Multi-hypothesis tracking of the tongue surface in ultrasound video recordings of normal and impaired speech
Observing and characterizing tongue motion is of interest to the study of normal and impaired speech production. Ultrasound (US) imaging is widely used for speech research (Stone, 2005) as it provides a spatially dense representation of the moving tongue at relatively good sampling rates, interferes minimally with natural articulatory processes, and is safe, affordable and portable, and thus suitable for field work. (Source: Medical Image Analysis)
Source: Medical Image Analysis - December 5, 2017 Category: Radiology Authors: Catherine Laporte, Lucie M énard Source Type: research
Automatic spinal cord localization, robust to MRI contrasts using global curve optimization
The spinal cord (SC) plays a key role in the central nervous system by ensuring the conduction of both motor and sensory signaling between the brain and the peripheral nervous systems. Although SC magnetic resonance imaging (MRI) has long been technically challenging, MRI has been increasingly used in the last two decades to provide valuable quantitative information through SC morphometry (Papinutto et al. 2015; Fradet et al. 2014; Martin, De Leener, Cohen-Adad, Cadotte, Kalsi-Ryan, Lange, Tetreault, Nouri, Crawley, Mikulis, and Others 2017) and to evaluate SC damage a range of neurologic disorders such as multiple scleros...
Source: Medical Image Analysis - December 5, 2017 Category: Radiology Authors: Charley Gros, Benjamin De Leener, Sara M. Dupont, Allan R. Martin, Michael G. Fehlings, Rohit Bakshi, Subhash Tummala, Vincent Auclair, Donald G. McLaren, Virginie Callot, Julien Cohen-Adad, Micha ël Sdika Source Type: research
Group-wise similarity registration of point sets using Student ’s t-mixture model for statistical shape models
Statistical shape models (SSMs) have found widespread use in a variety of medical image analysis applications in recent years such as segmentation (Patenaude et al., 2011; Castro-Mateos et al., 2015), shape-based prediction of tissue anisotropy (Lekadir et al., 2014), quantitative shape analysis and classification for computer-aided-diagnosis (Styner et al., 2004; Shen et al., 2012; Gooya et al., 2015b), to name a few. Their primary challenge has per sistently been the availability of training sets of sufficient size, necessary to adequately describe anatomical shape variability observed across different demographic...
Source: Medical Image Analysis - December 2, 2017 Category: Radiology Authors: Nishant Ravikumar, Ali Gooya, Serkan Çimen, Alejandro F. Frangi, Zeike A. Taylor Source Type: research
Learning Non-Linear Patch Embeddings with Neural Networks for Label Fusion
Segmentation of brain structures from magnetic resonance images (MRI) is an important step in many neuroscience applications, including discovery of morphological biomarkers, monitoring disease progression or diagnosis. For example, segmentation is widely used as basic image quantification step in studies of early brain development (Benkarim et al., 2017) and dementia (Chupin et al., 2009; Li et al., 2007). (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 30, 2017 Category: Radiology Authors: Gerard Sanroma, Oualid M. Benkarim, Gemma Piella, Oscar Camara, Guorong Wu, Dinggang Shen, Juan D. Gispert, Jos é Luis Molinuevo, Miguel A. González Ballester, for the Alzheimer’s Disease Neuroimaging Initiative Source Type: research
Gaze Gesture Based Human Robot Interaction for Laparoscopic Surgery
Technological advances over the past decade have enabled the routine use of Minimally Invasive Surgery (MIS) in an increasing number of clinical specialities. MIS offers several benefits to patients including a reduction in operating trauma, post-operative pain, and faster recovery times. It has also led to budgetary benefits for hospitals through cost savings from reduced hospitalisation duration. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 28, 2017 Category: Radiology Authors: Kenko Fujii, Gauthier Gras, Antonino Salerno, Guang-Zhong Yang Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - November 26, 2017 Category: Radiology Source Type: research
Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis
Obstructive coronary artery disease (CAD) is the most common type of heart disease (Mozaffarian et al., 2016). Obstructive CAD occurs when one or more of the coronary arteries which supply blood to myocardium are narrowed owing to plaque buildup on the arteries’ inner walls, causing stenosis. Only functionally significant stenoses, i.e stenoses that significantly limit the blood flow to the m yocardium and lead to myocardial ischemia need to be treated to reduce CAD morbidity (Pijls et al., 1996; Tonino et al., 2009; Pijls et al., 2010; van Nunen et al., 2015). (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 25, 2017 Category: Radiology Authors: Majd Zreik, Nikolas Lessmann, Robbert W. van Hamersvelt, Jelmer M. Wolterink, Michiel Voskuil, Max A. Viergever, Tim Leiner, Ivana I šgum Source Type: research
A Real-time and Registration-free Framework for Dynamic Shape Instantiation
Current clinical systems for minimally invasive procedures, such as cardiac radio-frequency ablation, image-guided needle biopsies, and endovascular interventions, typically incorporate static 3D surfaces for guidance. Real-time dynamic tracking of 3D surfaces can help to optimize the interventional procedure, especially for complex anatomical structures undergoing gross tissue deformation, bulk organ motion, and potential topological changes during interventions. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 25, 2017 Category: Radiology Authors: Xiao-Yun Zhou, Guang-Zhong Yang, Su-Lin Lee Source Type: research
