Reyes Source Type: research
CATARACTS: Challenge on Automatic Tool Annotation for cataRACT Surgery
Video recording is a unique solution to collect information about a surgery. Combined with computer vision and machine learning, it allows a wide range of applications, including automatic report generation, surgical skill evaluation and training, surgical workflow optimization, as well as warning and recommendation generation. Key indicators of what the surgeon is doing at any given time are the surgical tools that he or she is using. Therefore, several tool detection techniques have been presented in recent years (Bouget et al., 2017). (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 16, 2018 Category: Radiology Authors: Hassan Al Hajj, Mathieu Lamard, Pierre-Henri Conze, Soumali Roychowdhury, Xiaowei Hu, Gabija Mar šalkaitė, Odysseas Zisimopoulos, Muneer Ahmad Dedmari, Fenqiang Zhao, Jonas Prellberg, Manish Sahu, Adrian Galdran, Teresa Araújo, Duc My Vo, Chandan Panda Source Type: research
Motion Artifact Recognition and Quantification in Coronary CT Angiography using Convolutional Neural Networks
Non-invasive coronary computed tomography angiography (CCTA) has become a preferred technique for the detection and diagnosis of coronary artery disease (CAD) (Budoff et al., 2017; Foy et al., 2017; Camargo et al., 2017; Liu et al., 2017), but high quality imaging for small and moving vessels is still challenging. ECG-controlled acquisition is used to enable the reconstruction of heart phases with small motion level and gating windows are limited to the tempora l projection range required for back-projection. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 15, 2018 Category: Radiology Authors: T. Lossau (n ée Elss), H. Nickisch, T. Wissel, R. Bippus, H. Schmitt, M. Morlock, M. Grass Source Type: research
Automatic graph-based method for localization of cochlear implant electrode arrays in clinical CT with sub-voxel accuracy
Cochlear implants (CIs) are surgically implanted devices for treating severe-to-profound hearing loss (National Institute on Deafness and Other Communication Disorders, 2011). A CI uses an electrode array implanted within the cochlea to stimulate the spiral ganglion (SG) nerves to induce the sensation of hearing. The SG nerves are tonotopically ordered by decreasing characteristic frequency along the length of the cochlea (Greenwood, 1990; Stakhovskaya et al., 2007) (Shown in Figure 1). A SG nerve is stimulated when the frequency associated with it exists in the incoming sound (Wilson and Dorman, 2008). (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 13, 2018 Category: Radiology Authors: Yiyuan Zhao, Srijata Chakravorti, Robert F. Labadie, Benoit M. Dawant, Jack H. Noble Source Type: research
Multimodal hyper-connectivity of functional networks using functionally-weighted LASSO for MCI classification
Alzheimer's disease (AD) is the most common cause of dementia in people over 65 years old (Barker et al., 2002; Wilson et al., 2012). Recently, it has been reported that a new case of AD is expected to develop every 33 seconds, and by 2050 it will result in nearly a million new cases each year (Association, 2016, Li et al., 2018a,b). As a prodromal stage of AD, mild cognitive impairment (MCI) has gained a great deal of attention recently due to its high progression rate to AD. Existing studies show that people with MCI, especially MCI involving memory problems (i.e., amnestic MCI), are more likely to develop AD than people...
Source: Medical Image Analysis - November 13, 2018 Category: Radiology Authors: Yang Li, Jingyu Liu, Xinqiang Gao, Biao Jie, Minjeong Kim, Pew-Thian Yap, Chong-Yaw Wee, Dinggang Shen Source Type: research
Quality-based UnwRap of SUbdivided Large Arrays (URSULA) for High-Resolution MRI Data
Multidimensional phase data acquired in Magnetic Resonance Imaging (MRI) reflect the position-dependent, in-plane orientation of the transverse magnetisation, observed within a rotating frame of reference. In a hypothetical ideal experiment on a homogeneous medium, the phase is expected to be constant (zero) throughout the volume. Under realistic conditions, however, phase data reflect inhomogeneities caused by the transmit and receive processes, by the distribution of the static magnetic field and by local electromagnetic tissue properties, such as the magnetic susceptibility and chemical shifts. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 13, 2018 Category: Radiology Authors: J. Lindemeyer, A.-M. Oros-Peusquens, N.J. Shah Source Type: research
Disease Quantification on PET/CT Images without Explicit Object Delineation
It is now generally believed that quantitative radiology (QR), when brought to routine clinical practice, will bring about significant enhancement of the role of radiology in the medical milieu, potentially spawning numerous new advances in medicine. The derivation of quantitative information from images, however, continues to face a major image analysis hurdle, namely the identification and delineation of “objects” of interest in the image. The “object” may be an anatomic organ, a sub-organ, a tissue region, a pathological region, or an anatomic zone such as a well-defined lymph node station. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 10, 2018 Category: Radiology Authors: Yubing Tong, Jayaram K. Udupa, Dewey Odhner, Caiyun Wu, Stephen J. Schuster, Drew A. Torigian Source Type: research
Automatic Brain Labeling via Multi-Atlas Guided Fully Convolutional Networks
