Spine-GAN: Semantic Segmentation of Multiple Spinal Structures
Spinal diseases greatly limit body mobility, block nervous system, and deteriorate quality of life worldwide. For instance, neural foraminal stenosis (NFS)1 often causes muscle weakness and body disability, and NFS has attacked about 80% of the elderly population (Kaneko et al., 2012; Rajaee et al., 2012). In another instance, intervertebral disc degeneration (IDD) easily induces chronic back pain and body functional incapacity, while IDD is responsible for over 90% of spine surgical procedures (He et al., 2017a). (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 24, 2018 Category: Radiology Authors: Zhongyi Han, Benzheng Wei, Ashley Mercado, Stephanie Leung, Shuo Li Source Type: research
Algorithms for left atrial wall segmentation and thickness – Evaluation on an open-source CT and MRI image database
In the past decade, algorithms for medical image analysis have grown rapidly with the availability of several open-source image processing and visualisation libraries. However, translation of these algorithms to the clinical environment has been limited despite their rapid development. Algorithms are usually validated in-house extensively, but it often remains unclear how they compare to other existing algorithms. Cross comparing the algorithm ’s performance becomes a challenge with the absence of a common pool of data. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 23, 2018 Category: Radiology Authors: Rashed Karim, Lauren-Emma Blake, Jiro Inoue, Qian Tao, Shuman Jia, R. James Housden, Pranav Bhagirath, Jean-Luc Duval, Marta Varela, Jonathan Behar, Lo ïc Cadour, Rob J. van der Geest, Hubert Cochet, Maria Drangova, Maxime Sermesant, Reza Razavi, Oleg As Source Type: research
Algorithms for Left Atrial Wall Segmentation and Thickness - Evaluation on an Open-source CT and MRI Image Database
In the past decade, algorithms for medical image analysis have grown rapidly with the availability of several open-source image processing and visualisation libraries. However, translation of these algorithms to the clinical environment has been limited despite their rapid development. Algorithms are usually validated in-house extensively, but it often remains unclear how they compare to other existing algorithms. Cross comparing the algorithm ’s performance becomes a challenge with the absence of a common pool of data. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 23, 2018 Category: Radiology Authors: Rashed Karim, Lauren-Emma Blake, Jiro Inoue, Qian Tao, Shuman Jia, R. James Housden, Pranav Bhagirath, Jean-Luc Duval, Marta Varela, Jonathan Behar, Loic Cadour, Rob J. van der Geest, Hubert Cochet, Maria Drangova, Maxime Sermesant, Reza Razavi, Oleg Asla Source Type: research
Equilibrated Warping: Finite Element Image Registration with Finite Strain Equilibrium Gap Regularization
Image processing, in particular image registration for motion tracking, is playing an important role in biomedical imaging (Tobon-Gomez et al., 2013; Sotiras et al., 2013) and in other domains such as materials and mechanical engineering (Sutton and Hild, 2015). However, despite important progress made in the past decades, robustness, efficiency and precision of the existing methods must still be improved to translate them into medi cal and engineering applications. In this paper we propose a novel regularization approach that has a strong mechanical basis, and apply it to finite element-based image registration problem...
Source: Medical Image Analysis - August 22, 2018 Category: Radiology Authors: M. Genet, C.T. Stoeck, C. von Deuster, L.C. Lee, S. Kozerke Source Type: research
Automated multi-atlas segmentation of cardiac 4D flow MRI
Magnetic Resonance Imaging (MRI) enables fast and accurate generation of morphological and functional images of the cardiovascular system, and is routinely performed to diagnose and assess the function of the heart and great vessels. In order to extract relevant information from these images in the heart, one of the most important and challenging pre-processing steps is the segmentation of clinically useful cardiac regions, usually relying on manual delineation of the contours by an expert observer. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 13, 2018 Category: Radiology Authors: Mariana Bustamante, Vikas Gupta, Daniel Forsberg, Carl-Johan Carlh äll, Jan Engvall, Tino Ebbers Source Type: research
Fast Iteratively Reweighted Least Squares Algorithms for Analysis-Based Sparse Reconstruction
Ill-posed problems widely exist in medical imaging and computer vision. In order to seek a meaningful solution, regularization is often used if we have certain prior knowledge. With the emerging of compressive sensing (CS) (Candes et al., 2006; Donoho, 2006), sparsity regularization has been an active topic in recent years. If the original data is sparse or compressible, it can be recovered precisely from a small number of measurements. The ℓ1 norm is usually used to induce sparsity and gains great success in many real appli cations. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 7, 2018 Category: Radiology Authors: Chen Chen, Lei He, Hongsheng Li, Junzhou Huang Source Type: research
Unmixing dynamic PET images with variable specific binding kinetics
Dynamic positron emission tomography (PET) is a non-invasive nuclear imaging technique that allows biological processes to be quantified and organ metabolic functions to be evaluated through the three-dimensional measure of the radiotracer concentration over time. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 6, 2018 Category: Radiology Authors: Yanna Cruz Cavalcanti, Thomas Oberlin, Nicolas Dobigeon, Simon Stute, Maria Ribeiro, Clovis Tauber Source Type: research
Building medical image classifiers with very limited data using segmentation networks