Dictionary-based Fiber Orientation Estimation with Improved Spatial Consistency
Diffusion magnetic resonance imaging (dMRI) captures the anisotropic water diffusion in tissue and enables in vivo reconstruction of white matter tracts (Johansen-Berg and Behrens, 2013). Diffusion tensor imaging (DTI) (Basser et al., 1994) is a basic dMRI strategy that models the water diffusion using a Gaussian distribution, yet it fails to represent crossing fiber tracts. More advanced high angular resolution diffusion imaging (HARDI) (Tuch et al., 2002) and diffusion spectrum imaging (DSI) (Wedeen et al., 2005) have been proposed to resolve crossing fibers. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 23, 2017 Category: Radiology Authors: Chuyang Ye, Jerry L. Prince Source Type: research
The Semiotics of Medical Image Segmentation
The notion of the computer as a blind symbol-processing engine is under-prepared to describe the complexity of modern computational systems and tasks. The idea that any communication with a computer must be symbolic (thus limiting the tool-set used to investigate it) by virtue of the computer's processor operating, on the lowest level, upon zeros and ones is philosophically naive and denies the flexibility of modern input and output methods (both physical and abstract) and their suitability for particular interfaces. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 20, 2017 Category: Radiology Authors: John SH Baxter, Eli Gibson, Roy Eagleson, Terry M. Peters Source Type: research
An Efficient Algorithm for Dynamic MRI Using Low-Rank and Total Variation Regularizations
Dynamic magnetic resonance imaging (dMRI) is an important medical imaging technique that has been widely used for multiple clinical applications. However, dynamic MRI is inherently a very slow process due to a combination of different constraints such as nuclear relaxation times and peripheral nerve stimulation. Since the speed of acquisition in dynamic MRI has physical limits, there exists a trade-off between temporal and spatial resolution. Additionally, long scan durations can make patient uncomfortable and also increase the chance of motion artifacts. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 16, 2017 Category: Radiology Authors: Jiawen Yao, Zheng Xu, Xiaolei Huang, Junzhou Huang Source Type: research
Measurement of the bone endocortical region using clinical CT
Fragility fractures due to osteoporosis and other skeletal diseases are a significant public health burden (Kanis et al., 2013; Organisation, 2007), which is set to increase as the global population continues to age. The societal cost of hip fractures is particularly severe due to high morbidity and mortality associated with this fracture (Organisation, 2007). The quantity and severity of fragility fractures can be reduced through early identification and treatment of those at risk. Fracture risk prediction, treatment assessment and the monitoring of osteoporosis disease progression in the proximal femur are hence all of...
Source: Medical Image Analysis - November 16, 2017 Category: Radiology Authors: R.A. Pearson, G.M. Treece Source Type: research
Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
Segmentation is an active area of research in medical image analysis. With the introduction of Convolutional Neural Networks (CNNs), significant improvements in performance have been achieved in many standard datasets. For example, for the EM ISBI 2012 dataset (Arganda-Carreras et al., 2015), PROMISE12 challenge or MS lesions (Styner et al., 2008), the top entries are built on CNNs (Ronneberger et al., 2015; Chen et al., 2016b; Havaei et al., 2017; Yu et al., 2017). (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 14, 2017 Category: Radiology Authors: Michal Drozdzal, Gabriel Chartrand, Eugene Vorontsov, Mahsa Shakeri, Lisa Di Jorio, An Tang, Adriana Romero, Yoshua Bengio, Chris Pal, Samuel Kadoury Source Type: research
Segmentation of the Hippocampus by Transferring Algorithmic Knowledge for large cohort processing
The essential role played by the hippocampus within the human brain makes it a particularly important target for neuroimaging studies. The hippocampus is well known for its functional involvement in the mechanisms of memory and has also been associated with various diseases or conditions through its very structure, either directly in memory-related disorders such as Alzheimer's Disease (Bobinski et al., 1999; Jack et al., 1999; Laakso et al., 1996; Reiman et al., 1998; Schuff et al., 2009; Šimić et al., 1997) and PTSD (Bonne et al., 2001; Gilbertson et al., 2002; Gurvits et al., 1996; Pederson et al., 2004; Shin et al., ...
Source: Medical Image Analysis - November 10, 2017 Category: Radiology Authors: Benjamin Thyreau, Kazunori Sato, Hiroshi Fukuda, Yasuyuki Taki Source Type: research
Robust Brain ROI Segmentation by Deformation Regression and Deformable Shape Model
Human brain function network is characterized by the functional connectivity of different brain regions (Li et al., 2009; Tzourio-Mazoyer et al., 2002; Fischl et al., 2002). The functional connectivity can be quantified as a connectivity matrix, where each entry measures the Pearson or partial correlation between the functional activities of two brain regions of interest (ROIs) (Liu et al., 2012; Liu an d Ye, 2010). To calculate the connectivity matrix, the brain ROIs need to be segmented from MR images. (Source: Medical Image Analysis)
Source: Medical Image Analysis - November 9, 2017 Category: Radiology Authors: Zhengwang Wu, Yanrong Guo, Sang Hyun Park, Yaozong Gao, Pei Dong, Seong-Whan Lee, Dinggang Shen Source Type: research