Anatomical brain labeling is highly desired for region-based analysis of MR brain images, which is important for many research studies and clinical applications, such as facilitating diagnosis (Zhou, Gennatas et al. 2012, Chen, Zhang et al. 2017) and investigating early brain development (Holland, Chang et al. 2014). Also, brain labeling is a fundamental step in brain network analysis pipelines, where regions-of-interest (ROIs) need to be identified prior to exploring any connectivity traits (Bullmore and Bassett 2011, Liu, Zeng et al. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 1, 2018 Category: Radiology Authors: Longwei Fang, Lichi Zhang, Dong Nie, Xiaohuan Cao, Islem Rekik, Seong-Whan Lee, Huiguang He, Dinggang Shen Source Type: research
A graph-based lesion characterization and deep embedding approach for improved computer-aided diagnosis of nonmass breast MRI lesions
The Breast Imaging Reporting and Data System (BI-RADS) lexicon(Morris et al., 2013) defines a nonmass-like enhancement in breast MR Imaging as an area of enhancement distinct from the surrounding parenchyma, that is not a space-occupying mass or a focus ( (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 1, 2018 Category: Radiology Authors: Cristina Gallego-Ortiz, Anne L. Martel Source Type: research
Hierarchical segmentation using equivalence test (HiSET): Application to DCE image sequences
DCE (dynamic contrast enhanced) imaging using computed tomography (CT), magnetic resonance imaging (MRI) or ultrasound imaging (US) appears promising as it can monitor the local changes in microcirculation secondary to the development of new vessels (neo-angiogenesis). DCE-MRI and DCE-CT (called also CT-perfusion) have been extensively tested alone or in combination with other techniques (Winfield et al., 2016) in pathological conditions such as cancer, ischemia and inflammation, in various tissues including brain (Bergamino et al., 2014), breast (Chen et al., 2010), prostate (Sanz-Requena et al., 2016), heart (Bakir ...
Source: Medical Image Analysis - October 27, 2018 Category: Radiology Authors: Fuchen Liu, Charles-Andr é Cuenod, Isabelle Thomassin-Naggara, Stéphane Chemouny, Yves Rozenholc Source Type: research
A Collaborative Computer Aided Diagnosis (C-CAD) System with Eye-Tracking, Sparse Attentional Model, and Deep Learning
Lung cancer screening with low dose computed tomography (CT) was shown to reduce lung cancer mortality by 20% (Siegel et al., 2017). Yet, human error remains a significant problem to detect abnormalities. For instance, Missing a tumor (recognition error) and misdiagnosing (decision making error) are called perceptual errors (Kundel et al., 1978). It’s reported that 35% of lung nodules are typically missed during the screening process (Caroline, 2014). Over-diagnosis is another significant bias leading to unnecessary treatment which can cause harm and unnecessary medical expenses. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 27, 2018 Category: Radiology Authors: Naji Khosravan, Haydar Celik, Baris Turkbey, Elizabeth C. Jones, Bradford Wood, Ulas Bagci Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - October 26, 2018 Category: Radiology Source Type: research
Reproducibility and intercorrelation of graph theoretical measures in structural brain connectivity networks
Diffusion-weighted (DW1) magnetic resonance imaging (MRI) can be used to noninvasively investigate the microstructural properties of the brain. Diffusion in fiber tracts is anisotropic, i.e. larger parallel to the tract than perpendicular to it, which enables the reconstruction of neural pathways in the brain with fiber tracking [9,38]. Diffusion tensor imaging (DTI) is traditionally the most common method used for the analysis of DW-MRI data [7,8]. However, its major limitation is the inability to correctly describe complex fiber configurations such as crossing fibers, present in the majority of white matter (WM) [40,...
Source: Medical Image Analysis - October 26, 2018 Category: Radiology Authors: Timo Roine, Ben Jeurissen, Daniele Perrone, Jan Aelterman, Wilfried Philips, Jan Sijbers, Alexander Leemans Source Type: research
3D Regression Neural Network for the Quantification of Enlarged Perivascular Spaces in Brain MRI
This paper addresses the problem of automated quantification of enlarged perivascular spaces from MR images. The perivascular space - also called Virchow-Robin space - is the space between a vein or an artery and pia mater, the envelope covering the brain. These spaces are known to have a tendency to dilate for reasons not yet clearly understood (Adams et al., 2015). Enlarged - or dilated - perivascular spaces (EPVS) can be identified as hyperintensities on T2-weighted MRI. In Fig. 1, we show examples of EPVS in T2-weighted scans. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 25, 2018 Category: Radiology Authors: Florian Dubost, Hieab Adams, Gerda Bortsova, M. Arfan Ikram, Wiro Niessen, Meike Vernooij, Marleen de Bruijne Source Type: research
Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier
Accurate information about the geometry and topology of a patient ’s vasculature is crucial for many medical applications. In patients with suspected coronary artery disease, information about the cardiac vasculature may be obtained non-invasively using a cardiac CT angiography (CCTA) scan (Leipsic et al., 2014). A typical first step in the analysis of CCTA sca ns is the extraction of coronary artery lumen centerlines, which allow multi-planar reconstructions that facilitate stenosis detection and plaque identification. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 22, 2018 Category: Radiology Authors: Jelmer M. Wolterink, Robbert W. van Hamersvelt, Max A. Viergever, Tim Leiner, Ivana I šgum Source Type: research