With the availability of big data and GPU computing, deep learning has become a powerful technique which raises the benchmarks of classification and detection challenges in computer vision (Schmidhuber, 2015). Using huge databases such as ImageNet which has more than a million annotated images (Deng et al., 2009), deep convolutional neural networks (CNNs) such as AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan and Zisserman, 2014), and GoogLeNet (Szegedy et al., 2015) were proposed with impressive performance in visual pattern recognition. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 3, 2018 Category: Radiology Authors: Ken C.L. Wong, Tanveer Syeda-Mahmood, Mehdi Moradi Source Type: research
Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data
Computer Aided Detection (CAD) techniques play an important role in the process of assessing medical images used in a number of medical sectors ranging from oncology to neurology. The main contribution of CAD is a reduction in the duration of routine steps, thus resulting in fewer mistakes caused by fatigued medical staff and larger amounts of images being assessed. One of the most challenging aspects of the application of CAD is the detection and segmentation of metastases for subsequent time-development analysis and observing responses to treatment. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 2, 2018 Category: Radiology Authors: Jiri Chmelik, Roman Jakubicek, Petr Walek, Jiri Jan, Petr Ourednicek, Lukas Lambert, Elena Amadori, Giampaolo Gavelli Source Type: research
Quantification of the detailed cardiac left ventricular trabecular morphogenesis in the mouse embryo
The development of the myocardium appears to be similar in many vertebrates. In particular, before the intramural cardiac vessels appear, the ventricular walls consist mainly of trabeculations. Those early trabeculations increase myocardial surface area and serve to increase myocardial oxygenation and nutrient delivery by diffusion, while sufficient tissue volume builds up for myocardium development at the later stages. However, the decrease in trabecular complexity does not lead to a disappearance of the trabeculations. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 2, 2018 Category: Radiology Authors: Bruno Paun, Bart Bijnens, Andrew C. Cook, Timothy J. Mohun, Constantine Butakoff Source Type: research
Neural Multi-Atlas Label Fusion: Application to Cardiac MR Images
As one of the most successful medical image segmentation techniques, multi-atlas segmentation (MAS) approach has been applied to various medical image segmentation tasks, including segmentation of abdominal anatomy (Tong et al., 2015; Wang et al., 2014; Wolz et al., 2013; Xu et al., 2015), cardiac ventricle (Xie et al., 2015; Bai et al., 2015; 2013; Zhuang and Shen, 2016), brain (Wu et al., 2014; Asman and Landman, 2013; Coupé et al., 2011; Duc et al., 2013; Artaechevarria et al., 2009; Sanroma et al., 2014; Wang et al., 2013; Cardoso et al., 2013; Asman et al., 2015), etc. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 1, 2018 Category: Radiology Authors: Heran Yang, Jian Sun, Huibin Li, Lisheng Wang, Zongben Xu Source Type: research
Special Issue on MICCAI 2017
We were very proud to host the 20th Medical Image Computing and Computer Assisted Interventions (MICCAI) conference at the Quebec City Conference Center from September 10th to 14th 2017 in Quebec City, Canada. Ce fut un plaisir et une fiert é de vous recevoir tous et chacun à Québec, berceau de la culture francophone en Amérique du Nord. MICCAI 2017 was organized out of Université Laval (Quebec City, Canada) in collaboration with the German Cancer Research Center (Heidelberg, Germany); McGill University (Montréal, Canada); Univer sité de Rennes I (Rennes, France); and Université de Sherbrooke (Sherbrooke, Canada). ...
Source: Medical Image Analysis - July 31, 2018 Category: Radiology Authors: Maxime Descoteaux, Lena Maier-Hein, Alfred Franz, Pierre Jannin, D. Louis Collins, Simon Duchesne Tags: Editorial Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - July 31, 2018 Category: Radiology Source Type: research
A Computational Method for Longitudinal Mapping of Orientation-specific Expansion of Cortical Surface in Infants
The cerebral cortex of the human brain is a highly convoluted, sheet-like structure of gray matter, with the cortical folds formed during late gestation (Chi et al., 1977; Dubois et al., 2007; Habas et al., 2011; Kim et al., 2016; Zilles et al., 2013). At term birth, although all primary and secondary cortical folds, as well as many tertiary cortical folds, are well established, both brain volume and cortical surface area are only one-third of those o f adults (Dubois et al., 2007; Hill et al., 2010; Li et al., 2014a). (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 21, 2018 Category: Radiology Authors: Jing Xia, Fan Wang, Yu Meng, Zhengwang Wu, Li Wang, Weili Lin, Caiming Zhang, Dinggang Shen, Gang Li Source Type: research
Segmentation of glandular epithelium in colorectal tumours to automatically compartmentalise IHC biomarker quantification: a deep learning approach
Immunohistochemistry (IHC) is an efficient and routinely used technique to localise a specific antigen in a tissue sample and its cell components. This staining technique is commonly employed for diagnostic and prognostic purposes in histopathology as well as for biomarker validation in clinical research. Whole slide scanning and image analysis tools now enable to objectively and quantitatively evaluate IHC biomarkers in a whole tissue slide or a specific region of interest delineated by a pathologist. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 12, 2018 Category: Radiology Authors: Yves-R émi Van Eycke, Cédric Balsat, Laurine Verset, Olivier Debeir, Isabelle Salmon, Christine Decaestecker Source Type: research
